2023-11-02 18:43:33,737 - mmseg - INFO - Multi-processing start method is `None` 2023-11-02 18:43:33,742 - mmseg - INFO - OpenCV num_threads is `128 2023-11-02 18:43:33,742 - mmseg - INFO - OMP num threads is 1 2023-11-02 18:43:33,819 - mmseg - INFO - Environment info: ------------------------------------------------------------ sys.platform: linux Python: 3.8.15 (default, Nov 4 2022, 20:59:55) [GCC 11.2.0] CUDA available: True GPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB CUDA_HOME: /mnt/petrelfs/wangwenhai/miniconda3/envs/mmdetseg NVCC: Cuda compilation tools, release 11.7, V11.7.99 GCC: gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-44) PyTorch: 1.13.0 PyTorch compiling details: PyTorch built with: - GCC 9.3 - C++ Version: 201402 - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - NNPACK is enabled - CPU capability usage: AVX2 - CUDA Runtime 11.7 - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37 - CuDNN 8.5 - Magma 2.6.1 - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, TorchVision: 0.14.0 OpenCV: 4.8.0 MMCV: 1.7.0 MMCV Compiler: GCC 7.3 MMCV CUDA Compiler: 11.7 MMSegmentation: 0.27.0+ ------------------------------------------------------------ 2023-11-02 18:43:33,819 - mmseg - INFO - Distributed training: True 2023-11-02 18:43:34,085 - mmseg - INFO - Config: checkpoint = 'https://download.openmmlab.com/mmsegmentation/v0.5/pretrain/segmenter/vit_base_p16_384_20220308-96dfe169.pth' backbone_norm_cfg = dict(type='LN', eps=1e-06, requires_grad=True) model = dict( type='EncoderDecoder', pretrained= './pretrained/intern_vit_6b_224px.pth', backbone=dict( type='InternViT6B', pretrain_size=224, img_size=504, patch_size=14, embed_dim=3200, depth=48, num_heads=25, mlp_ratio=4.0, qkv_bias=False, drop_path_rate=0.4, init_values=0.1, with_cp=True, use_flash_attn=True, qk_normalization=True, layerscale_no_force_fp32=True, freeze_vit=False, out_indices=[47]), decode_head=dict( type='FCNHead', in_channels=3200, channels=3200, num_convs=0, dropout_ratio=0.0, concat_input=False, num_classes=150, with_norm=True, loss_decode=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)), test_cfg=dict(mode='slide', crop_size=(504, 504), stride=(322, 322))) dataset_type = 'ADE20KDataset' data_root = 'data/ade/ADEChallengeData2016' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) crop_size = (504, 504) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', reduce_zero_label=True), dict(type='Resize', img_scale=(2016, 504), ratio_range=(0.5, 2.0)), dict(type='RandomCrop', crop_size=(504, 504), cat_max_ratio=0.75), dict(type='RandomFlip', prob=0.5), dict(type='PhotoMetricDistortion'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size=(504, 504), pad_val=0, seg_pad_val=255), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_semantic_seg']) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(2016, 504), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='ResizeToMultiple', size_divisor=14), dict(type='RandomFlip'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ] data = dict( samples_per_gpu=2, workers_per_gpu=4, train=dict( type='ADE20KDataset', data_root='data/ade/ADEChallengeData2016', img_dir='images/training', ann_dir='annotations/training', max_image_num=5052, pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', reduce_zero_label=True), dict(type='Resize', img_scale=(2016, 504), ratio_range=(0.5, 2.0)), dict(type='RandomCrop', crop_size=(504, 504), cat_max_ratio=0.75), dict(type='RandomFlip', prob=0.5), dict(type='PhotoMetricDistortion'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='Pad', size=(504, 504), pad_val=0, seg_pad_val=255), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_semantic_seg']) ]), val=dict( type='ADE20KDataset', data_root='data/ade/ADEChallengeData2016', img_dir='images/validation', ann_dir='annotations/validation', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(2016, 504), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='ResizeToMultiple', size_divisor=14), dict(type='RandomFlip'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ]), test=dict( type='ADE20KDataset', data_root='data/ade/ADEChallengeData2016', img_dir='images/validation', ann_dir='annotations/validation', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(2016, 504), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='ResizeToMultiple', size_divisor=14), dict(type='RandomFlip'), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ])) log_config = dict( interval=50, hooks=[ dict(type='TextLoggerHook', by_epoch=False), dict(type='TensorboardLoggerHook') ]) dist_params = dict(backend='nccl') log_level = 'INFO' load_from = None resume_from = None workflow = [('train', 1)] cudnn_benchmark = True optimizer = dict( type='AdamW', lr=4e-05, betas=(0.9, 0.999), weight_decay=0.05, constructor='CustomLayerDecayOptimizerConstructor', paramwise_cfg=dict(num_layers=48, layer_decay_rate=0.95)) optimizer_config = dict() lr_config = dict( policy='poly', warmup='linear', warmup_iters=400, warmup_ratio=1e-06, power=1.0, min_lr=0.0, by_epoch=False) runner = dict(type='IterBasedRunner', max_iters=20000) checkpoint_config = dict( by_epoch=False, interval=1000, deepspeed=True, max_keep_ckpts=2) evaluation = dict( interval=1000, metric='mIoU', pre_eval=True, save_best='auto') deepspeed = True deepspeed_config = 'zero_configs/adam_zero1_bf16.json' pretrained = './pretrained/intern_vit_6b_224px.pth' custom_hooks = [dict(type='ToBFloat16Hook', priority=49)] work_dir = './work_dirs/segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4' gpu_ids = range(0, 8) auto_resume = False 2023-11-02 18:43:38,697 - mmseg - INFO - Set random seed to 1482176558, deterministic: False 2023-11-02 18:44:56,165 - mmseg - INFO - 2023-11-02 18:45:14,425 - mmseg - INFO - initialize FCNHead with init_cfg {'type': 'Normal', 'std': 0.01, 'override': {'name': 'conv_seg'}} Name of parameter - Initialization information backbone.pos_embed - torch.Size([1, 1297, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.cls_token - torch.Size([1, 1, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.patch_embed.proj.weight - torch.Size([3200, 3, 14, 14]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.patch_embed.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.0.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.1.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.2.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.3.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.4.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.5.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.6.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.7.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.8.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.9.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.10.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.11.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.12.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.13.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.14.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.15.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.16.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.17.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.18.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.19.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.20.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.21.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.22.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.23.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.24.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.24.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.24.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.24.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.24.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.24.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.24.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.24.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.24.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.24.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.24.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.24.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.24.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.25.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.25.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.25.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.25.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.25.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.25.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.25.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.25.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.25.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.25.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.25.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.25.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.25.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.26.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.26.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.26.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.26.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.26.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.26.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.26.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.26.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.26.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.26.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.26.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.26.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.26.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.27.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.27.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.27.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.27.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.27.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.27.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.27.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.27.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.27.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.27.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.27.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.27.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.27.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.28.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.28.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.28.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.28.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.28.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.28.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.28.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.28.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.28.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.28.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.28.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.28.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.28.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.29.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.29.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.29.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.29.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.29.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.29.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.29.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.29.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.29.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.29.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.29.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.29.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.29.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.30.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.30.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.30.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.30.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.30.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.30.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.30.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.30.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.30.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.30.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.30.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.30.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.30.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.31.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.31.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.31.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.31.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.31.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.31.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.31.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.31.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.31.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.31.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.31.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.31.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.31.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.32.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.32.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.32.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.32.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.32.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.32.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.32.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.32.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.32.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.32.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.32.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.32.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.32.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.33.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.33.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.33.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.33.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.33.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.33.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.33.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.33.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.33.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.33.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.33.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.33.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.33.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.34.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.34.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.34.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.34.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.34.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.34.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.34.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.34.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.34.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.34.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.34.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.34.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.34.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.35.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.35.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.35.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.35.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.35.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.35.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.35.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.35.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.35.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.35.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.35.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.35.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.35.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.36.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.36.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.36.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.36.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.36.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.36.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.36.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.36.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.36.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.36.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.36.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.36.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.36.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.37.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.37.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.37.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.37.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.37.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.37.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.37.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.37.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.37.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.37.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.37.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.37.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.37.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.38.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.38.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.38.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.38.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.38.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.38.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.38.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.38.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.38.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.38.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.38.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.38.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.38.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.39.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.39.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.39.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.39.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.39.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.39.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.39.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.39.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.39.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.39.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.39.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.39.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.39.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.40.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.40.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.40.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.40.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.40.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.40.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.40.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.40.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.40.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.40.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.40.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.40.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.40.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.41.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.41.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.41.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.41.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.41.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.41.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.41.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.41.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.41.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.41.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.41.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.41.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.41.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.42.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.42.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.42.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.42.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.42.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.42.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.42.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.42.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.42.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.42.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.42.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.42.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.42.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.43.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.43.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.43.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.43.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.43.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.43.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.43.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.43.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.43.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.43.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.43.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.43.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.43.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.44.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.44.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.44.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.44.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.44.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.44.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.44.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.44.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.44.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.44.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.44.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.44.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.44.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.45.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.45.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.45.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.45.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.45.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.45.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.45.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.45.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.45.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.45.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.45.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.45.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.45.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.46.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.46.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.46.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.46.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.46.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.46.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.46.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.46.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.46.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.46.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.46.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.46.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.46.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.47.norm1.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.47.attn.qkv.weight - torch.Size([9600, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.47.attn.proj.weight - torch.Size([3200, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.47.attn.proj.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.47.attn.q_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.47.attn.k_norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.47.ls1.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.47.norm2.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.47.mlp.fc1.weight - torch.Size([12800, 3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.47.mlp.fc1.bias - torch.Size([12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.47.mlp.fc2.weight - torch.Size([3200, 12800]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.47.mlp.fc2.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder backbone.blocks.47.ls2.gamma - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.conv_seg.weight - torch.Size([150, 3200, 1, 1]): NormalInit: mean=0, std=0.01, bias=0 decode_head.conv_seg.bias - torch.Size([150]): NormalInit: mean=0, std=0.01, bias=0 decode_head.norm.weight - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder decode_head.norm.bias - torch.Size([3200]): The value is the same before and after calling `init_weights` of EncoderDecoder 2023-11-02 18:45:14,433 - mmseg - INFO - EncoderDecoder( (backbone): InternViT6B( (patch_embed): PatchEmbed( (proj): Conv2d(3, 3200, kernel_size=(14, 14), stride=(14, 14)) (norm): Identity() ) (pos_drop): Identity() (blocks): ModuleList( (0): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): Identity() (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): Identity() ) (1): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.009) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.009) ) (2): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.017) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.017) ) (3): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.026) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.026) ) (4): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.034) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.034) ) (5): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.043) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.043) ) (6): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.051) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.051) ) (7): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.060) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.060) ) (8): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.068) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.068) ) (9): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.077) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.077) ) (10): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.085) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.085) ) (11): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.094) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.094) ) (12): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.102) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.102) ) (13): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.111) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.111) ) (14): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.119) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.119) ) (15): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.128) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.128) ) (16): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.136) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.136) ) (17): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.145) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.145) ) (18): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.153) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.153) ) (19): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.162) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.162) ) (20): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.170) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.170) ) (21): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.179) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.179) ) (22): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.187) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.187) ) (23): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.196) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.196) ) (24): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.204) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.204) ) (25): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.213) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.213) ) (26): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.221) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.221) ) (27): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.230) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.230) ) (28): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.238) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.238) ) (29): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.247) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.247) ) (30): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.255) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.255) ) (31): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.264) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.264) ) (32): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.272) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.272) ) (33): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.281) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.281) ) (34): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.289) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.289) ) (35): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.298) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.298) ) (36): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.306) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.306) ) (37): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.315) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.315) ) (38): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.323) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.323) ) (39): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.332) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.332) ) (40): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.340) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.340) ) (41): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.349) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.349) ) (42): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.357) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.357) ) (43): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.366) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.366) ) (44): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.374) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.374) ) (45): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.383) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.383) ) (46): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.391) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.391) ) (47): Block( (norm1): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (attn): Attention( (qkv): Linear(in_features=3200, out_features=9600, bias=False) (attn_drop): Dropout(p=0.0, inplace=False) (proj): Linear(in_features=3200, out_features=3200, bias=True) (proj_drop): Dropout(p=0.0, inplace=False) (inner_attn): FlashAttention() (q_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (k_norm): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) ) (ls1): LayerScale() (drop_path1): DropPath(drop_prob=0.400) (norm2): FusedRMSNorm(torch.Size([3200]), eps=1e-06, elementwise_affine=True) (mlp): Mlp( (fc1): Linear(in_features=3200, out_features=12800, bias=True) (act): GELU(approximate='none') (drop1): Dropout(p=0.0, inplace=False) (fc2): Linear(in_features=12800, out_features=3200, bias=True) (drop2): Dropout(p=0.0, inplace=False) ) (ls2): LayerScale() (drop_path2): DropPath(drop_prob=0.400) ) ) ) (decode_head): FCNHead( input_transform=None, ignore_index=255, align_corners=False (loss_decode): CrossEntropyLoss(avg_non_ignore=False) (conv_seg): Conv2d(3200, 150, kernel_size=(1, 1), stride=(1, 1)) (convs): Identity() (norm): SyncBatchNorm(3200, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) init_cfg={'type': 'Normal', 'std': 0.01, 'override': {'name': 'conv_seg'}} ) 2023-11-02 18:45:15,007 - mmseg - INFO - Loaded 20210 images 2023-11-02 18:45:15,017 - mmseg - INFO - Randomly select 5052 images 2023-11-02 18:45:16,451 - mmseg - INFO - {'num_layers': 48, 'layer_decay_rate': 0.95} 2023-11-02 18:45:16,451 - mmseg - INFO - Build LayerDecayOptimizerConstructor 0.950000 - 50 2023-11-02 18:45:16,455 - mmseg - INFO - Param groups = { "layer_0_decay": { "param_names": [ "backbone.pos_embed", "backbone.cls_token", "backbone.patch_embed.proj.weight" ], "lr_scale": 0.0809947108175928, "lr": 3.2397884327037123e-06, "weight_decay": 0.05 }, "layer_0_no_decay": { "param_names": [ "backbone.patch_embed.proj.bias" ], "lr_scale": 0.0809947108175928, "lr": 3.2397884327037123e-06, "weight_decay": 0.0 }, "layer_1_no_decay": { "param_names": [ "backbone.blocks.0.norm1.weight", "backbone.blocks.0.attn.proj.bias", "backbone.blocks.0.attn.q_norm.weight", "backbone.blocks.0.attn.k_norm.weight", "backbone.blocks.0.ls1.gamma", "backbone.blocks.0.norm2.weight", "backbone.blocks.0.mlp.fc1.bias", "backbone.blocks.0.mlp.fc2.bias", "backbone.blocks.0.ls2.gamma" ], "lr_scale": 0.0852575903343082, "lr": 3.4103036133723282e-06, "weight_decay": 0.0 }, "layer_1_decay": { "param_names": [ "backbone.blocks.0.attn.qkv.weight", "backbone.blocks.0.attn.proj.weight", "backbone.blocks.0.mlp.fc1.weight", "backbone.blocks.0.mlp.fc2.weight" ], "lr_scale": 0.0852575903343082, "lr": 3.4103036133723282e-06, "weight_decay": 0.05 }, "layer_2_no_decay": { "param_names": [ "backbone.blocks.1.norm1.weight", "backbone.blocks.1.attn.proj.bias", "backbone.blocks.1.attn.q_norm.weight", "backbone.blocks.1.attn.k_norm.weight", "backbone.blocks.1.ls1.gamma", "backbone.blocks.1.norm2.weight", "backbone.blocks.1.mlp.fc1.bias", "backbone.blocks.1.mlp.fc2.bias", "backbone.blocks.1.ls2.gamma" ], "lr_scale": 0.08974483193085075, "lr": 3.5897932772340305e-06, "weight_decay": 0.0 }, "layer_2_decay": { "param_names": [ "backbone.blocks.1.attn.qkv.weight", "backbone.blocks.1.attn.proj.weight", "backbone.blocks.1.mlp.fc1.weight", "backbone.blocks.1.mlp.fc2.weight" ], "lr_scale": 0.08974483193085075, "lr": 3.5897932772340305e-06, "weight_decay": 0.05 }, "layer_3_no_decay": { "param_names": [ "backbone.blocks.2.norm1.weight", "backbone.blocks.2.attn.proj.bias", "backbone.blocks.2.attn.q_norm.weight", "backbone.blocks.2.attn.k_norm.weight", "backbone.blocks.2.ls1.gamma", "backbone.blocks.2.norm2.weight", "backbone.blocks.2.mlp.fc1.bias", "backbone.blocks.2.mlp.fc2.bias", "backbone.blocks.2.ls2.gamma" ], "lr_scale": 0.09446824413773763, "lr": 3.7787297655095058e-06, "weight_decay": 0.0 }, "layer_3_decay": { "param_names": [ "backbone.blocks.2.attn.qkv.weight", "backbone.blocks.2.attn.proj.weight", "backbone.blocks.2.mlp.fc1.weight", "backbone.blocks.2.mlp.fc2.weight" ], "lr_scale": 0.09446824413773763, "lr": 3.7787297655095058e-06, "weight_decay": 0.05 }, "layer_4_no_decay": { "param_names": [ "backbone.blocks.3.norm1.weight", "backbone.blocks.3.attn.proj.bias", "backbone.blocks.3.attn.q_norm.weight", "backbone.blocks.3.attn.k_norm.weight", "backbone.blocks.3.ls1.gamma", "backbone.blocks.3.norm2.weight", "backbone.blocks.3.mlp.fc1.bias", "backbone.blocks.3.mlp.fc2.bias", "backbone.blocks.3.ls2.gamma" ], "lr_scale": 0.09944025698709225, "lr": 3.97761027948369e-06, "weight_decay": 0.0 }, "layer_4_decay": { "param_names": [ "backbone.blocks.3.attn.qkv.weight", "backbone.blocks.3.attn.proj.weight", "backbone.blocks.3.mlp.fc1.weight", "backbone.blocks.3.mlp.fc2.weight" ], "lr_scale": 0.09944025698709225, "lr": 3.97761027948369e-06, "weight_decay": 0.05 }, "layer_5_no_decay": { "param_names": [ "backbone.blocks.4.norm1.weight", "backbone.blocks.4.attn.proj.bias", "backbone.blocks.4.attn.q_norm.weight", "backbone.blocks.4.attn.k_norm.weight", "backbone.blocks.4.ls1.gamma", "backbone.blocks.4.norm2.weight", "backbone.blocks.4.mlp.fc1.bias", "backbone.blocks.4.mlp.fc2.bias", "backbone.blocks.4.ls2.gamma" ], "lr_scale": 0.10467395472325501, "lr": 4.186958188930201e-06, "weight_decay": 0.0 }, "layer_5_decay": { "param_names": [ "backbone.blocks.4.attn.qkv.weight", "backbone.blocks.4.attn.proj.weight", "backbone.blocks.4.mlp.fc1.weight", "backbone.blocks.4.mlp.fc2.weight" ], "lr_scale": 0.10467395472325501, "lr": 4.186958188930201e-06, "weight_decay": 0.05 }, "layer_6_no_decay": { "param_names": [ "backbone.blocks.5.norm1.weight", "backbone.blocks.5.attn.proj.bias", "backbone.blocks.5.attn.q_norm.weight", "backbone.blocks.5.attn.k_norm.weight", "backbone.blocks.5.ls1.gamma", "backbone.blocks.5.norm2.weight", "backbone.blocks.5.mlp.fc1.bias", "backbone.blocks.5.mlp.fc2.bias", "backbone.blocks.5.ls2.gamma" ], "lr_scale": 0.11018311023500528, "lr": 4.407324409400211e-06, "weight_decay": 0.0 }, "layer_6_decay": { "param_names": [ "backbone.blocks.5.attn.qkv.weight", "backbone.blocks.5.attn.proj.weight", "backbone.blocks.5.mlp.fc1.weight", "backbone.blocks.5.mlp.fc2.weight" ], "lr_scale": 0.11018311023500528, "lr": 4.407324409400211e-06, "weight_decay": 0.05 }, "layer_7_no_decay": { "param_names": [ "backbone.blocks.6.norm1.weight", "backbone.blocks.6.attn.proj.bias", "backbone.blocks.6.attn.q_norm.weight", "backbone.blocks.6.attn.k_norm.weight", "backbone.blocks.6.ls1.gamma", "backbone.blocks.6.norm2.weight", "backbone.blocks.6.mlp.fc1.bias", "backbone.blocks.6.mlp.fc2.bias", "backbone.blocks.6.ls2.gamma" ], "lr_scale": 0.11598222130000556, "lr": 4.639288852000222e-06, "weight_decay": 0.0 }, "layer_7_decay": { "param_names": [ "backbone.blocks.6.attn.qkv.weight", "backbone.blocks.6.attn.proj.weight", "backbone.blocks.6.mlp.fc1.weight", "backbone.blocks.6.mlp.fc2.weight" ], "lr_scale": 0.11598222130000556, "lr": 4.639288852000222e-06, "weight_decay": 0.05 }, "layer_8_no_decay": { "param_names": [ "backbone.blocks.7.norm1.weight", "backbone.blocks.7.attn.proj.bias", "backbone.blocks.7.attn.q_norm.weight", "backbone.blocks.7.attn.k_norm.weight", "backbone.blocks.7.ls1.gamma", "backbone.blocks.7.norm2.weight", "backbone.blocks.7.mlp.fc1.bias", "backbone.blocks.7.mlp.fc2.bias", "backbone.blocks.7.ls2.gamma" ], "lr_scale": 0.12208654873684796, "lr": 4.883461949473919e-06, "weight_decay": 0.0 }, "layer_8_decay": { "param_names": [ "backbone.blocks.7.attn.qkv.weight", "backbone.blocks.7.attn.proj.weight", "backbone.blocks.7.mlp.fc1.weight", "backbone.blocks.7.mlp.fc2.weight" ], "lr_scale": 0.12208654873684796, "lr": 4.883461949473919e-06, "weight_decay": 0.05 }, "layer_9_no_decay": { "param_names": [ "backbone.blocks.8.norm1.weight", "backbone.blocks.8.attn.proj.bias", "backbone.blocks.8.attn.q_norm.weight", "backbone.blocks.8.attn.k_norm.weight", "backbone.blocks.8.ls1.gamma", "backbone.blocks.8.norm2.weight", "backbone.blocks.8.mlp.fc1.bias", "backbone.blocks.8.mlp.fc2.bias", "backbone.blocks.8.ls2.gamma" ], "lr_scale": 0.12851215656510312, "lr": 5.140486262604126e-06, "weight_decay": 0.0 }, "layer_9_decay": { "param_names": [ "backbone.blocks.8.attn.qkv.weight", "backbone.blocks.8.attn.proj.weight", "backbone.blocks.8.mlp.fc1.weight", "backbone.blocks.8.mlp.fc2.weight" ], "lr_scale": 0.12851215656510312, "lr": 5.140486262604126e-06, "weight_decay": 0.05 }, "layer_10_no_decay": { "param_names": [ "backbone.blocks.9.norm1.weight", "backbone.blocks.9.attn.proj.bias", "backbone.blocks.9.attn.q_norm.weight", "backbone.blocks.9.attn.k_norm.weight", "backbone.blocks.9.ls1.gamma", "backbone.blocks.9.norm2.weight", "backbone.blocks.9.mlp.fc1.bias", "backbone.blocks.9.mlp.fc2.bias", "backbone.blocks.9.ls2.gamma" ], "lr_scale": 0.13527595427905592, "lr": 5.411038171162237e-06, "weight_decay": 0.0 }, "layer_10_decay": { "param_names": [ "backbone.blocks.9.attn.qkv.weight", "backbone.blocks.9.attn.proj.weight", "backbone.blocks.9.mlp.fc1.weight", "backbone.blocks.9.mlp.fc2.weight" ], "lr_scale": 0.13527595427905592, "lr": 5.411038171162237e-06, "weight_decay": 0.05 }, "layer_11_no_decay": { "param_names": [ "backbone.blocks.10.norm1.weight", "backbone.blocks.10.attn.proj.bias", "backbone.blocks.10.attn.q_norm.weight", "backbone.blocks.10.attn.k_norm.weight", "backbone.blocks.10.ls1.gamma", "backbone.blocks.10.norm2.weight", "backbone.blocks.10.mlp.fc1.bias", "backbone.blocks.10.mlp.fc2.bias", "backbone.blocks.10.ls2.gamma" ], "lr_scale": 0.14239574134637467, "lr": 5.695829653854987e-06, "weight_decay": 0.0 }, "layer_11_decay": { "param_names": [ "backbone.blocks.10.attn.qkv.weight", "backbone.blocks.10.attn.proj.weight", "backbone.blocks.10.mlp.fc1.weight", "backbone.blocks.10.mlp.fc2.weight" ], "lr_scale": 0.14239574134637467, "lr": 5.695829653854987e-06, "weight_decay": 0.05 }, "layer_12_no_decay": { "param_names": [ "backbone.blocks.11.norm1.weight", "backbone.blocks.11.attn.proj.bias", "backbone.blocks.11.attn.q_norm.weight", "backbone.blocks.11.attn.k_norm.weight", "backbone.blocks.11.ls1.gamma", "backbone.blocks.11.norm2.weight", "backbone.blocks.11.mlp.fc1.bias", "backbone.blocks.11.mlp.fc2.bias", "backbone.blocks.11.ls2.gamma" ], "lr_scale": 0.14989025404881545, "lr": 5.995610161952619e-06, "weight_decay": 0.0 }, "layer_12_decay": { "param_names": [ "backbone.blocks.11.attn.qkv.weight", "backbone.blocks.11.attn.proj.weight", "backbone.blocks.11.mlp.fc1.weight", "backbone.blocks.11.mlp.fc2.weight" ], "lr_scale": 0.14989025404881545, "lr": 5.995610161952619e-06, "weight_decay": 0.05 }, "layer_13_no_decay": { "param_names": [ "backbone.blocks.12.norm1.weight", "backbone.blocks.12.attn.proj.bias", "backbone.blocks.12.attn.q_norm.weight", "backbone.blocks.12.attn.k_norm.weight", "backbone.blocks.12.ls1.gamma", "backbone.blocks.12.norm2.weight", "backbone.blocks.12.mlp.fc1.bias", "backbone.blocks.12.mlp.fc2.bias", "backbone.blocks.12.ls2.gamma" ], "lr_scale": 0.1577792147882268, "lr": 6.311168591529072e-06, "weight_decay": 0.0 }, "layer_13_decay": { "param_names": [ "backbone.blocks.12.attn.qkv.weight", "backbone.blocks.12.attn.proj.weight", "backbone.blocks.12.mlp.fc1.weight", "backbone.blocks.12.mlp.fc2.weight" ], "lr_scale": 0.1577792147882268, "lr": 6.311168591529072e-06, "weight_decay": 0.05 }, "layer_14_no_decay": { "param_names": [ "backbone.blocks.13.norm1.weight", "backbone.blocks.13.attn.proj.bias", "backbone.blocks.13.attn.q_norm.weight", "backbone.blocks.13.attn.k_norm.weight", "backbone.blocks.13.ls1.gamma", "backbone.blocks.13.norm2.weight", "backbone.blocks.13.mlp.fc1.bias", "backbone.blocks.13.mlp.fc2.bias", "backbone.blocks.13.ls2.gamma" ], "lr_scale": 0.16608338398760716, "lr": 6.6433353595042875e-06, "weight_decay": 0.0 }, "layer_14_decay": { "param_names": [ "backbone.blocks.13.attn.qkv.weight", "backbone.blocks.13.attn.proj.weight", "backbone.blocks.13.mlp.fc1.weight", "backbone.blocks.13.mlp.fc2.weight" ], "lr_scale": 0.16608338398760716, "lr": 6.6433353595042875e-06, "weight_decay": 0.05 }, "layer_15_no_decay": { "param_names": [ "backbone.blocks.14.norm1.weight", "backbone.blocks.14.attn.proj.bias", "backbone.blocks.14.attn.q_norm.weight", "backbone.blocks.14.attn.k_norm.weight", "backbone.blocks.14.ls1.gamma", "backbone.blocks.14.norm2.weight", "backbone.blocks.14.mlp.fc1.bias", "backbone.blocks.14.mlp.fc2.bias", "backbone.blocks.14.ls2.gamma" ], "lr_scale": 0.174824614723797, "lr": 6.9929845889518814e-06, "weight_decay": 0.0 }, "layer_15_decay": { "param_names": [ "backbone.blocks.14.attn.qkv.weight", "backbone.blocks.14.attn.proj.weight", "backbone.blocks.14.mlp.fc1.weight", "backbone.blocks.14.mlp.fc2.weight" ], "lr_scale": 0.174824614723797, "lr": 6.9929845889518814e-06, "weight_decay": 0.05 }, "layer_16_no_decay": { "param_names": [ "backbone.blocks.15.norm1.weight", "backbone.blocks.15.attn.proj.bias", "backbone.blocks.15.attn.q_norm.weight", "backbone.blocks.15.attn.k_norm.weight", "backbone.blocks.15.ls1.gamma", "backbone.blocks.15.norm2.weight", "backbone.blocks.15.mlp.fc1.bias", "backbone.blocks.15.mlp.fc2.bias", "backbone.blocks.15.ls2.gamma" ], "lr_scale": 0.18402591023557582, "lr": 7.361036409423033e-06, "weight_decay": 0.0 }, "layer_16_decay": { "param_names": [ "backbone.blocks.15.attn.qkv.weight", "backbone.blocks.15.attn.proj.weight", "backbone.blocks.15.mlp.fc1.weight", "backbone.blocks.15.mlp.fc2.weight" ], "lr_scale": 0.18402591023557582, "lr": 7.361036409423033e-06, "weight_decay": 0.05 }, "layer_17_no_decay": { "param_names": [ "backbone.blocks.16.norm1.weight", "backbone.blocks.16.attn.proj.bias", "backbone.blocks.16.attn.q_norm.weight", "backbone.blocks.16.attn.k_norm.weight", "backbone.blocks.16.ls1.gamma", "backbone.blocks.16.norm2.weight", "backbone.blocks.16.mlp.fc1.bias", "backbone.blocks.16.mlp.fc2.bias", "backbone.blocks.16.ls2.gamma" ], "lr_scale": 0.19371148445850087, "lr": 7.748459378340036e-06, "weight_decay": 0.0 }, "layer_17_decay": { "param_names": [ "backbone.blocks.16.attn.qkv.weight", "backbone.blocks.16.attn.proj.weight", "backbone.blocks.16.mlp.fc1.weight", "backbone.blocks.16.mlp.fc2.weight" ], "lr_scale": 0.19371148445850087, "lr": 7.748459378340036e-06, "weight_decay": 0.05 }, "layer_18_no_decay": { "param_names": [ "backbone.blocks.17.norm1.weight", "backbone.blocks.17.attn.proj.bias", "backbone.blocks.17.attn.q_norm.weight", "backbone.blocks.17.attn.k_norm.weight", "backbone.blocks.17.ls1.gamma", "backbone.blocks.17.norm2.weight", "backbone.blocks.17.mlp.fc1.bias", "backbone.blocks.17.mlp.fc2.bias", "backbone.blocks.17.ls2.gamma" ], "lr_scale": 0.2039068257457904, "lr": 8.156273029831616e-06, "weight_decay": 0.0 }, "layer_18_decay": { "param_names": [ "backbone.blocks.17.attn.qkv.weight", "backbone.blocks.17.attn.proj.weight", "backbone.blocks.17.mlp.fc1.weight", "backbone.blocks.17.mlp.fc2.weight" ], "lr_scale": 0.2039068257457904, "lr": 8.156273029831616e-06, "weight_decay": 0.05 }, "layer_19_no_decay": { "param_names": [ "backbone.blocks.18.norm1.weight", "backbone.blocks.18.attn.proj.bias", "backbone.blocks.18.attn.q_norm.weight", "backbone.blocks.18.attn.k_norm.weight", "backbone.blocks.18.ls1.gamma", "backbone.blocks.18.norm2.weight", "backbone.blocks.18.mlp.fc1.bias", "backbone.blocks.18.mlp.fc2.bias", "backbone.blocks.18.ls2.gamma" ], "lr_scale": 0.21463876394293727, "lr": 8.585550557717492e-06, "weight_decay": 0.0 }, "layer_19_decay": { "param_names": [ "backbone.blocks.18.attn.qkv.weight", "backbone.blocks.18.attn.proj.weight", "backbone.blocks.18.mlp.fc1.weight", "backbone.blocks.18.mlp.fc2.weight" ], "lr_scale": 0.21463876394293727, "lr": 8.585550557717492e-06, "weight_decay": 0.05 }, "layer_20_no_decay": { "param_names": [ "backbone.blocks.19.norm1.weight", "backbone.blocks.19.attn.proj.bias", "backbone.blocks.19.attn.q_norm.weight", "backbone.blocks.19.attn.k_norm.weight", "backbone.blocks.19.ls1.gamma", "backbone.blocks.19.norm2.weight", "backbone.blocks.19.mlp.fc1.bias", "backbone.blocks.19.mlp.fc2.bias", "backbone.blocks.19.ls2.gamma" ], "lr_scale": 0.22593554099256555, "lr": 9.037421639702623e-06, "weight_decay": 0.0 }, "layer_20_decay": { "param_names": [ "backbone.blocks.19.attn.qkv.weight", "backbone.blocks.19.attn.proj.weight", "backbone.blocks.19.mlp.fc1.weight", "backbone.blocks.19.mlp.fc2.weight" ], "lr_scale": 0.22593554099256555, "lr": 9.037421639702623e-06, "weight_decay": 0.05 }, "layer_21_no_decay": { "param_names": [ "backbone.blocks.20.norm1.weight", "backbone.blocks.20.attn.proj.bias", "backbone.blocks.20.attn.q_norm.weight", "backbone.blocks.20.attn.k_norm.weight", "backbone.blocks.20.ls1.gamma", "backbone.blocks.20.norm2.weight", "backbone.blocks.20.mlp.fc1.bias", "backbone.blocks.20.mlp.fc2.bias", "backbone.blocks.20.ls2.gamma" ], "lr_scale": 0.23782688525533216, "lr": 9.513075410213288e-06, "weight_decay": 0.0 }, "layer_21_decay": { "param_names": [ "backbone.blocks.20.attn.qkv.weight", "backbone.blocks.20.attn.proj.weight", "backbone.blocks.20.mlp.fc1.weight", "backbone.blocks.20.mlp.fc2.weight" ], "lr_scale": 0.23782688525533216, "lr": 9.513075410213288e-06, "weight_decay": 0.05 }, "layer_22_no_decay": { "param_names": [ "backbone.blocks.21.norm1.weight", "backbone.blocks.21.attn.proj.bias", "backbone.blocks.21.attn.q_norm.weight", "backbone.blocks.21.attn.k_norm.weight", "backbone.blocks.21.ls1.gamma", "backbone.blocks.21.norm2.weight", "backbone.blocks.21.mlp.fc1.bias", "backbone.blocks.21.mlp.fc2.bias", "backbone.blocks.21.ls2.gamma" ], "lr_scale": 0.2503440897424549, "lr": 1.0013763589698198e-05, "weight_decay": 0.0 }, "layer_22_decay": { "param_names": [ "backbone.blocks.21.attn.qkv.weight", "backbone.blocks.21.attn.proj.weight", "backbone.blocks.21.mlp.fc1.weight", "backbone.blocks.21.mlp.fc2.weight" ], "lr_scale": 0.2503440897424549, "lr": 1.0013763589698198e-05, "weight_decay": 0.05 }, "layer_23_no_decay": { "param_names": [ "backbone.blocks.22.norm1.weight", "backbone.blocks.22.attn.proj.bias", "backbone.blocks.22.attn.q_norm.weight", "backbone.blocks.22.attn.k_norm.weight", "backbone.blocks.22.ls1.gamma", "backbone.blocks.22.norm2.weight", "backbone.blocks.22.mlp.fc1.bias", "backbone.blocks.22.mlp.fc2.bias", "backbone.blocks.22.ls2.gamma" ], "lr_scale": 0.26352009446574204, "lr": 1.0540803778629682e-05, "weight_decay": 0.0 }, "layer_23_decay": { "param_names": [ "backbone.blocks.22.attn.qkv.weight", "backbone.blocks.22.attn.proj.weight", "backbone.blocks.22.mlp.fc1.weight", "backbone.blocks.22.mlp.fc2.weight" ], "lr_scale": 0.26352009446574204, "lr": 1.0540803778629682e-05, "weight_decay": 0.05 }, "layer_24_no_decay": { "param_names": [ "backbone.blocks.23.norm1.weight", "backbone.blocks.23.attn.proj.bias", "backbone.blocks.23.attn.q_norm.weight", "backbone.blocks.23.attn.k_norm.weight", "backbone.blocks.23.ls1.gamma", "backbone.blocks.23.norm2.weight", "backbone.blocks.23.mlp.fc1.bias", "backbone.blocks.23.mlp.fc2.bias", "backbone.blocks.23.ls2.gamma" ], "lr_scale": 0.27738957312183377, "lr": 1.109558292487335e-05, "weight_decay": 0.0 }, "layer_24_decay": { "param_names": [ "backbone.blocks.23.attn.qkv.weight", "backbone.blocks.23.attn.proj.weight", "backbone.blocks.23.mlp.fc1.weight", "backbone.blocks.23.mlp.fc2.weight" ], "lr_scale": 0.27738957312183377, "lr": 1.109558292487335e-05, "weight_decay": 0.05 }, "layer_25_no_decay": { "param_names": [ "backbone.blocks.24.norm1.weight", "backbone.blocks.24.attn.proj.bias", "backbone.blocks.24.attn.q_norm.weight", "backbone.blocks.24.attn.k_norm.weight", "backbone.blocks.24.ls1.gamma", "backbone.blocks.24.norm2.weight", "backbone.blocks.24.mlp.fc1.bias", "backbone.blocks.24.mlp.fc2.bias", "backbone.blocks.24.ls2.gamma" ], "lr_scale": 0.2919890243387724, "lr": 1.1679560973550896e-05, "weight_decay": 0.0 }, "layer_25_decay": { "param_names": [ "backbone.blocks.24.attn.qkv.weight", "backbone.blocks.24.attn.proj.weight", "backbone.blocks.24.mlp.fc1.weight", "backbone.blocks.24.mlp.fc2.weight" ], "lr_scale": 0.2919890243387724, "lr": 1.1679560973550896e-05, "weight_decay": 0.05 }, "layer_26_no_decay": { "param_names": [ "backbone.blocks.25.norm1.weight", "backbone.blocks.25.attn.proj.bias", "backbone.blocks.25.attn.q_norm.weight", "backbone.blocks.25.attn.k_norm.weight", "backbone.blocks.25.ls1.gamma", "backbone.blocks.25.norm2.weight", "backbone.blocks.25.mlp.fc1.bias", "backbone.blocks.25.mlp.fc2.bias", "backbone.blocks.25.ls2.gamma" ], "lr_scale": 0.3073568677250236, "lr": 1.2294274709000943e-05, "weight_decay": 0.0 }, "layer_26_decay": { "param_names": [ "backbone.blocks.25.attn.qkv.weight", "backbone.blocks.25.attn.proj.weight", "backbone.blocks.25.mlp.fc1.weight", "backbone.blocks.25.mlp.fc2.weight" ], "lr_scale": 0.3073568677250236, "lr": 1.2294274709000943e-05, "weight_decay": 0.05 }, "layer_27_no_decay": { "param_names": [ "backbone.blocks.26.norm1.weight", "backbone.blocks.26.attn.proj.bias", "backbone.blocks.26.attn.q_norm.weight", "backbone.blocks.26.attn.k_norm.weight", "backbone.blocks.26.ls1.gamma", "backbone.blocks.26.norm2.weight", "backbone.blocks.26.mlp.fc1.bias", "backbone.blocks.26.mlp.fc2.bias", "backbone.blocks.26.ls2.gamma" ], "lr_scale": 0.323533544973709, "lr": 1.2941341798948362e-05, "weight_decay": 0.0 }, "layer_27_decay": { "param_names": [ "backbone.blocks.26.attn.qkv.weight", "backbone.blocks.26.attn.proj.weight", "backbone.blocks.26.mlp.fc1.weight", "backbone.blocks.26.mlp.fc2.weight" ], "lr_scale": 0.323533544973709, "lr": 1.2941341798948362e-05, "weight_decay": 0.05 }, "layer_28_no_decay": { "param_names": [ "backbone.blocks.27.norm1.weight", "backbone.blocks.27.attn.proj.bias", "backbone.blocks.27.attn.q_norm.weight", "backbone.blocks.27.attn.k_norm.weight", "backbone.blocks.27.ls1.gamma", "backbone.blocks.27.norm2.weight", "backbone.blocks.27.mlp.fc1.bias", "backbone.blocks.27.mlp.fc2.bias", "backbone.blocks.27.ls2.gamma" ], "lr_scale": 0.3405616262881148, "lr": 1.3622465051524594e-05, "weight_decay": 0.0 }, "layer_28_decay": { "param_names": [ "backbone.blocks.27.attn.qkv.weight", "backbone.blocks.27.attn.proj.weight", "backbone.blocks.27.mlp.fc1.weight", "backbone.blocks.27.mlp.fc2.weight" ], "lr_scale": 0.3405616262881148, "lr": 1.3622465051524594e-05, "weight_decay": 0.05 }, "layer_29_no_decay": { "param_names": [ "backbone.blocks.28.norm1.weight", "backbone.blocks.28.attn.proj.bias", "backbone.blocks.28.attn.q_norm.weight", "backbone.blocks.28.attn.k_norm.weight", "backbone.blocks.28.ls1.gamma", "backbone.blocks.28.norm2.weight", "backbone.blocks.28.mlp.fc1.bias", "backbone.blocks.28.mlp.fc2.bias", "backbone.blocks.28.ls2.gamma" ], "lr_scale": 0.3584859224085419, "lr": 1.4339436896341676e-05, "weight_decay": 0.0 }, "layer_29_decay": { "param_names": [ "backbone.blocks.28.attn.qkv.weight", "backbone.blocks.28.attn.proj.weight", "backbone.blocks.28.mlp.fc1.weight", "backbone.blocks.28.mlp.fc2.weight" ], "lr_scale": 0.3584859224085419, "lr": 1.4339436896341676e-05, "weight_decay": 0.05 }, "layer_30_no_decay": { "param_names": [ "backbone.blocks.29.norm1.weight", "backbone.blocks.29.attn.proj.bias", "backbone.blocks.29.attn.q_norm.weight", "backbone.blocks.29.attn.k_norm.weight", "backbone.blocks.29.ls1.gamma", "backbone.blocks.29.norm2.weight", "backbone.blocks.29.mlp.fc1.bias", "backbone.blocks.29.mlp.fc2.bias", "backbone.blocks.29.ls2.gamma" ], "lr_scale": 0.37735360253530725, "lr": 1.509414410141229e-05, "weight_decay": 0.0 }, "layer_30_decay": { "param_names": [ "backbone.blocks.29.attn.qkv.weight", "backbone.blocks.29.attn.proj.weight", "backbone.blocks.29.mlp.fc1.weight", "backbone.blocks.29.mlp.fc2.weight" ], "lr_scale": 0.37735360253530725, "lr": 1.509414410141229e-05, "weight_decay": 0.05 }, "layer_31_no_decay": { "param_names": [ "backbone.blocks.30.norm1.weight", "backbone.blocks.30.attn.proj.bias", "backbone.blocks.30.attn.q_norm.weight", "backbone.blocks.30.attn.k_norm.weight", "backbone.blocks.30.ls1.gamma", "backbone.blocks.30.norm2.weight", "backbone.blocks.30.mlp.fc1.bias", "backbone.blocks.30.mlp.fc2.bias", "backbone.blocks.30.ls2.gamma" ], "lr_scale": 0.3972143184582182, "lr": 1.588857273832873e-05, "weight_decay": 0.0 }, "layer_31_decay": { "param_names": [ "backbone.blocks.30.attn.qkv.weight", "backbone.blocks.30.attn.proj.weight", "backbone.blocks.30.mlp.fc1.weight", "backbone.blocks.30.mlp.fc2.weight" ], "lr_scale": 0.3972143184582182, "lr": 1.588857273832873e-05, "weight_decay": 0.05 }, "layer_32_no_decay": { "param_names": [ "backbone.blocks.31.norm1.weight", "backbone.blocks.31.attn.proj.bias", "backbone.blocks.31.attn.q_norm.weight", "backbone.blocks.31.attn.k_norm.weight", "backbone.blocks.31.ls1.gamma", "backbone.blocks.31.norm2.weight", "backbone.blocks.31.mlp.fc1.bias", "backbone.blocks.31.mlp.fc2.bias", "backbone.blocks.31.ls2.gamma" ], "lr_scale": 0.4181203352191771, "lr": 1.6724813408767084e-05, "weight_decay": 0.0 }, "layer_32_decay": { "param_names": [ "backbone.blocks.31.attn.qkv.weight", "backbone.blocks.31.attn.proj.weight", "backbone.blocks.31.mlp.fc1.weight", "backbone.blocks.31.mlp.fc2.weight" ], "lr_scale": 0.4181203352191771, "lr": 1.6724813408767084e-05, "weight_decay": 0.05 }, "layer_33_no_decay": { "param_names": [ "backbone.blocks.32.norm1.weight", "backbone.blocks.32.attn.proj.bias", "backbone.blocks.32.attn.q_norm.weight", "backbone.blocks.32.attn.k_norm.weight", "backbone.blocks.32.ls1.gamma", "backbone.blocks.32.norm2.weight", "backbone.blocks.32.mlp.fc1.bias", "backbone.blocks.32.mlp.fc2.bias", "backbone.blocks.32.ls2.gamma" ], "lr_scale": 0.44012666865176536, "lr": 1.7605066746070617e-05, "weight_decay": 0.0 }, "layer_33_decay": { "param_names": [ "backbone.blocks.32.attn.qkv.weight", "backbone.blocks.32.attn.proj.weight", "backbone.blocks.32.mlp.fc1.weight", "backbone.blocks.32.mlp.fc2.weight" ], "lr_scale": 0.44012666865176536, "lr": 1.7605066746070617e-05, "weight_decay": 0.05 }, "layer_34_no_decay": { "param_names": [ "backbone.blocks.33.norm1.weight", "backbone.blocks.33.attn.proj.bias", "backbone.blocks.33.attn.q_norm.weight", "backbone.blocks.33.attn.k_norm.weight", "backbone.blocks.33.ls1.gamma", "backbone.blocks.33.norm2.weight", "backbone.blocks.33.mlp.fc1.bias", "backbone.blocks.33.mlp.fc2.bias", "backbone.blocks.33.ls2.gamma" ], "lr_scale": 0.46329123015975304, "lr": 1.8531649206390123e-05, "weight_decay": 0.0 }, "layer_34_decay": { "param_names": [ "backbone.blocks.33.attn.qkv.weight", "backbone.blocks.33.attn.proj.weight", "backbone.blocks.33.mlp.fc1.weight", "backbone.blocks.33.mlp.fc2.weight" ], "lr_scale": 0.46329123015975304, "lr": 1.8531649206390123e-05, "weight_decay": 0.05 }, "layer_35_no_decay": { "param_names": [ "backbone.blocks.34.norm1.weight", "backbone.blocks.34.attn.proj.bias", "backbone.blocks.34.attn.q_norm.weight", "backbone.blocks.34.attn.k_norm.weight", "backbone.blocks.34.ls1.gamma", "backbone.blocks.34.norm2.weight", "backbone.blocks.34.mlp.fc1.bias", "backbone.blocks.34.mlp.fc2.bias", "backbone.blocks.34.ls2.gamma" ], "lr_scale": 0.48767497911552954, "lr": 1.9506999164621184e-05, "weight_decay": 0.0 }, "layer_35_decay": { "param_names": [ "backbone.blocks.34.attn.qkv.weight", "backbone.blocks.34.attn.proj.weight", "backbone.blocks.34.mlp.fc1.weight", "backbone.blocks.34.mlp.fc2.weight" ], "lr_scale": 0.48767497911552954, "lr": 1.9506999164621184e-05, "weight_decay": 0.05 }, "layer_36_no_decay": { "param_names": [ "backbone.blocks.35.norm1.weight", "backbone.blocks.35.attn.proj.bias", "backbone.blocks.35.attn.q_norm.weight", "backbone.blocks.35.attn.k_norm.weight", "backbone.blocks.35.ls1.gamma", "backbone.blocks.35.norm2.weight", "backbone.blocks.35.mlp.fc1.bias", "backbone.blocks.35.mlp.fc2.bias", "backbone.blocks.35.ls2.gamma" ], "lr_scale": 0.5133420832795048, "lr": 2.0533683331180195e-05, "weight_decay": 0.0 }, "layer_36_decay": { "param_names": [ "backbone.blocks.35.attn.qkv.weight", "backbone.blocks.35.attn.proj.weight", "backbone.blocks.35.mlp.fc1.weight", "backbone.blocks.35.mlp.fc2.weight" ], "lr_scale": 0.5133420832795048, "lr": 2.0533683331180195e-05, "weight_decay": 0.05 }, "layer_37_no_decay": { "param_names": [ "backbone.blocks.36.norm1.weight", "backbone.blocks.36.attn.proj.bias", "backbone.blocks.36.attn.q_norm.weight", "backbone.blocks.36.attn.k_norm.weight", "backbone.blocks.36.ls1.gamma", "backbone.blocks.36.norm2.weight", "backbone.blocks.36.mlp.fc1.bias", "backbone.blocks.36.mlp.fc2.bias", "backbone.blocks.36.ls2.gamma" ], "lr_scale": 0.5403600876626367, "lr": 2.1614403506505468e-05, "weight_decay": 0.0 }, "layer_37_decay": { "param_names": [ "backbone.blocks.36.attn.qkv.weight", "backbone.blocks.36.attn.proj.weight", "backbone.blocks.36.mlp.fc1.weight", "backbone.blocks.36.mlp.fc2.weight" ], "lr_scale": 0.5403600876626367, "lr": 2.1614403506505468e-05, "weight_decay": 0.05 }, "layer_38_no_decay": { "param_names": [ "backbone.blocks.37.norm1.weight", "backbone.blocks.37.attn.proj.bias", "backbone.blocks.37.attn.q_norm.weight", "backbone.blocks.37.attn.k_norm.weight", "backbone.blocks.37.ls1.gamma", "backbone.blocks.37.norm2.weight", "backbone.blocks.37.mlp.fc1.bias", "backbone.blocks.37.mlp.fc2.bias", "backbone.blocks.37.ls2.gamma" ], "lr_scale": 0.5688000922764597, "lr": 2.275200369105839e-05, "weight_decay": 0.0 }, "layer_38_decay": { "param_names": [ "backbone.blocks.37.attn.qkv.weight", "backbone.blocks.37.attn.proj.weight", "backbone.blocks.37.mlp.fc1.weight", "backbone.blocks.37.mlp.fc2.weight" ], "lr_scale": 0.5688000922764597, "lr": 2.275200369105839e-05, "weight_decay": 0.05 }, "layer_39_no_decay": { "param_names": [ "backbone.blocks.38.norm1.weight", "backbone.blocks.38.attn.proj.bias", "backbone.blocks.38.attn.q_norm.weight", "backbone.blocks.38.attn.k_norm.weight", "backbone.blocks.38.ls1.gamma", "backbone.blocks.38.norm2.weight", "backbone.blocks.38.mlp.fc1.bias", "backbone.blocks.38.mlp.fc2.bias", "backbone.blocks.38.ls2.gamma" ], "lr_scale": 0.5987369392383787, "lr": 2.394947756953515e-05, "weight_decay": 0.0 }, "layer_39_decay": { "param_names": [ "backbone.blocks.38.attn.qkv.weight", "backbone.blocks.38.attn.proj.weight", "backbone.blocks.38.mlp.fc1.weight", "backbone.blocks.38.mlp.fc2.weight" ], "lr_scale": 0.5987369392383787, "lr": 2.394947756953515e-05, "weight_decay": 0.05 }, "layer_40_no_decay": { "param_names": [ "backbone.blocks.39.norm1.weight", "backbone.blocks.39.attn.proj.bias", "backbone.blocks.39.attn.q_norm.weight", "backbone.blocks.39.attn.k_norm.weight", "backbone.blocks.39.ls1.gamma", "backbone.blocks.39.norm2.weight", "backbone.blocks.39.mlp.fc1.bias", "backbone.blocks.39.mlp.fc2.bias", "backbone.blocks.39.ls2.gamma" ], "lr_scale": 0.6302494097246091, "lr": 2.5209976388984365e-05, "weight_decay": 0.0 }, "layer_40_decay": { "param_names": [ "backbone.blocks.39.attn.qkv.weight", "backbone.blocks.39.attn.proj.weight", "backbone.blocks.39.mlp.fc1.weight", "backbone.blocks.39.mlp.fc2.weight" ], "lr_scale": 0.6302494097246091, "lr": 2.5209976388984365e-05, "weight_decay": 0.05 }, "layer_41_no_decay": { "param_names": [ "backbone.blocks.40.norm1.weight", "backbone.blocks.40.attn.proj.bias", "backbone.blocks.40.attn.q_norm.weight", "backbone.blocks.40.attn.k_norm.weight", "backbone.blocks.40.ls1.gamma", "backbone.blocks.40.norm2.weight", "backbone.blocks.40.mlp.fc1.bias", "backbone.blocks.40.mlp.fc2.bias", "backbone.blocks.40.ls2.gamma" ], "lr_scale": 0.6634204312890623, "lr": 2.6536817251562493e-05, "weight_decay": 0.0 }, "layer_41_decay": { "param_names": [ "backbone.blocks.40.attn.qkv.weight", "backbone.blocks.40.attn.proj.weight", "backbone.blocks.40.mlp.fc1.weight", "backbone.blocks.40.mlp.fc2.weight" ], "lr_scale": 0.6634204312890623, "lr": 2.6536817251562493e-05, "weight_decay": 0.05 }, "layer_42_no_decay": { "param_names": [ "backbone.blocks.41.norm1.weight", "backbone.blocks.41.attn.proj.bias", "backbone.blocks.41.attn.q_norm.weight", "backbone.blocks.41.attn.k_norm.weight", "backbone.blocks.41.ls1.gamma", "backbone.blocks.41.norm2.weight", "backbone.blocks.41.mlp.fc1.bias", "backbone.blocks.41.mlp.fc2.bias", "backbone.blocks.41.ls2.gamma" ], "lr_scale": 0.6983372960937497, "lr": 2.793349184374999e-05, "weight_decay": 0.0 }, "layer_42_decay": { "param_names": [ "backbone.blocks.41.attn.qkv.weight", "backbone.blocks.41.attn.proj.weight", "backbone.blocks.41.mlp.fc1.weight", "backbone.blocks.41.mlp.fc2.weight" ], "lr_scale": 0.6983372960937497, "lr": 2.793349184374999e-05, "weight_decay": 0.05 }, "layer_43_no_decay": { "param_names": [ "backbone.blocks.42.norm1.weight", "backbone.blocks.42.attn.proj.bias", "backbone.blocks.42.attn.q_norm.weight", "backbone.blocks.42.attn.k_norm.weight", "backbone.blocks.42.ls1.gamma", "backbone.blocks.42.norm2.weight", "backbone.blocks.42.mlp.fc1.bias", "backbone.blocks.42.mlp.fc2.bias", "backbone.blocks.42.ls2.gamma" ], "lr_scale": 0.7350918906249998, "lr": 2.9403675624999993e-05, "weight_decay": 0.0 }, "layer_43_decay": { "param_names": [ "backbone.blocks.42.attn.qkv.weight", "backbone.blocks.42.attn.proj.weight", "backbone.blocks.42.mlp.fc1.weight", "backbone.blocks.42.mlp.fc2.weight" ], "lr_scale": 0.7350918906249998, "lr": 2.9403675624999993e-05, "weight_decay": 0.05 }, "layer_44_no_decay": { "param_names": [ "backbone.blocks.43.norm1.weight", "backbone.blocks.43.attn.proj.bias", "backbone.blocks.43.attn.q_norm.weight", "backbone.blocks.43.attn.k_norm.weight", "backbone.blocks.43.ls1.gamma", "backbone.blocks.43.norm2.weight", "backbone.blocks.43.mlp.fc1.bias", "backbone.blocks.43.mlp.fc2.bias", "backbone.blocks.43.ls2.gamma" ], "lr_scale": 0.7737809374999998, "lr": 3.0951237499999995e-05, "weight_decay": 0.0 }, "layer_44_decay": { "param_names": [ "backbone.blocks.43.attn.qkv.weight", "backbone.blocks.43.attn.proj.weight", "backbone.blocks.43.mlp.fc1.weight", "backbone.blocks.43.mlp.fc2.weight" ], "lr_scale": 0.7737809374999998, "lr": 3.0951237499999995e-05, "weight_decay": 0.05 }, "layer_45_no_decay": { "param_names": [ "backbone.blocks.44.norm1.weight", "backbone.blocks.44.attn.proj.bias", "backbone.blocks.44.attn.q_norm.weight", "backbone.blocks.44.attn.k_norm.weight", "backbone.blocks.44.ls1.gamma", "backbone.blocks.44.norm2.weight", "backbone.blocks.44.mlp.fc1.bias", "backbone.blocks.44.mlp.fc2.bias", "backbone.blocks.44.ls2.gamma" ], "lr_scale": 0.8145062499999999, "lr": 3.258025e-05, "weight_decay": 0.0 }, "layer_45_decay": { "param_names": [ "backbone.blocks.44.attn.qkv.weight", "backbone.blocks.44.attn.proj.weight", "backbone.blocks.44.mlp.fc1.weight", "backbone.blocks.44.mlp.fc2.weight" ], "lr_scale": 0.8145062499999999, "lr": 3.258025e-05, "weight_decay": 0.05 }, "layer_46_no_decay": { "param_names": [ "backbone.blocks.45.norm1.weight", "backbone.blocks.45.attn.proj.bias", "backbone.blocks.45.attn.q_norm.weight", "backbone.blocks.45.attn.k_norm.weight", "backbone.blocks.45.ls1.gamma", "backbone.blocks.45.norm2.weight", "backbone.blocks.45.mlp.fc1.bias", "backbone.blocks.45.mlp.fc2.bias", "backbone.blocks.45.ls2.gamma" ], "lr_scale": 0.8573749999999999, "lr": 3.4294999999999996e-05, "weight_decay": 0.0 }, "layer_46_decay": { "param_names": [ "backbone.blocks.45.attn.qkv.weight", "backbone.blocks.45.attn.proj.weight", "backbone.blocks.45.mlp.fc1.weight", "backbone.blocks.45.mlp.fc2.weight" ], "lr_scale": 0.8573749999999999, "lr": 3.4294999999999996e-05, "weight_decay": 0.05 }, "layer_47_no_decay": { "param_names": [ "backbone.blocks.46.norm1.weight", "backbone.blocks.46.attn.proj.bias", "backbone.blocks.46.attn.q_norm.weight", "backbone.blocks.46.attn.k_norm.weight", "backbone.blocks.46.ls1.gamma", "backbone.blocks.46.norm2.weight", "backbone.blocks.46.mlp.fc1.bias", "backbone.blocks.46.mlp.fc2.bias", "backbone.blocks.46.ls2.gamma" ], "lr_scale": 0.9025, "lr": 3.61e-05, "weight_decay": 0.0 }, "layer_47_decay": { "param_names": [ "backbone.blocks.46.attn.qkv.weight", "backbone.blocks.46.attn.proj.weight", "backbone.blocks.46.mlp.fc1.weight", "backbone.blocks.46.mlp.fc2.weight" ], "lr_scale": 0.9025, "lr": 3.61e-05, "weight_decay": 0.05 }, "layer_48_no_decay": { "param_names": [ "backbone.blocks.47.norm1.weight", "backbone.blocks.47.attn.proj.bias", "backbone.blocks.47.attn.q_norm.weight", "backbone.blocks.47.attn.k_norm.weight", "backbone.blocks.47.ls1.gamma", "backbone.blocks.47.norm2.weight", "backbone.blocks.47.mlp.fc1.bias", "backbone.blocks.47.mlp.fc2.bias", "backbone.blocks.47.ls2.gamma" ], "lr_scale": 0.95, "lr": 3.8e-05, "weight_decay": 0.0 }, "layer_48_decay": { "param_names": [ "backbone.blocks.47.attn.qkv.weight", "backbone.blocks.47.attn.proj.weight", "backbone.blocks.47.mlp.fc1.weight", "backbone.blocks.47.mlp.fc2.weight" ], "lr_scale": 0.95, "lr": 3.8e-05, "weight_decay": 0.05 }, "layer_49_decay": { "param_names": [ "decode_head.conv_seg.weight" ], "lr_scale": 1.0, "lr": 4e-05, "weight_decay": 0.05 }, "layer_49_no_decay": { "param_names": [ "decode_head.conv_seg.bias", "decode_head.norm.weight", "decode_head.norm.bias" ], "lr_scale": 1.0, "lr": 4e-05, "weight_decay": 0.0 } } 2023-11-02 18:45:53,233 - mmseg - INFO - trainable parameters: 5906608150 2023-11-02 18:45:53,235 - mmseg - INFO - total parameters: 5906608150 2023-11-02 18:45:53,279 - mmseg - INFO - Loaded 2000 images 2023-11-02 18:45:53,279 - mmseg - INFO - Randomly select 2000 images 2023-11-02 18:45:53,280 - mmseg - INFO - Start running, host: wangwenhai@SH-IDC1-10-140-37-50, work_dir: /mnt/petrelfs/wangwenhai/workspace/ViTDetection/mmsegmentation/work_dirs/segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4 2023-11-02 18:45:53,280 - mmseg - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) PolyLrUpdaterHook (49 ) ToBFloat16Hook (49 ) ToBFloat16Hook (NORMAL ) DeepspeedCheckpointHook (LOW ) DeepspeedDistEvalHook (VERY_LOW ) TextLoggerHook (VERY_LOW ) TensorboardLoggerHook -------------------- before_train_epoch: (VERY_HIGH ) PolyLrUpdaterHook (LOW ) IterTimerHook (LOW ) DeepspeedDistEvalHook (VERY_LOW ) TextLoggerHook (VERY_LOW ) TensorboardLoggerHook -------------------- before_train_iter: (VERY_HIGH ) PolyLrUpdaterHook (LOW ) IterTimerHook (LOW ) DeepspeedDistEvalHook -------------------- after_train_iter: (ABOVE_NORMAL) OptimizerHook (NORMAL ) DeepspeedCheckpointHook (LOW ) IterTimerHook (LOW ) DeepspeedDistEvalHook (VERY_LOW ) TextLoggerHook (VERY_LOW ) TensorboardLoggerHook -------------------- after_train_epoch: (NORMAL ) DeepspeedCheckpointHook (LOW ) DeepspeedDistEvalHook (VERY_LOW ) TextLoggerHook (VERY_LOW ) TensorboardLoggerHook -------------------- before_val_epoch: (LOW ) IterTimerHook (VERY_LOW ) TextLoggerHook (VERY_LOW ) TensorboardLoggerHook -------------------- before_val_iter: (LOW ) IterTimerHook -------------------- after_val_iter: (LOW ) IterTimerHook -------------------- after_val_epoch: (VERY_LOW ) TextLoggerHook (VERY_LOW ) TensorboardLoggerHook -------------------- after_run: (VERY_LOW ) TextLoggerHook (VERY_LOW ) TensorboardLoggerHook -------------------- 2023-11-02 18:45:53,280 - mmseg - INFO - workflow: [('train', 1)], max: 20000 iters 2023-11-02 18:45:53,288 - mmseg - INFO - Checkpoints will be saved to /mnt/petrelfs/wangwenhai/workspace/ViTDetection/mmsegmentation/work_dirs/segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4 by HardDiskBackend. 2023-11-02 18:48:02,714 - mmseg - INFO - Iter [50/20000] lr: 3.959e-07, eta: 7:04:22, time: 1.276, data_time: 0.009, memory: 38534, decode.loss_ce: 4.0656, decode.acc_seg: 0.9929, loss: 4.0656 2023-11-02 18:49:03,092 - mmseg - INFO - Iter [100/20000] lr: 7.979e-07, eta: 6:51:54, time: 1.208, data_time: 0.007, memory: 38534, decode.loss_ce: 3.8378, decode.acc_seg: 13.4720, loss: 3.8378 2023-11-02 18:50:03,569 - mmseg - INFO - Iter [150/20000] lr: 1.198e-06, eta: 6:47:16, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 2.4425, decode.acc_seg: 45.7282, loss: 2.4425 2023-11-02 18:51:04,068 - mmseg - INFO - Iter [200/20000] lr: 1.596e-06, eta: 6:44:31, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 1.7153, decode.acc_seg: 59.0562, loss: 1.7153 2023-11-02 18:52:04,527 - mmseg - INFO - Iter [250/20000] lr: 1.992e-06, eta: 6:42:24, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 1.3834, decode.acc_seg: 64.0278, loss: 1.3834 2023-11-02 18:53:05,069 - mmseg - INFO - Iter [300/20000] lr: 2.386e-06, eta: 6:40:45, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 1.2554, decode.acc_seg: 64.6334, loss: 1.2554 2023-11-02 18:54:07,922 - mmseg - INFO - Iter [350/20000] lr: 2.777e-06, eta: 6:41:26, time: 1.257, data_time: 0.053, memory: 38534, decode.loss_ce: 1.1024, decode.acc_seg: 68.3056, loss: 1.1024 2023-11-02 18:55:08,460 - mmseg - INFO - Iter [400/20000] lr: 3.167e-06, eta: 6:39:48, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.9841, decode.acc_seg: 70.5275, loss: 0.9841 2023-11-02 18:56:08,979 - mmseg - INFO - Iter [450/20000] lr: 3.167e-06, eta: 6:38:17, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.9515, decode.acc_seg: 70.8445, loss: 0.9515 2023-11-02 18:57:09,532 - mmseg - INFO - Iter [500/20000] lr: 3.159e-06, eta: 6:36:54, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.9363, decode.acc_seg: 71.7831, loss: 0.9363 2023-11-02 18:58:10,162 - mmseg - INFO - Iter [550/20000] lr: 3.151e-06, eta: 6:35:38, time: 1.213, data_time: 0.009, memory: 38534, decode.loss_ce: 0.8397, decode.acc_seg: 73.1715, loss: 0.8397 2023-11-02 18:59:10,720 - mmseg - INFO - Iter [600/20000] lr: 3.143e-06, eta: 6:34:22, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.8314, decode.acc_seg: 72.8868, loss: 0.8314 2023-11-02 19:00:13,755 - mmseg - INFO - Iter [650/20000] lr: 3.135e-06, eta: 6:34:22, time: 1.261, data_time: 0.056, memory: 38534, decode.loss_ce: 0.8055, decode.acc_seg: 73.8438, loss: 0.8055 2023-11-02 19:01:14,298 - mmseg - INFO - Iter [700/20000] lr: 3.127e-06, eta: 6:33:04, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.7864, decode.acc_seg: 74.0550, loss: 0.7864 2023-11-02 19:02:14,869 - mmseg - INFO - Iter [750/20000] lr: 3.118e-06, eta: 6:31:49, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.7053, decode.acc_seg: 77.2072, loss: 0.7053 2023-11-02 19:03:15,403 - mmseg - INFO - Iter [800/20000] lr: 3.110e-06, eta: 6:30:35, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.6970, decode.acc_seg: 76.0510, loss: 0.6970 2023-11-02 19:04:15,917 - mmseg - INFO - Iter [850/20000] lr: 3.102e-06, eta: 6:29:23, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.6860, decode.acc_seg: 76.4036, loss: 0.6860 2023-11-02 19:05:16,466 - mmseg - INFO - Iter [900/20000] lr: 3.094e-06, eta: 6:28:12, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.6707, decode.acc_seg: 77.2282, loss: 0.6707 2023-11-02 19:06:19,364 - mmseg - INFO - Iter [950/20000] lr: 3.086e-06, eta: 6:27:50, time: 1.258, data_time: 0.052, memory: 38534, decode.loss_ce: 0.6238, decode.acc_seg: 78.6259, loss: 0.6238 2023-11-02 19:07:19,992 - mmseg - INFO - Saving checkpoint at 1000 iterations 2023-11-02 19:08:14,340 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 19:08:14,340 - mmseg - INFO - Iter [1000/20000] lr: 3.078e-06, eta: 6:43:53, time: 2.300, data_time: 0.007, memory: 38534, decode.loss_ce: 0.6301, decode.acc_seg: 78.2823, loss: 0.6301 2023-11-02 19:10:06,496 - mmseg - INFO - per class results: 2023-11-02 19:10:06,502 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 75.61 | 84.48 | | building | 81.99 | 90.7 | | sky | 92.61 | 97.1 | | floor | 79.56 | 89.31 | | tree | 72.13 | 84.09 | | ceiling | 81.72 | 90.99 | | road | 83.34 | 87.22 | | bed | 87.52 | 96.21 | | windowpane | 61.34 | 76.28 | | grass | 70.64 | 86.5 | | cabinet | 58.55 | 67.69 | | sidewalk | 59.94 | 86.32 | | person | 78.84 | 90.64 | | earth | 36.77 | 53.22 | | door | 51.82 | 71.78 | | table | 58.42 | 75.77 | | mountain | 58.41 | 70.93 | | plant | 53.01 | 74.27 | | curtain | 73.97 | 86.17 | | chair | 52.78 | 62.38 | | car | 79.41 | 93.31 | | water | 45.3 | 59.59 | | painting | 64.3 | 87.06 | | sofa | 68.56 | 90.42 | | shelf | 39.92 | 54.81 | | house | 45.51 | 58.63 | | sea | 49.1 | 81.56 | | mirror | 57.88 | 86.89 | | rug | 63.53 | 79.76 | | field | 35.78 | 52.85 | | armchair | 42.4 | 62.47 | | seat | 57.27 | 88.99 | | fence | 38.51 | 61.42 | | desk | 39.79 | 77.93 | | rock | 32.21 | 35.36 | | wardrobe | 53.2 | 69.4 | | lamp | 54.52 | 77.48 | | bathtub | 77.63 | 92.05 | | railing | 34.28 | 44.46 | | cushion | 47.38 | 53.06 | | base | 34.03 | 58.41 | | box | 24.41 | 31.48 | | column | 46.02 | 54.57 | | signboard | 33.5 | 55.77 | | chest of drawers | 35.91 | 66.11 | | counter | 44.61 | 61.17 | | sand | 40.49 | 52.06 | | sink | 68.04 | 79.29 | | skyscraper | 37.57 | 43.34 | | fireplace | 66.06 | 93.12 | | refrigerator | 67.76 | 86.21 | | grandstand | 40.04 | 69.86 | | path | 8.84 | 9.55 | | stairs | 8.26 | 8.77 | | runway | 69.37 | 93.78 | | case | 53.08 | 72.72 | | pool table | 86.84 | 96.94 | | pillow | 56.36 | 74.45 | | screen door | 67.76 | 78.87 | | stairway | 27.69 | 56.03 | | river | 18.77 | 26.65 | | bridge | 60.49 | 91.51 | | bookcase | 35.24 | 48.32 | | blind | 33.16 | 34.95 | | coffee table | 60.04 | 82.2 | | toilet | 81.65 | 93.5 | | flower | 35.07 | 53.24 | | book | 43.79 | 67.59 | | hill | 9.52 | 18.16 | | bench | 49.64 | 61.93 | | countertop | 55.19 | 74.78 | | stove | 63.71 | 68.8 | | palm | 47.78 | 80.77 | | kitchen island | 52.95 | 76.29 | | computer | 69.02 | 87.55 | | swivel chair | 42.24 | 64.25 | | boat | 55.58 | 84.09 | | bar | 48.5 | 63.12 | | arcade machine | 81.07 | 88.44 | | hovel | 22.38 | 23.96 | | bus | 43.2 | 43.73 | | towel | 64.21 | 77.76 | | light | 43.29 | 57.4 | | truck | 26.43 | 53.29 | | tower | 24.34 | 53.24 | | chandelier | 58.59 | 82.86 | | awning | 30.94 | 36.81 | | streetlight | 19.38 | 27.24 | | booth | 27.39 | 30.65 | | television receiver | 70.64 | 83.86 | | airplane | 44.42 | 71.56 | | dirt track | 0.0 | 0.0 | | apparel | 38.45 | 60.02 | | pole | 8.53 | 9.07 | | land | 0.13 | 0.13 | | bannister | 6.81 | 8.14 | | escalator | 31.29 | 34.94 | | ottoman | 43.07 | 57.67 | | bottle | 19.84 | 31.14 | | buffet | 39.66 | 54.46 | | poster | 10.22 | 12.23 | | stage | 10.15 | 12.71 | | van | 12.6 | 22.09 | | ship | 9.87 | 10.08 | | fountain | 35.32 | 39.81 | | conveyer belt | 82.16 | 92.12 | | canopy | 56.02 | 66.17 | | washer | 81.34 | 91.44 | | plaything | 32.74 | 61.88 | | swimming pool | 60.27 | 74.66 | | stool | 34.89 | 47.67 | | barrel | 3.63 | 18.1 | | basket | 30.93 | 46.86 | | waterfall | 51.8 | 94.93 | | tent | 77.44 | 98.96 | | bag | 9.58 | 10.26 | | minibike | 67.41 | 86.04 | | cradle | 74.5 | 93.69 | | oven | 39.78 | 75.36 | | ball | 50.07 | 61.26 | | food | 58.3 | 74.63 | | step | 3.04 | 3.1 | | tank | 37.04 | 37.39 | | trade name | 21.12 | 25.77 | | microwave | 78.81 | 90.43 | | pot | 42.42 | 50.45 | | animal | 61.43 | 66.62 | | bicycle | 57.32 | 72.43 | | lake | 0.0 | 0.0 | | dishwasher | 51.08 | 60.43 | | screen | 61.85 | 85.28 | | blanket | 0.32 | 0.32 | | sculpture | 47.56 | 65.6 | | hood | 59.13 | 78.28 | | sconce | 21.51 | 24.49 | | vase | 28.81 | 42.66 | | traffic light | 24.55 | 38.09 | | tray | 0.54 | 0.61 | | ashcan | 38.93 | 48.69 | | fan | 51.69 | 75.15 | | pier | 28.77 | 29.69 | | crt screen | 3.32 | 3.62 | | plate | 48.21 | 54.61 | | monitor | 38.61 | 46.03 | | bulletin board | 35.05 | 42.24 | | shower | 0.0 | 0.0 | | radiator | 46.68 | 49.05 | | glass | 0.05 | 0.05 | | clock | 25.32 | 28.0 | | flag | 60.31 | 66.04 | +---------------------+-------+-------+ 2023-11-02 19:10:06,502 - mmseg - INFO - Summary: 2023-11-02 19:10:06,502 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 81.75 | 45.21 | 58.75 | +-------+-------+-------+ 2023-11-02 19:10:06,503 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 19:10:06,503 - mmseg - INFO - Iter(val) [250] aAcc: 0.8175, mIoU: 0.4521, mAcc: 0.5875, IoU.wall: 0.7561, IoU.building: 0.8199, IoU.sky: 0.9261, IoU.floor: 0.7956, IoU.tree: 0.7213, IoU.ceiling: 0.8172, IoU.road: 0.8334, IoU.bed : 0.8752, IoU.windowpane: 0.6134, IoU.grass: 0.7064, IoU.cabinet: 0.5855, IoU.sidewalk: 0.5994, IoU.person: 0.7884, IoU.earth: 0.3677, IoU.door: 0.5182, IoU.table: 0.5842, IoU.mountain: 0.5841, IoU.plant: 0.5301, IoU.curtain: 0.7397, IoU.chair: 0.5278, IoU.car: 0.7941, IoU.water: 0.4530, IoU.painting: 0.6430, IoU.sofa: 0.6856, IoU.shelf: 0.3992, IoU.house: 0.4551, IoU.sea: 0.4910, IoU.mirror: 0.5788, IoU.rug: 0.6353, IoU.field: 0.3578, IoU.armchair: 0.4240, IoU.seat: 0.5727, IoU.fence: 0.3851, IoU.desk: 0.3979, IoU.rock: 0.3221, IoU.wardrobe: 0.5320, IoU.lamp: 0.5452, IoU.bathtub: 0.7763, IoU.railing: 0.3428, IoU.cushion: 0.4738, IoU.base: 0.3403, IoU.box: 0.2441, IoU.column: 0.4602, IoU.signboard: 0.3350, IoU.chest of drawers: 0.3591, IoU.counter: 0.4461, IoU.sand: 0.4049, IoU.sink: 0.6804, IoU.skyscraper: 0.3757, IoU.fireplace: 0.6606, IoU.refrigerator: 0.6776, IoU.grandstand: 0.4004, IoU.path: 0.0884, IoU.stairs: 0.0826, IoU.runway: 0.6937, IoU.case: 0.5308, IoU.pool table: 0.8684, IoU.pillow: 0.5636, IoU.screen door: 0.6776, IoU.stairway: 0.2769, IoU.river: 0.1877, IoU.bridge: 0.6049, IoU.bookcase: 0.3524, IoU.blind: 0.3316, IoU.coffee table: 0.6004, IoU.toilet: 0.8165, IoU.flower: 0.3507, IoU.book: 0.4379, IoU.hill: 0.0952, IoU.bench: 0.4964, IoU.countertop: 0.5519, IoU.stove: 0.6371, IoU.palm: 0.4778, IoU.kitchen island: 0.5295, IoU.computer: 0.6902, IoU.swivel chair: 0.4224, IoU.boat: 0.5558, IoU.bar: 0.4850, IoU.arcade machine: 0.8107, IoU.hovel: 0.2238, IoU.bus: 0.4320, IoU.towel: 0.6421, IoU.light: 0.4329, IoU.truck: 0.2643, IoU.tower: 0.2434, IoU.chandelier: 0.5859, IoU.awning: 0.3094, IoU.streetlight: 0.1938, IoU.booth: 0.2739, IoU.television receiver: 0.7064, IoU.airplane: 0.4442, IoU.dirt track: 0.0000, IoU.apparel: 0.3845, IoU.pole: 0.0853, IoU.land: 0.0013, IoU.bannister: 0.0681, IoU.escalator: 0.3129, IoU.ottoman: 0.4307, IoU.bottle: 0.1984, IoU.buffet: 0.3966, IoU.poster: 0.1022, IoU.stage: 0.1015, IoU.van: 0.1260, IoU.ship: 0.0987, IoU.fountain: 0.3532, IoU.conveyer belt: 0.8216, IoU.canopy: 0.5602, IoU.washer: 0.8134, IoU.plaything: 0.3274, IoU.swimming pool: 0.6027, IoU.stool: 0.3489, IoU.barrel: 0.0363, IoU.basket: 0.3093, IoU.waterfall: 0.5180, IoU.tent: 0.7744, IoU.bag: 0.0958, IoU.minibike: 0.6741, IoU.cradle: 0.7450, IoU.oven: 0.3978, IoU.ball: 0.5007, IoU.food: 0.5830, IoU.step: 0.0304, IoU.tank: 0.3704, IoU.trade name: 0.2112, IoU.microwave: 0.7881, IoU.pot: 0.4242, IoU.animal: 0.6143, IoU.bicycle: 0.5732, IoU.lake: 0.0000, IoU.dishwasher: 0.5108, IoU.screen: 0.6185, IoU.blanket: 0.0032, IoU.sculpture: 0.4756, IoU.hood: 0.5913, IoU.sconce: 0.2151, IoU.vase: 0.2881, IoU.traffic light: 0.2455, IoU.tray: 0.0054, IoU.ashcan: 0.3893, IoU.fan: 0.5169, IoU.pier: 0.2877, IoU.crt screen: 0.0332, IoU.plate: 0.4821, IoU.monitor: 0.3861, IoU.bulletin board: 0.3505, IoU.shower: 0.0000, IoU.radiator: 0.4668, IoU.glass: 0.0005, IoU.clock: 0.2532, IoU.flag: 0.6031, Acc.wall: 0.8448, Acc.building: 0.9070, Acc.sky: 0.9710, Acc.floor: 0.8931, Acc.tree: 0.8409, Acc.ceiling: 0.9099, Acc.road: 0.8722, Acc.bed : 0.9621, Acc.windowpane: 0.7628, Acc.grass: 0.8650, Acc.cabinet: 0.6769, Acc.sidewalk: 0.8632, Acc.person: 0.9064, Acc.earth: 0.5322, Acc.door: 0.7178, Acc.table: 0.7577, Acc.mountain: 0.7093, Acc.plant: 0.7427, Acc.curtain: 0.8617, Acc.chair: 0.6238, Acc.car: 0.9331, Acc.water: 0.5959, Acc.painting: 0.8706, Acc.sofa: 0.9042, Acc.shelf: 0.5481, Acc.house: 0.5863, Acc.sea: 0.8156, Acc.mirror: 0.8689, Acc.rug: 0.7976, Acc.field: 0.5285, Acc.armchair: 0.6247, Acc.seat: 0.8899, Acc.fence: 0.6142, Acc.desk: 0.7793, Acc.rock: 0.3536, Acc.wardrobe: 0.6940, Acc.lamp: 0.7748, Acc.bathtub: 0.9205, Acc.railing: 0.4446, Acc.cushion: 0.5306, Acc.base: 0.5841, Acc.box: 0.3148, Acc.column: 0.5457, Acc.signboard: 0.5577, Acc.chest of drawers: 0.6611, Acc.counter: 0.6117, Acc.sand: 0.5206, Acc.sink: 0.7929, Acc.skyscraper: 0.4334, Acc.fireplace: 0.9312, Acc.refrigerator: 0.8621, Acc.grandstand: 0.6986, Acc.path: 0.0955, Acc.stairs: 0.0877, Acc.runway: 0.9378, Acc.case: 0.7272, Acc.pool table: 0.9694, Acc.pillow: 0.7445, Acc.screen door: 0.7887, Acc.stairway: 0.5603, Acc.river: 0.2665, Acc.bridge: 0.9151, Acc.bookcase: 0.4832, Acc.blind: 0.3495, Acc.coffee table: 0.8220, Acc.toilet: 0.9350, Acc.flower: 0.5324, Acc.book: 0.6759, Acc.hill: 0.1816, Acc.bench: 0.6193, Acc.countertop: 0.7478, Acc.stove: 0.6880, Acc.palm: 0.8077, Acc.kitchen island: 0.7629, Acc.computer: 0.8755, Acc.swivel chair: 0.6425, Acc.boat: 0.8409, Acc.bar: 0.6312, Acc.arcade machine: 0.8844, Acc.hovel: 0.2396, Acc.bus: 0.4373, Acc.towel: 0.7776, Acc.light: 0.5740, Acc.truck: 0.5329, Acc.tower: 0.5324, Acc.chandelier: 0.8286, Acc.awning: 0.3681, Acc.streetlight: 0.2724, Acc.booth: 0.3065, Acc.television receiver: 0.8386, Acc.airplane: 0.7156, Acc.dirt track: 0.0000, Acc.apparel: 0.6002, Acc.pole: 0.0907, Acc.land: 0.0013, Acc.bannister: 0.0814, Acc.escalator: 0.3494, Acc.ottoman: 0.5767, Acc.bottle: 0.3114, Acc.buffet: 0.5446, Acc.poster: 0.1223, Acc.stage: 0.1271, Acc.van: 0.2209, Acc.ship: 0.1008, Acc.fountain: 0.3981, Acc.conveyer belt: 0.9212, Acc.canopy: 0.6617, Acc.washer: 0.9144, Acc.plaything: 0.6188, Acc.swimming pool: 0.7466, Acc.stool: 0.4767, Acc.barrel: 0.1810, Acc.basket: 0.4686, Acc.waterfall: 0.9493, Acc.tent: 0.9896, Acc.bag: 0.1026, Acc.minibike: 0.8604, Acc.cradle: 0.9369, Acc.oven: 0.7536, Acc.ball: 0.6126, Acc.food: 0.7463, Acc.step: 0.0310, Acc.tank: 0.3739, Acc.trade name: 0.2577, Acc.microwave: 0.9043, Acc.pot: 0.5045, Acc.animal: 0.6662, Acc.bicycle: 0.7243, Acc.lake: 0.0000, Acc.dishwasher: 0.6043, Acc.screen: 0.8528, Acc.blanket: 0.0032, Acc.sculpture: 0.6560, Acc.hood: 0.7828, Acc.sconce: 0.2449, Acc.vase: 0.4266, Acc.traffic light: 0.3809, Acc.tray: 0.0061, Acc.ashcan: 0.4869, Acc.fan: 0.7515, Acc.pier: 0.2969, Acc.crt screen: 0.0362, Acc.plate: 0.5461, Acc.monitor: 0.4603, Acc.bulletin board: 0.4224, Acc.shower: 0.0000, Acc.radiator: 0.4905, Acc.glass: 0.0005, Acc.clock: 0.2800, Acc.flag: 0.6604 2023-11-02 19:11:07,107 - mmseg - INFO - Iter [1050/20000] lr: 3.070e-06, eta: 7:15:36, time: 3.455, data_time: 2.251, memory: 38534, decode.loss_ce: 0.6285, decode.acc_seg: 77.9845, loss: 0.6285 2023-11-02 19:12:07,677 - mmseg - INFO - Iter [1100/20000] lr: 3.062e-06, eta: 7:12:03, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.6351, decode.acc_seg: 78.1509, loss: 0.6351 2023-11-02 19:13:08,242 - mmseg - INFO - Iter [1150/20000] lr: 3.054e-06, eta: 7:08:43, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.6479, decode.acc_seg: 78.1887, loss: 0.6479 2023-11-02 19:14:08,774 - mmseg - INFO - Iter [1200/20000] lr: 3.046e-06, eta: 7:05:34, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.5968, decode.acc_seg: 79.0737, loss: 0.5968 2023-11-02 19:15:09,368 - mmseg - INFO - Iter [1250/20000] lr: 3.037e-06, eta: 7:02:36, time: 1.212, data_time: 0.007, memory: 38534, decode.loss_ce: 0.6032, decode.acc_seg: 78.7464, loss: 0.6032 2023-11-02 19:16:12,273 - mmseg - INFO - Iter [1300/20000] lr: 3.029e-06, eta: 7:00:21, time: 1.258, data_time: 0.053, memory: 38534, decode.loss_ce: 0.5329, decode.acc_seg: 81.0064, loss: 0.5329 2023-11-02 19:17:12,868 - mmseg - INFO - Iter [1350/20000] lr: 3.021e-06, eta: 6:57:39, time: 1.212, data_time: 0.007, memory: 38534, decode.loss_ce: 0.5616, decode.acc_seg: 80.4225, loss: 0.5616 2023-11-02 19:18:13,416 - mmseg - INFO - Iter [1400/20000] lr: 3.013e-06, eta: 6:55:04, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.5440, decode.acc_seg: 81.4628, loss: 0.5440 2023-11-02 19:19:13,986 - mmseg - INFO - Iter [1450/20000] lr: 3.005e-06, eta: 6:52:35, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.5496, decode.acc_seg: 80.4076, loss: 0.5496 2023-11-02 19:20:14,590 - mmseg - INFO - Iter [1500/20000] lr: 2.997e-06, eta: 6:50:13, time: 1.212, data_time: 0.008, memory: 38534, decode.loss_ce: 0.5130, decode.acc_seg: 82.2692, loss: 0.5130 2023-11-02 19:21:15,165 - mmseg - INFO - Iter [1550/20000] lr: 2.989e-06, eta: 6:47:56, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.5424, decode.acc_seg: 80.6565, loss: 0.5424 2023-11-02 19:22:20,926 - mmseg - INFO - Iter [1600/20000] lr: 2.981e-06, eta: 6:46:43, time: 1.315, data_time: 0.089, memory: 38534, decode.loss_ce: 0.5044, decode.acc_seg: 81.7380, loss: 0.5044 2023-11-02 19:23:21,494 - mmseg - INFO - Iter [1650/20000] lr: 2.973e-06, eta: 6:44:32, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4651, decode.acc_seg: 83.3684, loss: 0.4651 2023-11-02 19:24:22,212 - mmseg - INFO - Iter [1700/20000] lr: 2.965e-06, eta: 6:42:28, time: 1.214, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4770, decode.acc_seg: 82.7377, loss: 0.4770 2023-11-02 19:25:22,820 - mmseg - INFO - Iter [1750/20000] lr: 2.956e-06, eta: 6:40:26, time: 1.212, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4978, decode.acc_seg: 82.1650, loss: 0.4978 2023-11-02 19:26:23,445 - mmseg - INFO - Iter [1800/20000] lr: 2.948e-06, eta: 6:38:27, time: 1.212, data_time: 0.008, memory: 38534, decode.loss_ce: 0.5132, decode.acc_seg: 81.3011, loss: 0.5132 2023-11-02 19:27:24,013 - mmseg - INFO - Iter [1850/20000] lr: 2.940e-06, eta: 6:36:32, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.5101, decode.acc_seg: 81.6565, loss: 0.5101 2023-11-02 19:28:26,897 - mmseg - INFO - Iter [1900/20000] lr: 2.932e-06, eta: 6:35:01, time: 1.258, data_time: 0.053, memory: 38534, decode.loss_ce: 0.4959, decode.acc_seg: 82.2771, loss: 0.4959 2023-11-02 19:29:27,499 - mmseg - INFO - Iter [1950/20000] lr: 2.924e-06, eta: 6:33:10, time: 1.212, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4450, decode.acc_seg: 83.7184, loss: 0.4450 2023-11-02 19:30:28,149 - mmseg - INFO - Saving checkpoint at 2000 iterations 2023-11-02 19:31:24,466 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 19:31:24,466 - mmseg - INFO - Iter [2000/20000] lr: 2.916e-06, eta: 6:39:49, time: 2.339, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4417, decode.acc_seg: 83.7623, loss: 0.4417 2023-11-02 19:32:22,547 - mmseg - INFO - per class results: 2023-11-02 19:32:22,552 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 76.59 | 86.56 | | building | 81.95 | 93.11 | | sky | 93.41 | 97.05 | | floor | 81.5 | 90.1 | | tree | 73.98 | 87.54 | | ceiling | 83.01 | 89.77 | | road | 80.86 | 91.46 | | bed | 89.45 | 95.74 | | windowpane | 63.36 | 81.01 | | grass | 70.73 | 91.03 | | cabinet | 63.4 | 79.09 | | sidewalk | 63.11 | 78.63 | | person | 80.55 | 89.63 | | earth | 33.92 | 42.54 | | door | 51.58 | 71.9 | | table | 60.27 | 71.69 | | mountain | 61.4 | 72.34 | | plant | 52.21 | 62.35 | | curtain | 73.87 | 86.65 | | chair | 55.75 | 67.39 | | car | 83.46 | 91.88 | | water | 50.29 | 64.91 | | painting | 68.11 | 89.85 | | sofa | 73.04 | 80.93 | | shelf | 38.56 | 50.6 | | house | 32.32 | 37.72 | | sea | 57.26 | 82.98 | | mirror | 66.83 | 83.68 | | rug | 68.08 | 76.75 | | field | 34.87 | 52.88 | | armchair | 50.63 | 76.22 | | seat | 65.51 | 82.53 | | fence | 47.17 | 66.71 | | desk | 45.32 | 79.59 | | rock | 49.19 | 66.7 | | wardrobe | 54.28 | 70.22 | | lamp | 60.73 | 75.93 | | bathtub | 82.15 | 87.48 | | railing | 37.11 | 51.4 | | cushion | 59.1 | 74.55 | | base | 37.28 | 57.11 | | box | 27.16 | 36.53 | | column | 42.07 | 45.45 | | signboard | 34.72 | 55.27 | | chest of drawers | 31.37 | 36.86 | | counter | 44.44 | 67.76 | | sand | 40.16 | 56.75 | | sink | 70.73 | 79.39 | | skyscraper | 48.42 | 66.77 | | fireplace | 70.78 | 92.13 | | refrigerator | 66.94 | 77.01 | | grandstand | 39.47 | 65.02 | | path | 16.62 | 23.84 | | stairs | 17.23 | 18.78 | | runway | 63.38 | 74.56 | | case | 48.3 | 63.05 | | pool table | 90.19 | 96.9 | | pillow | 54.03 | 60.49 | | screen door | 60.41 | 76.47 | | stairway | 35.0 | 60.05 | | river | 18.73 | 35.31 | | bridge | 54.31 | 89.32 | | bookcase | 28.72 | 40.84 | | blind | 43.16 | 48.62 | | coffee table | 61.87 | 86.02 | | toilet | 86.2 | 93.08 | | flower | 35.78 | 58.54 | | book | 48.06 | 74.1 | | hill | 7.08 | 11.87 | | bench | 50.69 | 68.7 | | countertop | 55.53 | 67.68 | | stove | 76.49 | 87.24 | | palm | 52.24 | 77.18 | | kitchen island | 42.06 | 70.57 | | computer | 72.8 | 86.72 | | swivel chair | 40.65 | 65.22 | | boat | 42.52 | 84.34 | | bar | 51.14 | 53.75 | | arcade machine | 83.33 | 89.76 | | hovel | 17.9 | 24.97 | | bus | 88.14 | 90.2 | | towel | 64.68 | 72.43 | | light | 44.55 | 54.75 | | truck | 42.2 | 63.55 | | tower | 5.35 | 8.07 | | chandelier | 62.66 | 82.72 | | awning | 32.98 | 49.54 | | streetlight | 20.93 | 29.53 | | booth | 29.23 | 37.7 | | television receiver | 72.9 | 82.96 | | airplane | 54.41 | 58.87 | | dirt track | 15.79 | 23.29 | | apparel | 48.74 | 66.27 | | pole | 7.96 | 8.48 | | land | 2.96 | 3.43 | | bannister | 12.25 | 19.71 | | escalator | 38.15 | 44.31 | | ottoman | 47.5 | 69.85 | | bottle | 22.07 | 28.5 | | buffet | 37.76 | 39.85 | | poster | 28.5 | 35.51 | | stage | 9.65 | 13.07 | | van | 46.42 | 58.43 | | ship | 4.89 | 5.0 | | fountain | 19.79 | 20.14 | | conveyer belt | 81.15 | 97.3 | | canopy | 54.06 | 70.13 | | washer | 83.92 | 88.66 | | plaything | 27.11 | 43.55 | | swimming pool | 63.77 | 88.09 | | stool | 41.97 | 56.3 | | barrel | 40.12 | 45.26 | | basket | 34.61 | 48.8 | | waterfall | 43.53 | 57.9 | | tent | 84.51 | 98.23 | | bag | 18.05 | 22.45 | | minibike | 69.58 | 79.58 | | cradle | 73.88 | 97.49 | | oven | 59.6 | 76.73 | | ball | 22.02 | 22.39 | | food | 62.33 | 73.7 | | step | 13.92 | 16.04 | | tank | 56.5 | 60.07 | | trade name | 25.24 | 31.32 | | microwave | 81.87 | 90.57 | | pot | 46.16 | 53.49 | | animal | 70.83 | 74.72 | | bicycle | 55.91 | 66.41 | | lake | 44.37 | 66.03 | | dishwasher | 62.0 | 63.33 | | screen | 55.4 | 91.6 | | blanket | 8.33 | 9.42 | | sculpture | 59.29 | 62.25 | | hood | 60.98 | 70.33 | | sconce | 37.99 | 53.06 | | vase | 34.37 | 45.66 | | traffic light | 27.2 | 42.56 | | tray | 5.43 | 10.72 | | ashcan | 43.41 | 62.33 | | fan | 56.26 | 69.73 | | pier | 36.42 | 40.09 | | crt screen | 0.0 | 0.0 | | plate | 54.92 | 70.28 | | monitor | 56.47 | 64.85 | | bulletin board | 51.99 | 62.46 | | shower | 0.0 | 0.0 | | radiator | 57.33 | 66.21 | | glass | 15.02 | 16.6 | | clock | 17.88 | 18.56 | | flag | 66.93 | 75.94 | +---------------------+-------+-------+ 2023-11-02 19:32:22,552 - mmseg - INFO - Summary: 2023-11-02 19:32:22,552 - mmseg - INFO - +-------+-------+------+ | aAcc | mIoU | mAcc | +-------+-------+------+ | 82.89 | 48.97 | 61.2 | +-------+-------+------+ 2023-11-02 19:32:22,553 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 19:32:22,554 - mmseg - INFO - Iter(val) [250] aAcc: 0.8289, mIoU: 0.4897, mAcc: 0.6120, IoU.wall: 0.7659, IoU.building: 0.8195, IoU.sky: 0.9341, IoU.floor: 0.8150, IoU.tree: 0.7398, IoU.ceiling: 0.8301, IoU.road: 0.8086, IoU.bed : 0.8945, IoU.windowpane: 0.6336, IoU.grass: 0.7073, IoU.cabinet: 0.6340, IoU.sidewalk: 0.6311, IoU.person: 0.8055, IoU.earth: 0.3392, IoU.door: 0.5158, IoU.table: 0.6027, IoU.mountain: 0.6140, IoU.plant: 0.5221, IoU.curtain: 0.7387, IoU.chair: 0.5575, IoU.car: 0.8346, IoU.water: 0.5029, IoU.painting: 0.6811, IoU.sofa: 0.7304, IoU.shelf: 0.3856, IoU.house: 0.3232, IoU.sea: 0.5726, IoU.mirror: 0.6683, IoU.rug: 0.6808, IoU.field: 0.3487, IoU.armchair: 0.5063, IoU.seat: 0.6551, IoU.fence: 0.4717, IoU.desk: 0.4532, IoU.rock: 0.4919, IoU.wardrobe: 0.5428, IoU.lamp: 0.6073, IoU.bathtub: 0.8215, IoU.railing: 0.3711, IoU.cushion: 0.5910, IoU.base: 0.3728, IoU.box: 0.2716, IoU.column: 0.4207, IoU.signboard: 0.3472, IoU.chest of drawers: 0.3137, IoU.counter: 0.4444, IoU.sand: 0.4016, IoU.sink: 0.7073, IoU.skyscraper: 0.4842, IoU.fireplace: 0.7078, IoU.refrigerator: 0.6694, IoU.grandstand: 0.3947, IoU.path: 0.1662, IoU.stairs: 0.1723, IoU.runway: 0.6338, IoU.case: 0.4830, IoU.pool table: 0.9019, IoU.pillow: 0.5403, IoU.screen door: 0.6041, IoU.stairway: 0.3500, IoU.river: 0.1873, IoU.bridge: 0.5431, IoU.bookcase: 0.2872, IoU.blind: 0.4316, IoU.coffee table: 0.6187, IoU.toilet: 0.8620, IoU.flower: 0.3578, IoU.book: 0.4806, IoU.hill: 0.0708, IoU.bench: 0.5069, IoU.countertop: 0.5553, IoU.stove: 0.7649, IoU.palm: 0.5224, IoU.kitchen island: 0.4206, IoU.computer: 0.7280, IoU.swivel chair: 0.4065, IoU.boat: 0.4252, IoU.bar: 0.5114, IoU.arcade machine: 0.8333, IoU.hovel: 0.1790, IoU.bus: 0.8814, IoU.towel: 0.6468, IoU.light: 0.4455, IoU.truck: 0.4220, IoU.tower: 0.0535, IoU.chandelier: 0.6266, IoU.awning: 0.3298, IoU.streetlight: 0.2093, IoU.booth: 0.2923, IoU.television receiver: 0.7290, IoU.airplane: 0.5441, IoU.dirt track: 0.1579, IoU.apparel: 0.4874, IoU.pole: 0.0796, IoU.land: 0.0296, IoU.bannister: 0.1225, IoU.escalator: 0.3815, IoU.ottoman: 0.4750, IoU.bottle: 0.2207, IoU.buffet: 0.3776, IoU.poster: 0.2850, IoU.stage: 0.0965, IoU.van: 0.4642, IoU.ship: 0.0489, IoU.fountain: 0.1979, IoU.conveyer belt: 0.8115, IoU.canopy: 0.5406, IoU.washer: 0.8392, IoU.plaything: 0.2711, IoU.swimming pool: 0.6377, IoU.stool: 0.4197, IoU.barrel: 0.4012, IoU.basket: 0.3461, IoU.waterfall: 0.4353, IoU.tent: 0.8451, IoU.bag: 0.1805, IoU.minibike: 0.6958, IoU.cradle: 0.7388, IoU.oven: 0.5960, IoU.ball: 0.2202, IoU.food: 0.6233, IoU.step: 0.1392, IoU.tank: 0.5650, IoU.trade name: 0.2524, IoU.microwave: 0.8187, IoU.pot: 0.4616, IoU.animal: 0.7083, IoU.bicycle: 0.5591, IoU.lake: 0.4437, IoU.dishwasher: 0.6200, IoU.screen: 0.5540, IoU.blanket: 0.0833, IoU.sculpture: 0.5929, IoU.hood: 0.6098, IoU.sconce: 0.3799, IoU.vase: 0.3437, IoU.traffic light: 0.2720, IoU.tray: 0.0543, IoU.ashcan: 0.4341, IoU.fan: 0.5626, IoU.pier: 0.3642, IoU.crt screen: 0.0000, IoU.plate: 0.5492, IoU.monitor: 0.5647, IoU.bulletin board: 0.5199, IoU.shower: 0.0000, IoU.radiator: 0.5733, IoU.glass: 0.1502, IoU.clock: 0.1788, IoU.flag: 0.6693, Acc.wall: 0.8656, Acc.building: 0.9311, Acc.sky: 0.9705, Acc.floor: 0.9010, Acc.tree: 0.8754, Acc.ceiling: 0.8977, Acc.road: 0.9146, Acc.bed : 0.9574, Acc.windowpane: 0.8101, Acc.grass: 0.9103, Acc.cabinet: 0.7909, Acc.sidewalk: 0.7863, Acc.person: 0.8963, Acc.earth: 0.4254, Acc.door: 0.7190, Acc.table: 0.7169, Acc.mountain: 0.7234, Acc.plant: 0.6235, Acc.curtain: 0.8665, Acc.chair: 0.6739, Acc.car: 0.9188, Acc.water: 0.6491, Acc.painting: 0.8985, Acc.sofa: 0.8093, Acc.shelf: 0.5060, Acc.house: 0.3772, Acc.sea: 0.8298, Acc.mirror: 0.8368, Acc.rug: 0.7675, Acc.field: 0.5288, Acc.armchair: 0.7622, Acc.seat: 0.8253, Acc.fence: 0.6671, Acc.desk: 0.7959, Acc.rock: 0.6670, Acc.wardrobe: 0.7022, Acc.lamp: 0.7593, Acc.bathtub: 0.8748, Acc.railing: 0.5140, Acc.cushion: 0.7455, Acc.base: 0.5711, Acc.box: 0.3653, Acc.column: 0.4545, Acc.signboard: 0.5527, Acc.chest of drawers: 0.3686, Acc.counter: 0.6776, Acc.sand: 0.5675, Acc.sink: 0.7939, Acc.skyscraper: 0.6677, Acc.fireplace: 0.9213, Acc.refrigerator: 0.7701, Acc.grandstand: 0.6502, Acc.path: 0.2384, Acc.stairs: 0.1878, Acc.runway: 0.7456, Acc.case: 0.6305, Acc.pool table: 0.9690, Acc.pillow: 0.6049, Acc.screen door: 0.7647, Acc.stairway: 0.6005, Acc.river: 0.3531, Acc.bridge: 0.8932, Acc.bookcase: 0.4084, Acc.blind: 0.4862, Acc.coffee table: 0.8602, Acc.toilet: 0.9308, Acc.flower: 0.5854, Acc.book: 0.7410, Acc.hill: 0.1187, Acc.bench: 0.6870, Acc.countertop: 0.6768, Acc.stove: 0.8724, Acc.palm: 0.7718, Acc.kitchen island: 0.7057, Acc.computer: 0.8672, Acc.swivel chair: 0.6522, Acc.boat: 0.8434, Acc.bar: 0.5375, Acc.arcade machine: 0.8976, Acc.hovel: 0.2497, Acc.bus: 0.9020, Acc.towel: 0.7243, Acc.light: 0.5475, Acc.truck: 0.6355, Acc.tower: 0.0807, Acc.chandelier: 0.8272, Acc.awning: 0.4954, Acc.streetlight: 0.2953, Acc.booth: 0.3770, Acc.television receiver: 0.8296, Acc.airplane: 0.5887, Acc.dirt track: 0.2329, Acc.apparel: 0.6627, Acc.pole: 0.0848, Acc.land: 0.0343, Acc.bannister: 0.1971, Acc.escalator: 0.4431, Acc.ottoman: 0.6985, Acc.bottle: 0.2850, Acc.buffet: 0.3985, Acc.poster: 0.3551, Acc.stage: 0.1307, Acc.van: 0.5843, Acc.ship: 0.0500, Acc.fountain: 0.2014, Acc.conveyer belt: 0.9730, Acc.canopy: 0.7013, Acc.washer: 0.8866, Acc.plaything: 0.4355, Acc.swimming pool: 0.8809, Acc.stool: 0.5630, Acc.barrel: 0.4526, Acc.basket: 0.4880, Acc.waterfall: 0.5790, Acc.tent: 0.9823, Acc.bag: 0.2245, Acc.minibike: 0.7958, Acc.cradle: 0.9749, Acc.oven: 0.7673, Acc.ball: 0.2239, Acc.food: 0.7370, Acc.step: 0.1604, Acc.tank: 0.6007, Acc.trade name: 0.3132, Acc.microwave: 0.9057, Acc.pot: 0.5349, Acc.animal: 0.7472, Acc.bicycle: 0.6641, Acc.lake: 0.6603, Acc.dishwasher: 0.6333, Acc.screen: 0.9160, Acc.blanket: 0.0942, Acc.sculpture: 0.6225, Acc.hood: 0.7033, Acc.sconce: 0.5306, Acc.vase: 0.4566, Acc.traffic light: 0.4256, Acc.tray: 0.1072, Acc.ashcan: 0.6233, Acc.fan: 0.6973, Acc.pier: 0.4009, Acc.crt screen: 0.0000, Acc.plate: 0.7028, Acc.monitor: 0.6485, Acc.bulletin board: 0.6246, Acc.shower: 0.0000, Acc.radiator: 0.6621, Acc.glass: 0.1660, Acc.clock: 0.1856, Acc.flag: 0.7594 2023-11-02 19:33:23,180 - mmseg - INFO - Iter [2050/20000] lr: 2.908e-06, eta: 6:46:19, time: 2.374, data_time: 1.170, memory: 38534, decode.loss_ce: 0.4763, decode.acc_seg: 82.8537, loss: 0.4763 2023-11-02 19:34:23,715 - mmseg - INFO - Iter [2100/20000] lr: 2.900e-06, eta: 6:44:08, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4637, decode.acc_seg: 82.9974, loss: 0.4637 2023-11-02 19:35:24,241 - mmseg - INFO - Iter [2150/20000] lr: 2.892e-06, eta: 6:42:00, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.4818, decode.acc_seg: 82.6113, loss: 0.4818 2023-11-02 19:36:24,785 - mmseg - INFO - Iter [2200/20000] lr: 2.884e-06, eta: 6:39:56, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4439, decode.acc_seg: 83.7789, loss: 0.4439 2023-11-02 19:37:27,665 - mmseg - INFO - Iter [2250/20000] lr: 2.875e-06, eta: 6:38:13, time: 1.258, data_time: 0.054, memory: 38534, decode.loss_ce: 0.4507, decode.acc_seg: 83.9204, loss: 0.4507 2023-11-02 19:38:28,224 - mmseg - INFO - Iter [2300/20000] lr: 2.867e-06, eta: 6:36:14, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4568, decode.acc_seg: 83.1264, loss: 0.4568 2023-11-02 19:39:28,739 - mmseg - INFO - Iter [2350/20000] lr: 2.859e-06, eta: 6:34:17, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4226, decode.acc_seg: 84.3904, loss: 0.4226 2023-11-02 19:40:29,278 - mmseg - INFO - Iter [2400/20000] lr: 2.851e-06, eta: 6:32:22, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4230, decode.acc_seg: 84.3145, loss: 0.4230 2023-11-02 19:41:29,810 - mmseg - INFO - Iter [2450/20000] lr: 2.843e-06, eta: 6:30:30, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4318, decode.acc_seg: 84.2956, loss: 0.4318 2023-11-02 19:42:30,399 - mmseg - INFO - Iter [2500/20000] lr: 2.835e-06, eta: 6:28:40, time: 1.212, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4334, decode.acc_seg: 83.8425, loss: 0.4334 2023-11-02 19:43:33,279 - mmseg - INFO - Iter [2550/20000] lr: 2.827e-06, eta: 6:27:08, time: 1.258, data_time: 0.053, memory: 38534, decode.loss_ce: 0.3891, decode.acc_seg: 85.3906, loss: 0.3891 2023-11-02 19:44:33,853 - mmseg - INFO - Iter [2600/20000] lr: 2.819e-06, eta: 6:25:21, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4002, decode.acc_seg: 85.0933, loss: 0.4002 2023-11-02 19:45:34,353 - mmseg - INFO - Iter [2650/20000] lr: 2.811e-06, eta: 6:23:36, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3940, decode.acc_seg: 85.5818, loss: 0.3940 2023-11-02 19:46:34,904 - mmseg - INFO - Iter [2700/20000] lr: 2.803e-06, eta: 6:21:52, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4094, decode.acc_seg: 84.7267, loss: 0.4094 2023-11-02 19:47:35,414 - mmseg - INFO - Iter [2750/20000] lr: 2.794e-06, eta: 6:20:10, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4053, decode.acc_seg: 84.6952, loss: 0.4053 2023-11-02 19:48:35,906 - mmseg - INFO - Iter [2800/20000] lr: 2.786e-06, eta: 6:18:29, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4088, decode.acc_seg: 84.7386, loss: 0.4088 2023-11-02 19:49:38,825 - mmseg - INFO - Iter [2850/20000] lr: 2.778e-06, eta: 6:17:05, time: 1.258, data_time: 0.053, memory: 38534, decode.loss_ce: 0.4117, decode.acc_seg: 84.9727, loss: 0.4117 2023-11-02 19:50:39,407 - mmseg - INFO - Iter [2900/20000] lr: 2.770e-06, eta: 6:15:27, time: 1.212, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3753, decode.acc_seg: 85.6552, loss: 0.3753 2023-11-02 19:51:39,953 - mmseg - INFO - Iter [2950/20000] lr: 2.762e-06, eta: 6:13:50, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3748, decode.acc_seg: 85.7881, loss: 0.3748 2023-11-02 19:52:40,463 - mmseg - INFO - Saving checkpoint at 3000 iterations 2023-11-02 19:53:35,088 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 19:53:35,088 - mmseg - INFO - Iter [3000/20000] lr: 2.754e-06, eta: 6:17:24, time: 2.303, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3963, decode.acc_seg: 85.6519, loss: 0.3963 2023-11-02 19:54:35,813 - mmseg - INFO - per class results: 2023-11-02 19:54:35,819 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 77.61 | 86.14 | | building | 82.6 | 93.85 | | sky | 93.68 | 96.44 | | floor | 81.68 | 90.41 | | tree | 73.99 | 90.2 | | ceiling | 83.73 | 91.19 | | road | 83.67 | 89.82 | | bed | 89.51 | 96.47 | | windowpane | 63.33 | 76.91 | | grass | 69.6 | 92.15 | | cabinet | 62.89 | 73.54 | | sidewalk | 63.1 | 78.45 | | person | 80.85 | 90.83 | | earth | 36.55 | 48.89 | | door | 52.59 | 78.27 | | table | 64.03 | 77.02 | | mountain | 60.35 | 78.35 | | plant | 50.89 | 59.63 | | curtain | 73.12 | 86.73 | | chair | 58.52 | 71.56 | | car | 83.21 | 92.02 | | water | 49.98 | 59.8 | | painting | 71.63 | 81.96 | | sofa | 74.27 | 82.87 | | shelf | 40.36 | 59.38 | | house | 43.32 | 56.66 | | sea | 63.43 | 78.57 | | mirror | 68.36 | 87.43 | | rug | 67.69 | 80.28 | | field | 34.37 | 50.24 | | armchair | 54.76 | 70.68 | | seat | 61.53 | 90.12 | | fence | 45.51 | 70.83 | | desk | 47.99 | 75.79 | | rock | 46.73 | 62.51 | | wardrobe | 54.11 | 62.33 | | lamp | 60.31 | 77.41 | | bathtub | 82.49 | 88.54 | | railing | 40.26 | 52.42 | | cushion | 58.07 | 71.95 | | base | 34.37 | 51.78 | | box | 27.58 | 33.94 | | column | 51.25 | 64.56 | | signboard | 32.42 | 45.06 | | chest of drawers | 38.93 | 75.32 | | counter | 47.78 | 63.63 | | sand | 38.29 | 51.11 | | sink | 73.71 | 81.61 | | skyscraper | 48.21 | 53.71 | | fireplace | 70.28 | 90.99 | | refrigerator | 75.4 | 88.85 | | grandstand | 49.04 | 66.82 | | path | 18.87 | 30.01 | | stairs | 28.53 | 36.14 | | runway | 73.94 | 93.74 | | case | 39.06 | 40.33 | | pool table | 92.09 | 97.29 | | pillow | 56.29 | 65.33 | | screen door | 56.8 | 65.48 | | stairway | 43.99 | 58.25 | | river | 15.61 | 58.9 | | bridge | 70.66 | 78.19 | | bookcase | 34.02 | 63.13 | | blind | 32.4 | 33.5 | | coffee table | 64.37 | 73.42 | | toilet | 85.7 | 91.59 | | flower | 40.46 | 53.13 | | book | 45.01 | 57.83 | | hill | 5.68 | 6.94 | | bench | 53.28 | 62.21 | | countertop | 53.15 | 73.87 | | stove | 74.23 | 85.59 | | palm | 43.66 | 54.65 | | kitchen island | 55.4 | 78.86 | | computer | 73.57 | 88.18 | | swivel chair | 49.55 | 70.32 | | boat | 46.96 | 89.63 | | bar | 59.92 | 66.14 | | arcade machine | 77.26 | 79.97 | | hovel | 15.43 | 16.63 | | bus | 89.29 | 92.17 | | towel | 66.41 | 83.62 | | light | 46.03 | 59.37 | | truck | 46.13 | 58.01 | | tower | 2.53 | 3.25 | | chandelier | 62.79 | 81.82 | | awning | 25.65 | 27.56 | | streetlight | 24.06 | 31.85 | | booth | 30.96 | 36.98 | | television receiver | 71.88 | 85.92 | | airplane | 54.05 | 64.75 | | dirt track | 8.72 | 15.9 | | apparel | 51.8 | 82.0 | | pole | 20.46 | 25.63 | | land | 2.6 | 4.37 | | bannister | 15.64 | 20.38 | | escalator | 49.28 | 60.64 | | ottoman | 43.22 | 71.7 | | bottle | 22.11 | 29.64 | | buffet | 46.0 | 61.96 | | poster | 26.96 | 53.33 | | stage | 13.77 | 31.23 | | van | 48.85 | 63.01 | | ship | 0.97 | 0.99 | | fountain | 29.94 | 30.95 | | conveyer belt | 80.36 | 94.93 | | canopy | 52.81 | 65.46 | | washer | 82.83 | 91.99 | | plaything | 30.75 | 52.9 | | swimming pool | 55.84 | 78.11 | | stool | 41.89 | 61.12 | | barrel | 42.85 | 49.19 | | basket | 37.68 | 54.98 | | waterfall | 47.34 | 62.79 | | tent | 91.45 | 97.77 | | bag | 22.49 | 26.77 | | minibike | 68.73 | 84.04 | | cradle | 77.01 | 97.1 | | oven | 60.87 | 71.09 | | ball | 51.79 | 57.78 | | food | 62.98 | 72.57 | | step | 18.39 | 25.85 | | tank | 55.0 | 64.47 | | trade name | 17.27 | 19.32 | | microwave | 85.66 | 92.88 | | pot | 44.56 | 49.86 | | animal | 77.33 | 84.11 | | bicycle | 57.0 | 67.3 | | lake | 19.45 | 20.31 | | dishwasher | 66.35 | 71.78 | | screen | 55.31 | 90.41 | | blanket | 9.34 | 10.39 | | sculpture | 57.11 | 60.26 | | hood | 56.7 | 71.79 | | sconce | 35.62 | 42.67 | | vase | 37.33 | 53.52 | | traffic light | 26.18 | 44.27 | | tray | 7.23 | 11.13 | | ashcan | 47.36 | 60.54 | | fan | 58.25 | 75.86 | | pier | 36.0 | 44.1 | | crt screen | 0.15 | 0.17 | | plate | 54.82 | 77.15 | | monitor | 55.41 | 60.2 | | bulletin board | 51.38 | 69.11 | | shower | 0.15 | 0.23 | | radiator | 56.39 | 65.78 | | glass | 16.16 | 17.99 | | clock | 23.92 | 26.01 | | flag | 64.94 | 71.39 | +---------------------+-------+-------+ 2023-11-02 19:54:35,819 - mmseg - INFO - Summary: 2023-11-02 19:54:35,819 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 83.37 | 50.28 | 62.53 | +-------+-------+-------+ 2023-11-02 19:54:35,819 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 19:54:35,820 - mmseg - INFO - Iter(val) [250] aAcc: 0.8337, mIoU: 0.5028, mAcc: 0.6253, IoU.wall: 0.7761, IoU.building: 0.8260, IoU.sky: 0.9368, IoU.floor: 0.8168, IoU.tree: 0.7399, IoU.ceiling: 0.8373, IoU.road: 0.8367, IoU.bed : 0.8951, IoU.windowpane: 0.6333, IoU.grass: 0.6960, IoU.cabinet: 0.6289, IoU.sidewalk: 0.6310, IoU.person: 0.8085, IoU.earth: 0.3655, IoU.door: 0.5259, IoU.table: 0.6403, IoU.mountain: 0.6035, IoU.plant: 0.5089, IoU.curtain: 0.7312, IoU.chair: 0.5852, IoU.car: 0.8321, IoU.water: 0.4998, IoU.painting: 0.7163, IoU.sofa: 0.7427, IoU.shelf: 0.4036, IoU.house: 0.4332, IoU.sea: 0.6343, IoU.mirror: 0.6836, IoU.rug: 0.6769, IoU.field: 0.3437, IoU.armchair: 0.5476, IoU.seat: 0.6153, IoU.fence: 0.4551, IoU.desk: 0.4799, IoU.rock: 0.4673, IoU.wardrobe: 0.5411, IoU.lamp: 0.6031, IoU.bathtub: 0.8249, IoU.railing: 0.4026, IoU.cushion: 0.5807, IoU.base: 0.3437, IoU.box: 0.2758, IoU.column: 0.5125, IoU.signboard: 0.3242, IoU.chest of drawers: 0.3893, IoU.counter: 0.4778, IoU.sand: 0.3829, IoU.sink: 0.7371, IoU.skyscraper: 0.4821, IoU.fireplace: 0.7028, IoU.refrigerator: 0.7540, IoU.grandstand: 0.4904, IoU.path: 0.1887, IoU.stairs: 0.2853, IoU.runway: 0.7394, IoU.case: 0.3906, IoU.pool table: 0.9209, IoU.pillow: 0.5629, IoU.screen door: 0.5680, IoU.stairway: 0.4399, IoU.river: 0.1561, IoU.bridge: 0.7066, IoU.bookcase: 0.3402, IoU.blind: 0.3240, IoU.coffee table: 0.6437, IoU.toilet: 0.8570, IoU.flower: 0.4046, IoU.book: 0.4501, IoU.hill: 0.0568, IoU.bench: 0.5328, IoU.countertop: 0.5315, IoU.stove: 0.7423, IoU.palm: 0.4366, IoU.kitchen island: 0.5540, IoU.computer: 0.7357, IoU.swivel chair: 0.4955, IoU.boat: 0.4696, IoU.bar: 0.5992, IoU.arcade machine: 0.7726, IoU.hovel: 0.1543, IoU.bus: 0.8929, IoU.towel: 0.6641, IoU.light: 0.4603, IoU.truck: 0.4613, IoU.tower: 0.0253, IoU.chandelier: 0.6279, IoU.awning: 0.2565, IoU.streetlight: 0.2406, IoU.booth: 0.3096, IoU.television receiver: 0.7188, IoU.airplane: 0.5405, IoU.dirt track: 0.0872, IoU.apparel: 0.5180, IoU.pole: 0.2046, IoU.land: 0.0260, IoU.bannister: 0.1564, IoU.escalator: 0.4928, IoU.ottoman: 0.4322, IoU.bottle: 0.2211, IoU.buffet: 0.4600, IoU.poster: 0.2696, IoU.stage: 0.1377, IoU.van: 0.4885, IoU.ship: 0.0097, IoU.fountain: 0.2994, IoU.conveyer belt: 0.8036, IoU.canopy: 0.5281, IoU.washer: 0.8283, IoU.plaything: 0.3075, IoU.swimming pool: 0.5584, IoU.stool: 0.4189, IoU.barrel: 0.4285, IoU.basket: 0.3768, IoU.waterfall: 0.4734, IoU.tent: 0.9145, IoU.bag: 0.2249, IoU.minibike: 0.6873, IoU.cradle: 0.7701, IoU.oven: 0.6087, IoU.ball: 0.5179, IoU.food: 0.6298, IoU.step: 0.1839, IoU.tank: 0.5500, IoU.trade name: 0.1727, IoU.microwave: 0.8566, IoU.pot: 0.4456, IoU.animal: 0.7733, IoU.bicycle: 0.5700, IoU.lake: 0.1945, IoU.dishwasher: 0.6635, IoU.screen: 0.5531, IoU.blanket: 0.0934, IoU.sculpture: 0.5711, IoU.hood: 0.5670, IoU.sconce: 0.3562, IoU.vase: 0.3733, IoU.traffic light: 0.2618, IoU.tray: 0.0723, IoU.ashcan: 0.4736, IoU.fan: 0.5825, IoU.pier: 0.3600, IoU.crt screen: 0.0015, IoU.plate: 0.5482, IoU.monitor: 0.5541, IoU.bulletin board: 0.5138, IoU.shower: 0.0015, IoU.radiator: 0.5639, IoU.glass: 0.1616, IoU.clock: 0.2392, IoU.flag: 0.6494, Acc.wall: 0.8614, Acc.building: 0.9385, Acc.sky: 0.9644, Acc.floor: 0.9041, Acc.tree: 0.9020, Acc.ceiling: 0.9119, Acc.road: 0.8982, Acc.bed : 0.9647, Acc.windowpane: 0.7691, Acc.grass: 0.9215, Acc.cabinet: 0.7354, Acc.sidewalk: 0.7845, Acc.person: 0.9083, Acc.earth: 0.4889, Acc.door: 0.7827, Acc.table: 0.7702, Acc.mountain: 0.7835, Acc.plant: 0.5963, Acc.curtain: 0.8673, Acc.chair: 0.7156, Acc.car: 0.9202, Acc.water: 0.5980, Acc.painting: 0.8196, Acc.sofa: 0.8287, Acc.shelf: 0.5938, Acc.house: 0.5666, Acc.sea: 0.7857, Acc.mirror: 0.8743, Acc.rug: 0.8028, Acc.field: 0.5024, Acc.armchair: 0.7068, Acc.seat: 0.9012, Acc.fence: 0.7083, Acc.desk: 0.7579, Acc.rock: 0.6251, Acc.wardrobe: 0.6233, Acc.lamp: 0.7741, Acc.bathtub: 0.8854, Acc.railing: 0.5242, Acc.cushion: 0.7195, Acc.base: 0.5178, Acc.box: 0.3394, Acc.column: 0.6456, Acc.signboard: 0.4506, Acc.chest of drawers: 0.7532, Acc.counter: 0.6363, Acc.sand: 0.5111, Acc.sink: 0.8161, Acc.skyscraper: 0.5371, Acc.fireplace: 0.9099, Acc.refrigerator: 0.8885, Acc.grandstand: 0.6682, Acc.path: 0.3001, Acc.stairs: 0.3614, Acc.runway: 0.9374, Acc.case: 0.4033, Acc.pool table: 0.9729, Acc.pillow: 0.6533, Acc.screen door: 0.6548, Acc.stairway: 0.5825, Acc.river: 0.5890, Acc.bridge: 0.7819, Acc.bookcase: 0.6313, Acc.blind: 0.3350, Acc.coffee table: 0.7342, Acc.toilet: 0.9159, Acc.flower: 0.5313, Acc.book: 0.5783, Acc.hill: 0.0694, Acc.bench: 0.6221, Acc.countertop: 0.7387, Acc.stove: 0.8559, Acc.palm: 0.5465, Acc.kitchen island: 0.7886, Acc.computer: 0.8818, Acc.swivel chair: 0.7032, Acc.boat: 0.8963, Acc.bar: 0.6614, Acc.arcade machine: 0.7997, Acc.hovel: 0.1663, Acc.bus: 0.9217, Acc.towel: 0.8362, Acc.light: 0.5937, Acc.truck: 0.5801, Acc.tower: 0.0325, Acc.chandelier: 0.8182, Acc.awning: 0.2756, Acc.streetlight: 0.3185, Acc.booth: 0.3698, Acc.television receiver: 0.8592, Acc.airplane: 0.6475, Acc.dirt track: 0.1590, Acc.apparel: 0.8200, Acc.pole: 0.2563, Acc.land: 0.0437, Acc.bannister: 0.2038, Acc.escalator: 0.6064, Acc.ottoman: 0.7170, Acc.bottle: 0.2964, Acc.buffet: 0.6196, Acc.poster: 0.5333, Acc.stage: 0.3123, Acc.van: 0.6301, Acc.ship: 0.0099, Acc.fountain: 0.3095, Acc.conveyer belt: 0.9493, Acc.canopy: 0.6546, Acc.washer: 0.9199, Acc.plaything: 0.5290, Acc.swimming pool: 0.7811, Acc.stool: 0.6112, Acc.barrel: 0.4919, Acc.basket: 0.5498, Acc.waterfall: 0.6279, Acc.tent: 0.9777, Acc.bag: 0.2677, Acc.minibike: 0.8404, Acc.cradle: 0.9710, Acc.oven: 0.7109, Acc.ball: 0.5778, Acc.food: 0.7257, Acc.step: 0.2585, Acc.tank: 0.6447, Acc.trade name: 0.1932, Acc.microwave: 0.9288, Acc.pot: 0.4986, Acc.animal: 0.8411, Acc.bicycle: 0.6730, Acc.lake: 0.2031, Acc.dishwasher: 0.7178, Acc.screen: 0.9041, Acc.blanket: 0.1039, Acc.sculpture: 0.6026, Acc.hood: 0.7179, Acc.sconce: 0.4267, Acc.vase: 0.5352, Acc.traffic light: 0.4427, Acc.tray: 0.1113, Acc.ashcan: 0.6054, Acc.fan: 0.7586, Acc.pier: 0.4410, Acc.crt screen: 0.0017, Acc.plate: 0.7715, Acc.monitor: 0.6020, Acc.bulletin board: 0.6911, Acc.shower: 0.0023, Acc.radiator: 0.6578, Acc.glass: 0.1799, Acc.clock: 0.2601, Acc.flag: 0.7139 2023-11-02 19:55:36,403 - mmseg - INFO - Iter [3050/20000] lr: 2.746e-06, eta: 6:21:22, time: 2.426, data_time: 1.222, memory: 38534, decode.loss_ce: 0.3763, decode.acc_seg: 85.5492, loss: 0.3763 2023-11-02 19:56:36,911 - mmseg - INFO - Iter [3100/20000] lr: 2.738e-06, eta: 6:19:36, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.4268, decode.acc_seg: 84.5497, loss: 0.4268 2023-11-02 19:57:37,418 - mmseg - INFO - Iter [3150/20000] lr: 2.730e-06, eta: 6:17:52, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.4096, decode.acc_seg: 84.8819, loss: 0.4096 2023-11-02 19:58:40,196 - mmseg - INFO - Iter [3200/20000] lr: 2.722e-06, eta: 6:16:21, time: 1.256, data_time: 0.050, memory: 38534, decode.loss_ce: 0.3988, decode.acc_seg: 84.9992, loss: 0.3988 2023-11-02 19:59:40,712 - mmseg - INFO - Iter [3250/20000] lr: 2.713e-06, eta: 6:14:39, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.4087, decode.acc_seg: 85.1685, loss: 0.4087 2023-11-02 20:00:41,243 - mmseg - INFO - Iter [3300/20000] lr: 2.705e-06, eta: 6:12:59, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3821, decode.acc_seg: 85.8676, loss: 0.3821 2023-11-02 20:01:41,738 - mmseg - INFO - Iter [3350/20000] lr: 2.697e-06, eta: 6:11:20, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3539, decode.acc_seg: 86.3600, loss: 0.3539 2023-11-02 20:02:42,272 - mmseg - INFO - Iter [3400/20000] lr: 2.689e-06, eta: 6:09:42, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3815, decode.acc_seg: 85.6357, loss: 0.3815 2023-11-02 20:03:42,814 - mmseg - INFO - Iter [3450/20000] lr: 2.681e-06, eta: 6:08:05, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3616, decode.acc_seg: 86.7740, loss: 0.3616 2023-11-02 20:04:45,780 - mmseg - INFO - Iter [3500/20000] lr: 2.673e-06, eta: 6:06:40, time: 1.259, data_time: 0.056, memory: 38534, decode.loss_ce: 0.3572, decode.acc_seg: 86.2248, loss: 0.3572 2023-11-02 20:05:46,303 - mmseg - INFO - Iter [3550/20000] lr: 2.665e-06, eta: 6:05:05, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3391, decode.acc_seg: 87.0361, loss: 0.3391 2023-11-02 20:06:46,800 - mmseg - INFO - Iter [3600/20000] lr: 2.657e-06, eta: 6:03:31, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3279, decode.acc_seg: 87.5706, loss: 0.3279 2023-11-02 20:07:47,352 - mmseg - INFO - Iter [3650/20000] lr: 2.649e-06, eta: 6:01:58, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3642, decode.acc_seg: 86.4379, loss: 0.3642 2023-11-02 20:08:47,850 - mmseg - INFO - Iter [3700/20000] lr: 2.641e-06, eta: 6:00:25, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3454, decode.acc_seg: 86.9671, loss: 0.3454 2023-11-02 20:09:48,365 - mmseg - INFO - Iter [3750/20000] lr: 2.632e-06, eta: 5:58:54, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3637, decode.acc_seg: 86.5543, loss: 0.3637 2023-11-02 20:10:51,330 - mmseg - INFO - Iter [3800/20000] lr: 2.624e-06, eta: 5:57:33, time: 1.259, data_time: 0.055, memory: 38534, decode.loss_ce: 0.3556, decode.acc_seg: 86.3449, loss: 0.3556 2023-11-02 20:11:51,902 - mmseg - INFO - Iter [3850/20000] lr: 2.616e-06, eta: 5:56:03, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3383, decode.acc_seg: 87.4556, loss: 0.3383 2023-11-02 20:12:52,447 - mmseg - INFO - Iter [3900/20000] lr: 2.608e-06, eta: 5:54:34, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3278, decode.acc_seg: 87.6375, loss: 0.3278 2023-11-02 20:13:52,981 - mmseg - INFO - Iter [3950/20000] lr: 2.600e-06, eta: 5:53:06, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3428, decode.acc_seg: 86.8686, loss: 0.3428 2023-11-02 20:14:53,584 - mmseg - INFO - Saving checkpoint at 4000 iterations 2023-11-02 20:15:53,411 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 20:15:53,412 - mmseg - INFO - Iter [4000/20000] lr: 2.592e-06, eta: 5:55:37, time: 2.409, data_time: 0.009, memory: 38534, decode.loss_ce: 0.3185, decode.acc_seg: 87.6655, loss: 0.3185 2023-11-02 20:16:53,869 - mmseg - INFO - per class results: 2023-11-02 20:16:53,874 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 77.71 | 87.48 | | building | 82.01 | 92.25 | | sky | 93.77 | 97.03 | | floor | 81.66 | 89.28 | | tree | 73.21 | 85.25 | | ceiling | 84.62 | 93.43 | | road | 83.92 | 89.98 | | bed | 90.64 | 96.04 | | windowpane | 64.22 | 81.12 | | grass | 71.49 | 86.68 | | cabinet | 61.35 | 71.37 | | sidewalk | 63.01 | 76.77 | | person | 81.03 | 90.34 | | earth | 39.05 | 54.62 | | door | 54.76 | 66.57 | | table | 63.66 | 74.22 | | mountain | 60.58 | 78.94 | | plant | 52.75 | 65.19 | | curtain | 75.49 | 87.94 | | chair | 56.52 | 67.26 | | car | 83.02 | 93.96 | | water | 50.19 | 58.98 | | painting | 72.27 | 88.1 | | sofa | 74.53 | 89.79 | | shelf | 45.92 | 70.58 | | house | 45.07 | 73.75 | | sea | 56.63 | 85.71 | | mirror | 73.14 | 83.25 | | rug | 66.36 | 81.21 | | field | 35.85 | 56.07 | | armchair | 50.06 | 65.19 | | seat | 62.03 | 90.05 | | fence | 46.43 | 66.22 | | desk | 45.74 | 71.16 | | rock | 48.83 | 63.76 | | wardrobe | 50.19 | 70.03 | | lamp | 62.7 | 73.3 | | bathtub | 84.0 | 88.8 | | railing | 42.54 | 62.42 | | cushion | 60.86 | 73.23 | | base | 28.76 | 41.0 | | box | 26.93 | 33.85 | | column | 47.64 | 57.28 | | signboard | 37.58 | 51.42 | | chest of drawers | 41.68 | 61.24 | | counter | 45.09 | 63.14 | | sand | 36.7 | 52.67 | | sink | 71.99 | 79.91 | | skyscraper | 46.89 | 58.54 | | fireplace | 70.67 | 93.14 | | refrigerator | 73.41 | 87.54 | | grandstand | 44.01 | 68.77 | | path | 18.5 | 38.67 | | stairs | 26.67 | 34.16 | | runway | 52.67 | 65.79 | | case | 56.95 | 69.0 | | pool table | 91.61 | 96.72 | | pillow | 61.0 | 71.19 | | screen door | 66.87 | 86.9 | | stairway | 32.53 | 48.85 | | river | 14.87 | 29.2 | | bridge | 64.24 | 78.88 | | bookcase | 39.2 | 47.47 | | blind | 39.22 | 42.8 | | coffee table | 63.11 | 85.5 | | toilet | 87.35 | 91.99 | | flower | 37.33 | 47.16 | | book | 48.6 | 65.8 | | hill | 6.74 | 7.68 | | bench | 46.81 | 54.45 | | countertop | 58.29 | 73.83 | | stove | 76.76 | 90.71 | | palm | 48.78 | 78.43 | | kitchen island | 51.74 | 64.25 | | computer | 73.35 | 89.4 | | swivel chair | 43.49 | 75.26 | | boat | 46.76 | 87.07 | | bar | 58.53 | 61.94 | | arcade machine | 75.61 | 77.2 | | hovel | 12.59 | 16.37 | | bus | 89.02 | 91.96 | | towel | 67.33 | 81.72 | | light | 44.99 | 51.03 | | truck | 45.39 | 58.45 | | tower | 17.13 | 32.26 | | chandelier | 63.28 | 84.88 | | awning | 33.96 | 44.56 | | streetlight | 25.4 | 32.77 | | booth | 29.39 | 35.18 | | television receiver | 69.95 | 86.41 | | airplane | 57.29 | 64.31 | | dirt track | 19.33 | 25.79 | | apparel | 51.18 | 64.96 | | pole | 26.35 | 34.23 | | land | 3.41 | 4.31 | | bannister | 14.43 | 20.25 | | escalator | 59.67 | 75.39 | | ottoman | 46.27 | 66.57 | | bottle | 23.12 | 30.61 | | buffet | 47.71 | 70.2 | | poster | 23.42 | 29.85 | | stage | 11.53 | 24.39 | | van | 44.62 | 57.15 | | ship | 1.63 | 1.7 | | fountain | 24.01 | 24.33 | | conveyer belt | 77.18 | 95.14 | | canopy | 49.67 | 67.2 | | washer | 79.25 | 81.79 | | plaything | 26.34 | 45.42 | | swimming pool | 58.95 | 86.15 | | stool | 36.54 | 65.42 | | barrel | 50.55 | 56.54 | | basket | 36.42 | 57.04 | | waterfall | 54.1 | 68.56 | | tent | 92.93 | 98.46 | | bag | 17.7 | 20.41 | | minibike | 73.12 | 84.63 | | cradle | 75.07 | 96.9 | | oven | 61.16 | 75.81 | | ball | 31.16 | 33.43 | | food | 63.0 | 71.12 | | step | 18.09 | 21.56 | | tank | 50.28 | 61.16 | | trade name | 25.54 | 30.65 | | microwave | 85.48 | 92.59 | | pot | 45.19 | 50.6 | | animal | 70.46 | 73.12 | | bicycle | 58.98 | 76.05 | | lake | 39.9 | 73.22 | | dishwasher | 68.39 | 73.02 | | screen | 23.24 | 27.38 | | blanket | 25.9 | 29.94 | | sculpture | 61.55 | 66.55 | | hood | 58.62 | 70.31 | | sconce | 42.55 | 54.43 | | vase | 39.95 | 55.87 | | traffic light | 30.05 | 49.49 | | tray | 7.86 | 13.33 | | ashcan | 50.17 | 62.0 | | fan | 54.79 | 64.57 | | pier | 52.47 | 65.3 | | crt screen | 9.88 | 28.98 | | plate | 55.19 | 76.28 | | monitor | 42.94 | 47.42 | | bulletin board | 44.51 | 49.13 | | shower | 0.0 | 0.0 | | radiator | 54.76 | 62.47 | | glass | 16.67 | 18.11 | | clock | 26.6 | 29.71 | | flag | 62.78 | 67.95 | +---------------------+-------+-------+ 2023-11-02 20:16:53,876 - mmseg - INFO - Summary: 2023-11-02 20:16:53,876 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 83.43 | 50.57 | 63.01 | +-------+-------+-------+ 2023-11-02 20:16:53,877 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 20:16:53,877 - mmseg - INFO - Iter(val) [250] aAcc: 0.8343, mIoU: 0.5057, mAcc: 0.6301, IoU.wall: 0.7771, IoU.building: 0.8201, IoU.sky: 0.9377, IoU.floor: 0.8166, IoU.tree: 0.7321, IoU.ceiling: 0.8462, IoU.road: 0.8392, IoU.bed : 0.9064, IoU.windowpane: 0.6422, IoU.grass: 0.7149, IoU.cabinet: 0.6135, IoU.sidewalk: 0.6301, IoU.person: 0.8103, IoU.earth: 0.3905, IoU.door: 0.5476, IoU.table: 0.6366, IoU.mountain: 0.6058, IoU.plant: 0.5275, IoU.curtain: 0.7549, IoU.chair: 0.5652, IoU.car: 0.8302, IoU.water: 0.5019, IoU.painting: 0.7227, IoU.sofa: 0.7453, IoU.shelf: 0.4592, IoU.house: 0.4507, IoU.sea: 0.5663, IoU.mirror: 0.7314, IoU.rug: 0.6636, IoU.field: 0.3585, IoU.armchair: 0.5006, IoU.seat: 0.6203, IoU.fence: 0.4643, IoU.desk: 0.4574, IoU.rock: 0.4883, IoU.wardrobe: 0.5019, IoU.lamp: 0.6270, IoU.bathtub: 0.8400, IoU.railing: 0.4254, IoU.cushion: 0.6086, IoU.base: 0.2876, IoU.box: 0.2693, IoU.column: 0.4764, IoU.signboard: 0.3758, IoU.chest of drawers: 0.4168, IoU.counter: 0.4509, IoU.sand: 0.3670, IoU.sink: 0.7199, IoU.skyscraper: 0.4689, IoU.fireplace: 0.7067, IoU.refrigerator: 0.7341, IoU.grandstand: 0.4401, IoU.path: 0.1850, IoU.stairs: 0.2667, IoU.runway: 0.5267, IoU.case: 0.5695, IoU.pool table: 0.9161, IoU.pillow: 0.6100, IoU.screen door: 0.6687, IoU.stairway: 0.3253, IoU.river: 0.1487, IoU.bridge: 0.6424, IoU.bookcase: 0.3920, IoU.blind: 0.3922, IoU.coffee table: 0.6311, IoU.toilet: 0.8735, IoU.flower: 0.3733, IoU.book: 0.4860, IoU.hill: 0.0674, IoU.bench: 0.4681, IoU.countertop: 0.5829, IoU.stove: 0.7676, IoU.palm: 0.4878, IoU.kitchen island: 0.5174, IoU.computer: 0.7335, IoU.swivel chair: 0.4349, IoU.boat: 0.4676, IoU.bar: 0.5853, IoU.arcade machine: 0.7561, IoU.hovel: 0.1259, IoU.bus: 0.8902, IoU.towel: 0.6733, IoU.light: 0.4499, IoU.truck: 0.4539, IoU.tower: 0.1713, IoU.chandelier: 0.6328, IoU.awning: 0.3396, IoU.streetlight: 0.2540, IoU.booth: 0.2939, IoU.television receiver: 0.6995, IoU.airplane: 0.5729, IoU.dirt track: 0.1933, IoU.apparel: 0.5118, IoU.pole: 0.2635, IoU.land: 0.0341, IoU.bannister: 0.1443, IoU.escalator: 0.5967, IoU.ottoman: 0.4627, IoU.bottle: 0.2312, IoU.buffet: 0.4771, IoU.poster: 0.2342, IoU.stage: 0.1153, IoU.van: 0.4462, IoU.ship: 0.0163, IoU.fountain: 0.2401, IoU.conveyer belt: 0.7718, IoU.canopy: 0.4967, IoU.washer: 0.7925, IoU.plaything: 0.2634, IoU.swimming pool: 0.5895, IoU.stool: 0.3654, IoU.barrel: 0.5055, IoU.basket: 0.3642, IoU.waterfall: 0.5410, IoU.tent: 0.9293, IoU.bag: 0.1770, IoU.minibike: 0.7312, IoU.cradle: 0.7507, IoU.oven: 0.6116, IoU.ball: 0.3116, IoU.food: 0.6300, IoU.step: 0.1809, IoU.tank: 0.5028, IoU.trade name: 0.2554, IoU.microwave: 0.8548, IoU.pot: 0.4519, IoU.animal: 0.7046, IoU.bicycle: 0.5898, IoU.lake: 0.3990, IoU.dishwasher: 0.6839, IoU.screen: 0.2324, IoU.blanket: 0.2590, IoU.sculpture: 0.6155, IoU.hood: 0.5862, IoU.sconce: 0.4255, IoU.vase: 0.3995, IoU.traffic light: 0.3005, IoU.tray: 0.0786, IoU.ashcan: 0.5017, IoU.fan: 0.5479, IoU.pier: 0.5247, IoU.crt screen: 0.0988, IoU.plate: 0.5519, IoU.monitor: 0.4294, IoU.bulletin board: 0.4451, IoU.shower: 0.0000, IoU.radiator: 0.5476, IoU.glass: 0.1667, IoU.clock: 0.2660, IoU.flag: 0.6278, Acc.wall: 0.8748, Acc.building: 0.9225, Acc.sky: 0.9703, Acc.floor: 0.8928, Acc.tree: 0.8525, Acc.ceiling: 0.9343, Acc.road: 0.8998, Acc.bed : 0.9604, Acc.windowpane: 0.8112, Acc.grass: 0.8668, Acc.cabinet: 0.7137, Acc.sidewalk: 0.7677, Acc.person: 0.9034, Acc.earth: 0.5462, Acc.door: 0.6657, Acc.table: 0.7422, Acc.mountain: 0.7894, Acc.plant: 0.6519, Acc.curtain: 0.8794, Acc.chair: 0.6726, Acc.car: 0.9396, Acc.water: 0.5898, Acc.painting: 0.8810, Acc.sofa: 0.8979, Acc.shelf: 0.7058, Acc.house: 0.7375, Acc.sea: 0.8571, Acc.mirror: 0.8325, Acc.rug: 0.8121, Acc.field: 0.5607, Acc.armchair: 0.6519, Acc.seat: 0.9005, Acc.fence: 0.6622, Acc.desk: 0.7116, Acc.rock: 0.6376, Acc.wardrobe: 0.7003, Acc.lamp: 0.7330, Acc.bathtub: 0.8880, Acc.railing: 0.6242, Acc.cushion: 0.7323, Acc.base: 0.4100, Acc.box: 0.3385, Acc.column: 0.5728, Acc.signboard: 0.5142, Acc.chest of drawers: 0.6124, Acc.counter: 0.6314, Acc.sand: 0.5267, Acc.sink: 0.7991, Acc.skyscraper: 0.5854, Acc.fireplace: 0.9314, Acc.refrigerator: 0.8754, Acc.grandstand: 0.6877, Acc.path: 0.3867, Acc.stairs: 0.3416, Acc.runway: 0.6579, Acc.case: 0.6900, Acc.pool table: 0.9672, Acc.pillow: 0.7119, Acc.screen door: 0.8690, Acc.stairway: 0.4885, Acc.river: 0.2920, Acc.bridge: 0.7888, Acc.bookcase: 0.4747, Acc.blind: 0.4280, Acc.coffee table: 0.8550, Acc.toilet: 0.9199, Acc.flower: 0.4716, Acc.book: 0.6580, Acc.hill: 0.0768, Acc.bench: 0.5445, Acc.countertop: 0.7383, Acc.stove: 0.9071, Acc.palm: 0.7843, Acc.kitchen island: 0.6425, Acc.computer: 0.8940, Acc.swivel chair: 0.7526, Acc.boat: 0.8707, Acc.bar: 0.6194, Acc.arcade machine: 0.7720, Acc.hovel: 0.1637, Acc.bus: 0.9196, Acc.towel: 0.8172, Acc.light: 0.5103, Acc.truck: 0.5845, Acc.tower: 0.3226, Acc.chandelier: 0.8488, Acc.awning: 0.4456, Acc.streetlight: 0.3277, Acc.booth: 0.3518, Acc.television receiver: 0.8641, Acc.airplane: 0.6431, Acc.dirt track: 0.2579, Acc.apparel: 0.6496, Acc.pole: 0.3423, Acc.land: 0.0431, Acc.bannister: 0.2025, Acc.escalator: 0.7539, Acc.ottoman: 0.6657, Acc.bottle: 0.3061, Acc.buffet: 0.7020, Acc.poster: 0.2985, Acc.stage: 0.2439, Acc.van: 0.5715, Acc.ship: 0.0170, Acc.fountain: 0.2433, Acc.conveyer belt: 0.9514, Acc.canopy: 0.6720, Acc.washer: 0.8179, Acc.plaything: 0.4542, Acc.swimming pool: 0.8615, Acc.stool: 0.6542, Acc.barrel: 0.5654, Acc.basket: 0.5704, Acc.waterfall: 0.6856, Acc.tent: 0.9846, Acc.bag: 0.2041, Acc.minibike: 0.8463, Acc.cradle: 0.9690, Acc.oven: 0.7581, Acc.ball: 0.3343, Acc.food: 0.7112, Acc.step: 0.2156, Acc.tank: 0.6116, Acc.trade name: 0.3065, Acc.microwave: 0.9259, Acc.pot: 0.5060, Acc.animal: 0.7312, Acc.bicycle: 0.7605, Acc.lake: 0.7322, Acc.dishwasher: 0.7302, Acc.screen: 0.2738, Acc.blanket: 0.2994, Acc.sculpture: 0.6655, Acc.hood: 0.7031, Acc.sconce: 0.5443, Acc.vase: 0.5587, Acc.traffic light: 0.4949, Acc.tray: 0.1333, Acc.ashcan: 0.6200, Acc.fan: 0.6457, Acc.pier: 0.6530, Acc.crt screen: 0.2898, Acc.plate: 0.7628, Acc.monitor: 0.4742, Acc.bulletin board: 0.4913, Acc.shower: 0.0000, Acc.radiator: 0.6247, Acc.glass: 0.1811, Acc.clock: 0.2971, Acc.flag: 0.6795 2023-11-02 20:17:54,469 - mmseg - INFO - Iter [4050/20000] lr: 2.584e-06, eta: 5:58:05, time: 2.421, data_time: 1.217, memory: 38534, decode.loss_ce: 0.3347, decode.acc_seg: 87.1442, loss: 0.3347 2023-11-02 20:18:55,010 - mmseg - INFO - Iter [4100/20000] lr: 2.576e-06, eta: 5:56:31, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3575, decode.acc_seg: 86.4256, loss: 0.3575 2023-11-02 20:19:57,847 - mmseg - INFO - Iter [4150/20000] lr: 2.568e-06, eta: 5:55:07, time: 1.257, data_time: 0.052, memory: 38534, decode.loss_ce: 0.3085, decode.acc_seg: 87.8391, loss: 0.3085 2023-11-02 20:20:58,396 - mmseg - INFO - Iter [4200/20000] lr: 2.560e-06, eta: 5:53:35, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3202, decode.acc_seg: 87.4150, loss: 0.3202 2023-11-02 20:21:58,937 - mmseg - INFO - Iter [4250/20000] lr: 2.551e-06, eta: 5:52:03, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3272, decode.acc_seg: 87.3680, loss: 0.3272 2023-11-02 20:22:59,430 - mmseg - INFO - Iter [4300/20000] lr: 2.543e-06, eta: 5:50:32, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3364, decode.acc_seg: 87.2096, loss: 0.3364 2023-11-02 20:23:59,980 - mmseg - INFO - Iter [4350/20000] lr: 2.535e-06, eta: 5:49:02, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3232, decode.acc_seg: 87.7866, loss: 0.3232 2023-11-02 20:25:00,553 - mmseg - INFO - Iter [4400/20000] lr: 2.527e-06, eta: 5:47:32, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3452, decode.acc_seg: 87.4995, loss: 0.3452 2023-11-02 20:26:04,407 - mmseg - INFO - Iter [4450/20000] lr: 2.519e-06, eta: 5:46:15, time: 1.277, data_time: 0.066, memory: 38534, decode.loss_ce: 0.3172, decode.acc_seg: 87.6560, loss: 0.3172 2023-11-02 20:27:04,992 - mmseg - INFO - Iter [4500/20000] lr: 2.511e-06, eta: 5:44:47, time: 1.212, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3081, decode.acc_seg: 88.0473, loss: 0.3081 2023-11-02 20:28:05,542 - mmseg - INFO - Iter [4550/20000] lr: 2.503e-06, eta: 5:43:19, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3268, decode.acc_seg: 87.7443, loss: 0.3268 2023-11-02 20:29:06,112 - mmseg - INFO - Iter [4600/20000] lr: 2.495e-06, eta: 5:41:52, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3308, decode.acc_seg: 87.5899, loss: 0.3308 2023-11-02 20:30:06,717 - mmseg - INFO - Iter [4650/20000] lr: 2.487e-06, eta: 5:40:26, time: 1.212, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3117, decode.acc_seg: 87.9129, loss: 0.3117 2023-11-02 20:31:07,295 - mmseg - INFO - Iter [4700/20000] lr: 2.479e-06, eta: 5:39:00, time: 1.212, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3016, decode.acc_seg: 88.3273, loss: 0.3016 2023-11-02 20:32:10,233 - mmseg - INFO - Iter [4750/20000] lr: 2.471e-06, eta: 5:37:42, time: 1.259, data_time: 0.051, memory: 38534, decode.loss_ce: 0.3058, decode.acc_seg: 88.5085, loss: 0.3058 2023-11-02 20:33:10,763 - mmseg - INFO - Iter [4800/20000] lr: 2.462e-06, eta: 5:36:17, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2966, decode.acc_seg: 88.7531, loss: 0.2966 2023-11-02 20:34:11,304 - mmseg - INFO - Iter [4850/20000] lr: 2.454e-06, eta: 5:34:52, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3222, decode.acc_seg: 87.5548, loss: 0.3222 2023-11-02 20:35:11,903 - mmseg - INFO - Iter [4900/20000] lr: 2.446e-06, eta: 5:33:28, time: 1.212, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3061, decode.acc_seg: 88.3002, loss: 0.3061 2023-11-02 20:36:12,458 - mmseg - INFO - Iter [4950/20000] lr: 2.438e-06, eta: 5:32:05, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3273, decode.acc_seg: 87.8503, loss: 0.3273 2023-11-02 20:37:13,061 - mmseg - INFO - Saving checkpoint at 5000 iterations 2023-11-02 20:38:11,816 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 20:38:11,816 - mmseg - INFO - Iter [5000/20000] lr: 2.430e-06, eta: 5:33:38, time: 2.387, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3067, decode.acc_seg: 87.9757, loss: 0.3067 2023-11-02 20:39:13,887 - mmseg - INFO - per class results: 2023-11-02 20:39:13,892 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 78.1 | 86.85 | | building | 81.95 | 93.84 | | sky | 93.98 | 96.42 | | floor | 81.3 | 89.96 | | tree | 74.92 | 88.44 | | ceiling | 84.38 | 94.15 | | road | 82.87 | 90.53 | | bed | 89.98 | 96.45 | | windowpane | 64.49 | 83.83 | | grass | 73.83 | 88.0 | | cabinet | 62.97 | 75.13 | | sidewalk | 64.19 | 77.18 | | person | 81.38 | 90.94 | | earth | 35.87 | 53.74 | | door | 53.6 | 67.5 | | table | 63.64 | 75.72 | | mountain | 59.43 | 71.52 | | plant | 54.6 | 67.94 | | curtain | 74.76 | 87.25 | | chair | 58.2 | 70.2 | | car | 84.77 | 91.51 | | water | 53.05 | 64.22 | | painting | 72.67 | 87.28 | | sofa | 72.08 | 90.72 | | shelf | 45.32 | 60.05 | | house | 37.74 | 50.84 | | sea | 55.29 | 82.45 | | mirror | 72.17 | 84.47 | | rug | 63.37 | 73.3 | | field | 36.4 | 59.61 | | armchair | 44.85 | 55.33 | | seat | 59.36 | 89.58 | | fence | 41.74 | 61.19 | | desk | 50.91 | 75.53 | | rock | 43.47 | 50.97 | | wardrobe | 51.82 | 67.37 | | lamp | 64.07 | 79.56 | | bathtub | 84.69 | 87.89 | | railing | 38.03 | 54.34 | | cushion | 60.17 | 74.47 | | base | 31.85 | 49.17 | | box | 28.39 | 35.39 | | column | 49.92 | 67.3 | | signboard | 37.18 | 48.32 | | chest of drawers | 38.76 | 52.21 | | counter | 44.08 | 55.08 | | sand | 37.01 | 52.24 | | sink | 74.92 | 82.71 | | skyscraper | 40.4 | 43.31 | | fireplace | 68.53 | 87.94 | | refrigerator | 78.33 | 92.37 | | grandstand | 46.16 | 75.68 | | path | 13.34 | 21.73 | | stairs | 17.59 | 19.37 | | runway | 68.04 | 86.02 | | case | 58.33 | 73.12 | | pool table | 91.33 | 97.78 | | pillow | 50.2 | 55.48 | | screen door | 65.84 | 87.11 | | stairway | 36.7 | 66.87 | | river | 14.74 | 31.06 | | bridge | 72.94 | 84.75 | | bookcase | 36.47 | 51.24 | | blind | 38.43 | 41.18 | | coffee table | 64.88 | 83.22 | | toilet | 87.44 | 94.2 | | flower | 39.6 | 53.02 | | book | 49.71 | 67.39 | | hill | 8.0 | 12.13 | | bench | 51.55 | 58.49 | | countertop | 55.72 | 75.92 | | stove | 76.57 | 88.57 | | palm | 48.54 | 81.19 | | kitchen island | 49.92 | 79.12 | | computer | 73.54 | 89.88 | | swivel chair | 49.75 | 79.06 | | boat | 48.98 | 87.37 | | bar | 62.59 | 72.92 | | arcade machine | 73.26 | 74.88 | | hovel | 10.29 | 11.34 | | bus | 90.63 | 93.54 | | towel | 68.35 | 85.22 | | light | 48.48 | 59.06 | | truck | 31.92 | 43.64 | | tower | 15.38 | 26.35 | | chandelier | 63.73 | 76.43 | | awning | 31.0 | 36.7 | | streetlight | 22.43 | 29.46 | | booth | 33.56 | 34.83 | | television receiver | 70.35 | 83.39 | | airplane | 57.76 | 64.72 | | dirt track | 11.03 | 29.22 | | apparel | 48.17 | 64.29 | | pole | 19.43 | 24.06 | | land | 2.97 | 4.64 | | bannister | 13.8 | 19.19 | | escalator | 44.73 | 53.51 | | ottoman | 45.74 | 59.59 | | bottle | 21.18 | 24.6 | | buffet | 54.61 | 61.89 | | poster | 27.41 | 36.29 | | stage | 13.71 | 28.08 | | van | 47.22 | 67.78 | | ship | 6.42 | 7.39 | | fountain | 8.1 | 8.19 | | conveyer belt | 80.2 | 91.31 | | canopy | 41.85 | 46.62 | | washer | 85.86 | 91.35 | | plaything | 29.15 | 44.97 | | swimming pool | 58.27 | 75.17 | | stool | 45.57 | 54.45 | | barrel | 38.44 | 43.2 | | basket | 42.26 | 55.99 | | waterfall | 54.4 | 72.7 | | tent | 93.94 | 98.58 | | bag | 19.19 | 22.86 | | minibike | 72.55 | 83.95 | | cradle | 78.13 | 96.6 | | oven | 52.96 | 65.11 | | ball | 46.9 | 49.68 | | food | 62.89 | 71.61 | | step | 14.61 | 17.82 | | tank | 56.43 | 65.19 | | trade name | 21.38 | 25.09 | | microwave | 82.99 | 93.76 | | pot | 49.82 | 55.75 | | animal | 67.84 | 71.35 | | bicycle | 58.59 | 77.99 | | lake | 46.82 | 69.79 | | dishwasher | 72.57 | 75.9 | | screen | 55.3 | 89.76 | | blanket | 14.19 | 16.11 | | sculpture | 59.42 | 62.21 | | hood | 60.39 | 76.17 | | sconce | 49.36 | 63.22 | | vase | 37.44 | 57.17 | | traffic light | 29.95 | 46.01 | | tray | 8.42 | 12.82 | | ashcan | 49.59 | 59.7 | | fan | 52.98 | 60.72 | | pier | 36.62 | 44.96 | | crt screen | 0.4 | 0.52 | | plate | 54.64 | 67.57 | | monitor | 51.81 | 62.81 | | bulletin board | 43.49 | 52.11 | | shower | 0.0 | 0.0 | | radiator | 54.62 | 63.86 | | glass | 12.82 | 13.23 | | clock | 26.5 | 28.55 | | flag | 68.63 | 75.46 | +---------------------+-------+-------+ 2023-11-02 20:39:13,892 - mmseg - INFO - Summary: 2023-11-02 20:39:13,892 - mmseg - INFO - +-------+------+-------+ | aAcc | mIoU | mAcc | +-------+------+-------+ | 83.54 | 50.5 | 62.29 | +-------+------+-------+ 2023-11-02 20:39:13,893 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 20:39:13,893 - mmseg - INFO - Iter(val) [250] aAcc: 0.8354, mIoU: 0.5050, mAcc: 0.6229, IoU.wall: 0.7810, IoU.building: 0.8195, IoU.sky: 0.9398, IoU.floor: 0.8130, IoU.tree: 0.7492, IoU.ceiling: 0.8438, IoU.road: 0.8287, IoU.bed : 0.8998, IoU.windowpane: 0.6449, IoU.grass: 0.7383, IoU.cabinet: 0.6297, IoU.sidewalk: 0.6419, IoU.person: 0.8138, IoU.earth: 0.3587, IoU.door: 0.5360, IoU.table: 0.6364, IoU.mountain: 0.5943, IoU.plant: 0.5460, IoU.curtain: 0.7476, IoU.chair: 0.5820, IoU.car: 0.8477, IoU.water: 0.5305, IoU.painting: 0.7267, IoU.sofa: 0.7208, IoU.shelf: 0.4532, IoU.house: 0.3774, IoU.sea: 0.5529, IoU.mirror: 0.7217, IoU.rug: 0.6337, IoU.field: 0.3640, IoU.armchair: 0.4485, IoU.seat: 0.5936, IoU.fence: 0.4174, IoU.desk: 0.5091, IoU.rock: 0.4347, IoU.wardrobe: 0.5182, IoU.lamp: 0.6407, IoU.bathtub: 0.8469, IoU.railing: 0.3803, IoU.cushion: 0.6017, IoU.base: 0.3185, IoU.box: 0.2839, IoU.column: 0.4992, IoU.signboard: 0.3718, IoU.chest of drawers: 0.3876, IoU.counter: 0.4408, IoU.sand: 0.3701, IoU.sink: 0.7492, IoU.skyscraper: 0.4040, IoU.fireplace: 0.6853, IoU.refrigerator: 0.7833, IoU.grandstand: 0.4616, IoU.path: 0.1334, IoU.stairs: 0.1759, IoU.runway: 0.6804, IoU.case: 0.5833, IoU.pool table: 0.9133, IoU.pillow: 0.5020, IoU.screen door: 0.6584, IoU.stairway: 0.3670, IoU.river: 0.1474, IoU.bridge: 0.7294, IoU.bookcase: 0.3647, IoU.blind: 0.3843, IoU.coffee table: 0.6488, IoU.toilet: 0.8744, IoU.flower: 0.3960, IoU.book: 0.4971, IoU.hill: 0.0800, IoU.bench: 0.5155, IoU.countertop: 0.5572, IoU.stove: 0.7657, IoU.palm: 0.4854, IoU.kitchen island: 0.4992, IoU.computer: 0.7354, IoU.swivel chair: 0.4975, IoU.boat: 0.4898, IoU.bar: 0.6259, IoU.arcade machine: 0.7326, IoU.hovel: 0.1029, IoU.bus: 0.9063, IoU.towel: 0.6835, IoU.light: 0.4848, IoU.truck: 0.3192, IoU.tower: 0.1538, IoU.chandelier: 0.6373, IoU.awning: 0.3100, IoU.streetlight: 0.2243, IoU.booth: 0.3356, IoU.television receiver: 0.7035, IoU.airplane: 0.5776, IoU.dirt track: 0.1103, IoU.apparel: 0.4817, IoU.pole: 0.1943, IoU.land: 0.0297, IoU.bannister: 0.1380, IoU.escalator: 0.4473, IoU.ottoman: 0.4574, IoU.bottle: 0.2118, IoU.buffet: 0.5461, IoU.poster: 0.2741, IoU.stage: 0.1371, IoU.van: 0.4722, IoU.ship: 0.0642, IoU.fountain: 0.0810, IoU.conveyer belt: 0.8020, IoU.canopy: 0.4185, IoU.washer: 0.8586, IoU.plaything: 0.2915, IoU.swimming pool: 0.5827, IoU.stool: 0.4557, IoU.barrel: 0.3844, IoU.basket: 0.4226, IoU.waterfall: 0.5440, IoU.tent: 0.9394, IoU.bag: 0.1919, IoU.minibike: 0.7255, IoU.cradle: 0.7813, IoU.oven: 0.5296, IoU.ball: 0.4690, IoU.food: 0.6289, IoU.step: 0.1461, IoU.tank: 0.5643, IoU.trade name: 0.2138, IoU.microwave: 0.8299, IoU.pot: 0.4982, IoU.animal: 0.6784, IoU.bicycle: 0.5859, IoU.lake: 0.4682, IoU.dishwasher: 0.7257, IoU.screen: 0.5530, IoU.blanket: 0.1419, IoU.sculpture: 0.5942, IoU.hood: 0.6039, IoU.sconce: 0.4936, IoU.vase: 0.3744, IoU.traffic light: 0.2995, IoU.tray: 0.0842, IoU.ashcan: 0.4959, IoU.fan: 0.5298, IoU.pier: 0.3662, IoU.crt screen: 0.0040, IoU.plate: 0.5464, IoU.monitor: 0.5181, IoU.bulletin board: 0.4349, IoU.shower: 0.0000, IoU.radiator: 0.5462, IoU.glass: 0.1282, IoU.clock: 0.2650, IoU.flag: 0.6863, Acc.wall: 0.8685, Acc.building: 0.9384, Acc.sky: 0.9642, Acc.floor: 0.8996, Acc.tree: 0.8844, Acc.ceiling: 0.9415, Acc.road: 0.9053, Acc.bed : 0.9645, Acc.windowpane: 0.8383, Acc.grass: 0.8800, Acc.cabinet: 0.7513, Acc.sidewalk: 0.7718, Acc.person: 0.9094, Acc.earth: 0.5374, Acc.door: 0.6750, Acc.table: 0.7572, Acc.mountain: 0.7152, Acc.plant: 0.6794, Acc.curtain: 0.8725, Acc.chair: 0.7020, Acc.car: 0.9151, Acc.water: 0.6422, Acc.painting: 0.8728, Acc.sofa: 0.9072, Acc.shelf: 0.6005, Acc.house: 0.5084, Acc.sea: 0.8245, Acc.mirror: 0.8447, Acc.rug: 0.7330, Acc.field: 0.5961, Acc.armchair: 0.5533, Acc.seat: 0.8958, Acc.fence: 0.6119, Acc.desk: 0.7553, Acc.rock: 0.5097, Acc.wardrobe: 0.6737, Acc.lamp: 0.7956, Acc.bathtub: 0.8789, Acc.railing: 0.5434, Acc.cushion: 0.7447, Acc.base: 0.4917, Acc.box: 0.3539, Acc.column: 0.6730, Acc.signboard: 0.4832, Acc.chest of drawers: 0.5221, Acc.counter: 0.5508, Acc.sand: 0.5224, Acc.sink: 0.8271, Acc.skyscraper: 0.4331, Acc.fireplace: 0.8794, Acc.refrigerator: 0.9237, Acc.grandstand: 0.7568, Acc.path: 0.2173, Acc.stairs: 0.1937, Acc.runway: 0.8602, Acc.case: 0.7312, Acc.pool table: 0.9778, Acc.pillow: 0.5548, Acc.screen door: 0.8711, Acc.stairway: 0.6687, Acc.river: 0.3106, Acc.bridge: 0.8475, Acc.bookcase: 0.5124, Acc.blind: 0.4118, Acc.coffee table: 0.8322, Acc.toilet: 0.9420, Acc.flower: 0.5302, Acc.book: 0.6739, Acc.hill: 0.1213, Acc.bench: 0.5849, Acc.countertop: 0.7592, Acc.stove: 0.8857, Acc.palm: 0.8119, Acc.kitchen island: 0.7912, Acc.computer: 0.8988, Acc.swivel chair: 0.7906, Acc.boat: 0.8737, Acc.bar: 0.7292, Acc.arcade machine: 0.7488, Acc.hovel: 0.1134, Acc.bus: 0.9354, Acc.towel: 0.8522, Acc.light: 0.5906, Acc.truck: 0.4364, Acc.tower: 0.2635, Acc.chandelier: 0.7643, Acc.awning: 0.3670, Acc.streetlight: 0.2946, Acc.booth: 0.3483, Acc.television receiver: 0.8339, Acc.airplane: 0.6472, Acc.dirt track: 0.2922, Acc.apparel: 0.6429, Acc.pole: 0.2406, Acc.land: 0.0464, Acc.bannister: 0.1919, Acc.escalator: 0.5351, Acc.ottoman: 0.5959, Acc.bottle: 0.2460, Acc.buffet: 0.6189, Acc.poster: 0.3629, Acc.stage: 0.2808, Acc.van: 0.6778, Acc.ship: 0.0739, Acc.fountain: 0.0819, Acc.conveyer belt: 0.9131, Acc.canopy: 0.4662, Acc.washer: 0.9135, Acc.plaything: 0.4497, Acc.swimming pool: 0.7517, Acc.stool: 0.5445, Acc.barrel: 0.4320, Acc.basket: 0.5599, Acc.waterfall: 0.7270, Acc.tent: 0.9858, Acc.bag: 0.2286, Acc.minibike: 0.8395, Acc.cradle: 0.9660, Acc.oven: 0.6511, Acc.ball: 0.4968, Acc.food: 0.7161, Acc.step: 0.1782, Acc.tank: 0.6519, Acc.trade name: 0.2509, Acc.microwave: 0.9376, Acc.pot: 0.5575, Acc.animal: 0.7135, Acc.bicycle: 0.7799, Acc.lake: 0.6979, Acc.dishwasher: 0.7590, Acc.screen: 0.8976, Acc.blanket: 0.1611, Acc.sculpture: 0.6221, Acc.hood: 0.7617, Acc.sconce: 0.6322, Acc.vase: 0.5717, Acc.traffic light: 0.4601, Acc.tray: 0.1282, Acc.ashcan: 0.5970, Acc.fan: 0.6072, Acc.pier: 0.4496, Acc.crt screen: 0.0052, Acc.plate: 0.6757, Acc.monitor: 0.6281, Acc.bulletin board: 0.5211, Acc.shower: 0.0000, Acc.radiator: 0.6386, Acc.glass: 0.1323, Acc.clock: 0.2855, Acc.flag: 0.7546 2023-11-02 20:40:14,538 - mmseg - INFO - Iter [5050/20000] lr: 2.422e-06, eta: 5:35:17, time: 2.454, data_time: 1.249, memory: 38534, decode.loss_ce: 0.2902, decode.acc_seg: 88.9063, loss: 0.2902 2023-11-02 20:41:17,448 - mmseg - INFO - Iter [5100/20000] lr: 2.414e-06, eta: 5:33:57, time: 1.258, data_time: 0.052, memory: 38534, decode.loss_ce: 0.2906, decode.acc_seg: 88.8612, loss: 0.2906 2023-11-02 20:42:17,990 - mmseg - INFO - Iter [5150/20000] lr: 2.406e-06, eta: 5:32:30, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2976, decode.acc_seg: 88.8708, loss: 0.2976 2023-11-02 20:43:18,499 - mmseg - INFO - Iter [5200/20000] lr: 2.398e-06, eta: 5:31:04, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3081, decode.acc_seg: 88.5226, loss: 0.3081 2023-11-02 20:44:19,038 - mmseg - INFO - Iter [5250/20000] lr: 2.390e-06, eta: 5:29:39, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2949, decode.acc_seg: 88.3622, loss: 0.2949 2023-11-02 20:45:19,616 - mmseg - INFO - Iter [5300/20000] lr: 2.381e-06, eta: 5:28:14, time: 1.212, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2954, decode.acc_seg: 88.4292, loss: 0.2954 2023-11-02 20:46:20,195 - mmseg - INFO - Iter [5350/20000] lr: 2.373e-06, eta: 5:26:49, time: 1.212, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3004, decode.acc_seg: 88.5882, loss: 0.3004 2023-11-02 20:47:23,046 - mmseg - INFO - Iter [5400/20000] lr: 2.365e-06, eta: 5:25:31, time: 1.257, data_time: 0.052, memory: 38534, decode.loss_ce: 0.2792, decode.acc_seg: 89.1986, loss: 0.2792 2023-11-02 20:48:23,600 - mmseg - INFO - Iter [5450/20000] lr: 2.357e-06, eta: 5:24:07, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2844, decode.acc_seg: 89.2485, loss: 0.2844 2023-11-02 20:49:24,122 - mmseg - INFO - Iter [5500/20000] lr: 2.349e-06, eta: 5:22:44, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2854, decode.acc_seg: 88.8143, loss: 0.2854 2023-11-02 20:50:24,718 - mmseg - INFO - Iter [5550/20000] lr: 2.341e-06, eta: 5:21:21, time: 1.212, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2853, decode.acc_seg: 89.0075, loss: 0.2853 2023-11-02 20:51:25,267 - mmseg - INFO - Iter [5600/20000] lr: 2.333e-06, eta: 5:19:59, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2858, decode.acc_seg: 88.8645, loss: 0.2858 2023-11-02 20:52:25,828 - mmseg - INFO - Iter [5650/20000] lr: 2.325e-06, eta: 5:18:36, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2920, decode.acc_seg: 88.9922, loss: 0.2920 2023-11-02 20:53:28,768 - mmseg - INFO - Iter [5700/20000] lr: 2.317e-06, eta: 5:17:21, time: 1.259, data_time: 0.050, memory: 38534, decode.loss_ce: 0.2734, decode.acc_seg: 89.2650, loss: 0.2734 2023-11-02 20:54:29,345 - mmseg - INFO - Iter [5750/20000] lr: 2.309e-06, eta: 5:15:59, time: 1.212, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2682, decode.acc_seg: 89.6925, loss: 0.2682 2023-11-02 20:55:29,941 - mmseg - INFO - Iter [5800/20000] lr: 2.300e-06, eta: 5:14:38, time: 1.212, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2758, decode.acc_seg: 89.4205, loss: 0.2758 2023-11-02 20:56:30,536 - mmseg - INFO - Iter [5850/20000] lr: 2.292e-06, eta: 5:13:17, time: 1.212, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2745, decode.acc_seg: 89.5483, loss: 0.2745 2023-11-02 20:57:31,092 - mmseg - INFO - Iter [5900/20000] lr: 2.284e-06, eta: 5:11:57, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2700, decode.acc_seg: 89.4252, loss: 0.2700 2023-11-02 20:58:31,725 - mmseg - INFO - Iter [5950/20000] lr: 2.276e-06, eta: 5:10:37, time: 1.213, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2875, decode.acc_seg: 88.6796, loss: 0.2875 2023-11-02 20:59:32,296 - mmseg - INFO - Saving checkpoint at 6000 iterations 2023-11-02 21:00:32,404 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 21:00:32,404 - mmseg - INFO - Iter [6000/20000] lr: 2.268e-06, eta: 5:11:38, time: 2.414, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2617, decode.acc_seg: 89.6331, loss: 0.2617 2023-11-02 21:01:29,328 - mmseg - INFO - per class results: 2023-11-02 21:01:29,333 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 79.09 | 88.29 | | building | 82.95 | 93.19 | | sky | 93.86 | 96.33 | | floor | 82.02 | 91.04 | | tree | 74.51 | 88.67 | | ceiling | 85.05 | 91.93 | | road | 83.15 | 91.63 | | bed | 90.63 | 95.24 | | windowpane | 63.99 | 78.86 | | grass | 70.98 | 81.76 | | cabinet | 62.08 | 70.85 | | sidewalk | 64.21 | 78.03 | | person | 81.49 | 90.57 | | earth | 36.22 | 50.5 | | door | 54.52 | 75.94 | | table | 64.45 | 78.98 | | mountain | 62.27 | 80.43 | | plant | 54.94 | 65.53 | | curtain | 76.28 | 88.48 | | chair | 57.8 | 69.24 | | car | 84.54 | 92.47 | | water | 53.59 | 69.89 | | painting | 72.06 | 86.04 | | sofa | 75.3 | 84.23 | | shelf | 44.8 | 69.99 | | house | 40.06 | 52.6 | | sea | 51.17 | 73.78 | | mirror | 73.09 | 84.63 | | rug | 66.97 | 70.55 | | field | 34.15 | 61.41 | | armchair | 53.24 | 78.06 | | seat | 62.84 | 89.19 | | fence | 47.01 | 64.32 | | desk | 50.46 | 78.95 | | rock | 46.75 | 58.02 | | wardrobe | 51.49 | 71.52 | | lamp | 64.31 | 76.19 | | bathtub | 84.28 | 89.48 | | railing | 41.29 | 55.54 | | cushion | 61.0 | 72.88 | | base | 34.76 | 49.94 | | box | 28.7 | 37.77 | | column | 48.93 | 62.95 | | signboard | 36.82 | 53.26 | | chest of drawers | 45.75 | 72.69 | | counter | 48.32 | 60.46 | | sand | 38.03 | 52.03 | | sink | 74.47 | 79.97 | | skyscraper | 46.02 | 60.6 | | fireplace | 69.58 | 83.48 | | refrigerator | 80.51 | 92.04 | | grandstand | 49.36 | 74.65 | | path | 21.29 | 35.76 | | stairs | 24.67 | 27.91 | | runway | 65.0 | 82.98 | | case | 58.7 | 73.11 | | pool table | 92.49 | 97.92 | | pillow | 61.63 | 76.24 | | screen door | 70.13 | 72.0 | | stairway | 42.32 | 63.04 | | river | 25.28 | 46.55 | | bridge | 73.39 | 88.2 | | bookcase | 37.99 | 53.47 | | blind | 39.08 | 42.63 | | coffee table | 65.51 | 82.26 | | toilet | 87.16 | 91.8 | | flower | 39.79 | 54.5 | | book | 47.89 | 66.78 | | hill | 8.22 | 12.43 | | bench | 50.84 | 59.53 | | countertop | 57.98 | 73.09 | | stove | 78.9 | 90.35 | | palm | 47.03 | 80.36 | | kitchen island | 52.77 | 69.97 | | computer | 72.02 | 91.93 | | swivel chair | 42.05 | 53.39 | | boat | 46.22 | 83.6 | | bar | 55.61 | 58.59 | | arcade machine | 81.23 | 86.36 | | hovel | 16.56 | 19.3 | | bus | 90.47 | 94.59 | | towel | 70.34 | 83.05 | | light | 47.51 | 57.28 | | truck | 41.26 | 54.81 | | tower | 12.29 | 20.37 | | chandelier | 64.23 | 82.06 | | awning | 30.56 | 36.4 | | streetlight | 23.7 | 31.84 | | booth | 31.16 | 36.73 | | television receiver | 71.21 | 82.31 | | airplane | 57.74 | 64.92 | | dirt track | 29.97 | 41.63 | | apparel | 54.45 | 79.24 | | pole | 21.24 | 25.91 | | land | 3.56 | 6.09 | | bannister | 16.55 | 24.06 | | escalator | 53.68 | 70.25 | | ottoman | 50.2 | 70.25 | | bottle | 23.12 | 29.63 | | buffet | 51.13 | 71.99 | | poster | 26.76 | 44.09 | | stage | 14.77 | 29.16 | | van | 44.09 | 58.01 | | ship | 2.49 | 2.54 | | fountain | 9.82 | 9.89 | | conveyer belt | 69.18 | 97.84 | | canopy | 55.23 | 64.5 | | washer | 83.02 | 89.2 | | plaything | 29.83 | 42.17 | | swimming pool | 64.55 | 84.48 | | stool | 42.12 | 48.53 | | barrel | 45.97 | 54.53 | | basket | 40.56 | 58.58 | | waterfall | 72.04 | 85.18 | | tent | 93.37 | 98.26 | | bag | 21.59 | 25.45 | | minibike | 70.95 | 84.33 | | cradle | 70.57 | 98.45 | | oven | 61.42 | 73.64 | | ball | 41.35 | 43.6 | | food | 62.19 | 69.61 | | step | 19.5 | 26.65 | | tank | 52.37 | 64.74 | | trade name | 27.22 | 32.92 | | microwave | 85.54 | 92.06 | | pot | 45.13 | 49.04 | | animal | 68.64 | 70.92 | | bicycle | 59.04 | 72.88 | | lake | 58.83 | 61.27 | | dishwasher | 72.01 | 75.06 | | screen | 47.83 | 68.99 | | blanket | 16.39 | 18.55 | | sculpture | 62.21 | 66.72 | | hood | 55.24 | 67.0 | | sconce | 48.6 | 58.35 | | vase | 38.71 | 50.07 | | traffic light | 32.12 | 46.63 | | tray | 7.69 | 13.15 | | ashcan | 51.15 | 60.27 | | fan | 55.69 | 64.14 | | pier | 39.08 | 44.48 | | crt screen | 3.92 | 10.18 | | plate | 53.64 | 73.78 | | monitor | 30.48 | 32.32 | | bulletin board | 57.56 | 73.94 | | shower | 0.36 | 0.81 | | radiator | 57.76 | 65.73 | | glass | 16.16 | 17.28 | | clock | 27.02 | 29.52 | | flag | 69.02 | 77.97 | +---------------------+-------+-------+ 2023-11-02 21:01:29,333 - mmseg - INFO - Summary: 2023-11-02 21:01:29,333 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 83.91 | 51.78 | 63.67 | +-------+-------+-------+ 2023-11-02 21:01:29,334 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 21:01:29,335 - mmseg - INFO - Iter(val) [250] aAcc: 0.8391, mIoU: 0.5178, mAcc: 0.6367, IoU.wall: 0.7909, IoU.building: 0.8295, IoU.sky: 0.9386, IoU.floor: 0.8202, IoU.tree: 0.7451, IoU.ceiling: 0.8505, IoU.road: 0.8315, IoU.bed : 0.9063, IoU.windowpane: 0.6399, IoU.grass: 0.7098, IoU.cabinet: 0.6208, IoU.sidewalk: 0.6421, IoU.person: 0.8149, IoU.earth: 0.3622, IoU.door: 0.5452, IoU.table: 0.6445, IoU.mountain: 0.6227, IoU.plant: 0.5494, IoU.curtain: 0.7628, IoU.chair: 0.5780, IoU.car: 0.8454, IoU.water: 0.5359, IoU.painting: 0.7206, IoU.sofa: 0.7530, IoU.shelf: 0.4480, IoU.house: 0.4006, IoU.sea: 0.5117, IoU.mirror: 0.7309, IoU.rug: 0.6697, IoU.field: 0.3415, IoU.armchair: 0.5324, IoU.seat: 0.6284, IoU.fence: 0.4701, IoU.desk: 0.5046, IoU.rock: 0.4675, IoU.wardrobe: 0.5149, IoU.lamp: 0.6431, IoU.bathtub: 0.8428, IoU.railing: 0.4129, IoU.cushion: 0.6100, IoU.base: 0.3476, IoU.box: 0.2870, IoU.column: 0.4893, IoU.signboard: 0.3682, IoU.chest of drawers: 0.4575, IoU.counter: 0.4832, IoU.sand: 0.3803, IoU.sink: 0.7447, IoU.skyscraper: 0.4602, IoU.fireplace: 0.6958, IoU.refrigerator: 0.8051, IoU.grandstand: 0.4936, IoU.path: 0.2129, IoU.stairs: 0.2467, IoU.runway: 0.6500, IoU.case: 0.5870, IoU.pool table: 0.9249, IoU.pillow: 0.6163, IoU.screen door: 0.7013, IoU.stairway: 0.4232, IoU.river: 0.2528, IoU.bridge: 0.7339, IoU.bookcase: 0.3799, IoU.blind: 0.3908, IoU.coffee table: 0.6551, IoU.toilet: 0.8716, IoU.flower: 0.3979, IoU.book: 0.4789, IoU.hill: 0.0822, IoU.bench: 0.5084, IoU.countertop: 0.5798, IoU.stove: 0.7890, IoU.palm: 0.4703, IoU.kitchen island: 0.5277, IoU.computer: 0.7202, IoU.swivel chair: 0.4205, IoU.boat: 0.4622, IoU.bar: 0.5561, IoU.arcade machine: 0.8123, IoU.hovel: 0.1656, IoU.bus: 0.9047, IoU.towel: 0.7034, IoU.light: 0.4751, IoU.truck: 0.4126, IoU.tower: 0.1229, IoU.chandelier: 0.6423, IoU.awning: 0.3056, IoU.streetlight: 0.2370, IoU.booth: 0.3116, IoU.television receiver: 0.7121, IoU.airplane: 0.5774, IoU.dirt track: 0.2997, IoU.apparel: 0.5445, IoU.pole: 0.2124, IoU.land: 0.0356, IoU.bannister: 0.1655, IoU.escalator: 0.5368, IoU.ottoman: 0.5020, IoU.bottle: 0.2312, IoU.buffet: 0.5113, IoU.poster: 0.2676, IoU.stage: 0.1477, IoU.van: 0.4409, IoU.ship: 0.0249, IoU.fountain: 0.0982, IoU.conveyer belt: 0.6918, IoU.canopy: 0.5523, IoU.washer: 0.8302, IoU.plaything: 0.2983, IoU.swimming pool: 0.6455, IoU.stool: 0.4212, IoU.barrel: 0.4597, IoU.basket: 0.4056, IoU.waterfall: 0.7204, IoU.tent: 0.9337, IoU.bag: 0.2159, IoU.minibike: 0.7095, IoU.cradle: 0.7057, IoU.oven: 0.6142, IoU.ball: 0.4135, IoU.food: 0.6219, IoU.step: 0.1950, IoU.tank: 0.5237, IoU.trade name: 0.2722, IoU.microwave: 0.8554, IoU.pot: 0.4513, IoU.animal: 0.6864, IoU.bicycle: 0.5904, IoU.lake: 0.5883, IoU.dishwasher: 0.7201, IoU.screen: 0.4783, IoU.blanket: 0.1639, IoU.sculpture: 0.6221, IoU.hood: 0.5524, IoU.sconce: 0.4860, IoU.vase: 0.3871, IoU.traffic light: 0.3212, IoU.tray: 0.0769, IoU.ashcan: 0.5115, IoU.fan: 0.5569, IoU.pier: 0.3908, IoU.crt screen: 0.0392, IoU.plate: 0.5364, IoU.monitor: 0.3048, IoU.bulletin board: 0.5756, IoU.shower: 0.0036, IoU.radiator: 0.5776, IoU.glass: 0.1616, IoU.clock: 0.2702, IoU.flag: 0.6902, Acc.wall: 0.8829, Acc.building: 0.9319, Acc.sky: 0.9633, Acc.floor: 0.9104, Acc.tree: 0.8867, Acc.ceiling: 0.9193, Acc.road: 0.9163, Acc.bed : 0.9524, Acc.windowpane: 0.7886, Acc.grass: 0.8176, Acc.cabinet: 0.7085, Acc.sidewalk: 0.7803, Acc.person: 0.9057, Acc.earth: 0.5050, Acc.door: 0.7594, Acc.table: 0.7898, Acc.mountain: 0.8043, Acc.plant: 0.6553, Acc.curtain: 0.8848, Acc.chair: 0.6924, Acc.car: 0.9247, Acc.water: 0.6989, Acc.painting: 0.8604, Acc.sofa: 0.8423, Acc.shelf: 0.6999, Acc.house: 0.5260, Acc.sea: 0.7378, Acc.mirror: 0.8463, Acc.rug: 0.7055, Acc.field: 0.6141, Acc.armchair: 0.7806, Acc.seat: 0.8919, Acc.fence: 0.6432, Acc.desk: 0.7895, Acc.rock: 0.5802, Acc.wardrobe: 0.7152, Acc.lamp: 0.7619, Acc.bathtub: 0.8948, Acc.railing: 0.5554, Acc.cushion: 0.7288, Acc.base: 0.4994, Acc.box: 0.3777, Acc.column: 0.6295, Acc.signboard: 0.5326, Acc.chest of drawers: 0.7269, Acc.counter: 0.6046, Acc.sand: 0.5203, Acc.sink: 0.7997, Acc.skyscraper: 0.6060, Acc.fireplace: 0.8348, Acc.refrigerator: 0.9204, Acc.grandstand: 0.7465, Acc.path: 0.3576, Acc.stairs: 0.2791, Acc.runway: 0.8298, Acc.case: 0.7311, Acc.pool table: 0.9792, Acc.pillow: 0.7624, Acc.screen door: 0.7200, Acc.stairway: 0.6304, Acc.river: 0.4655, Acc.bridge: 0.8820, Acc.bookcase: 0.5347, Acc.blind: 0.4263, Acc.coffee table: 0.8226, Acc.toilet: 0.9180, Acc.flower: 0.5450, Acc.book: 0.6678, Acc.hill: 0.1243, Acc.bench: 0.5953, Acc.countertop: 0.7309, Acc.stove: 0.9035, Acc.palm: 0.8036, Acc.kitchen island: 0.6997, Acc.computer: 0.9193, Acc.swivel chair: 0.5339, Acc.boat: 0.8360, Acc.bar: 0.5859, Acc.arcade machine: 0.8636, Acc.hovel: 0.1930, Acc.bus: 0.9459, Acc.towel: 0.8305, Acc.light: 0.5728, Acc.truck: 0.5481, Acc.tower: 0.2037, Acc.chandelier: 0.8206, Acc.awning: 0.3640, Acc.streetlight: 0.3184, Acc.booth: 0.3673, Acc.television receiver: 0.8231, Acc.airplane: 0.6492, Acc.dirt track: 0.4163, Acc.apparel: 0.7924, Acc.pole: 0.2591, Acc.land: 0.0609, Acc.bannister: 0.2406, Acc.escalator: 0.7025, Acc.ottoman: 0.7025, Acc.bottle: 0.2963, Acc.buffet: 0.7199, Acc.poster: 0.4409, Acc.stage: 0.2916, Acc.van: 0.5801, Acc.ship: 0.0254, Acc.fountain: 0.0989, Acc.conveyer belt: 0.9784, Acc.canopy: 0.6450, Acc.washer: 0.8920, Acc.plaything: 0.4217, Acc.swimming pool: 0.8448, Acc.stool: 0.4853, Acc.barrel: 0.5453, Acc.basket: 0.5858, Acc.waterfall: 0.8518, Acc.tent: 0.9826, Acc.bag: 0.2545, Acc.minibike: 0.8433, Acc.cradle: 0.9845, Acc.oven: 0.7364, Acc.ball: 0.4360, Acc.food: 0.6961, Acc.step: 0.2665, Acc.tank: 0.6474, Acc.trade name: 0.3292, Acc.microwave: 0.9206, Acc.pot: 0.4904, Acc.animal: 0.7092, Acc.bicycle: 0.7288, Acc.lake: 0.6127, Acc.dishwasher: 0.7506, Acc.screen: 0.6899, Acc.blanket: 0.1855, Acc.sculpture: 0.6672, Acc.hood: 0.6700, Acc.sconce: 0.5835, Acc.vase: 0.5007, Acc.traffic light: 0.4663, Acc.tray: 0.1315, Acc.ashcan: 0.6027, Acc.fan: 0.6414, Acc.pier: 0.4448, Acc.crt screen: 0.1018, Acc.plate: 0.7378, Acc.monitor: 0.3232, Acc.bulletin board: 0.7394, Acc.shower: 0.0081, Acc.radiator: 0.6573, Acc.glass: 0.1728, Acc.clock: 0.2952, Acc.flag: 0.7797 2023-11-02 21:02:32,273 - mmseg - INFO - Iter [6050/20000] lr: 2.260e-06, eta: 5:12:33, time: 2.397, data_time: 1.191, memory: 38534, decode.loss_ce: 0.2544, decode.acc_seg: 89.9362, loss: 0.2544 2023-11-02 21:03:32,838 - mmseg - INFO - Iter [6100/20000] lr: 2.252e-06, eta: 5:11:11, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2528, decode.acc_seg: 90.1842, loss: 0.2528 2023-11-02 21:04:33,363 - mmseg - INFO - Iter [6150/20000] lr: 2.244e-06, eta: 5:09:49, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2789, decode.acc_seg: 89.1438, loss: 0.2789 2023-11-02 21:05:33,929 - mmseg - INFO - Iter [6200/20000] lr: 2.236e-06, eta: 5:08:27, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2731, decode.acc_seg: 89.4132, loss: 0.2731 2023-11-02 21:06:34,499 - mmseg - INFO - Iter [6250/20000] lr: 2.228e-06, eta: 5:07:06, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2508, decode.acc_seg: 90.0415, loss: 0.2508 2023-11-02 21:07:35,050 - mmseg - INFO - Iter [6300/20000] lr: 2.219e-06, eta: 5:05:45, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2748, decode.acc_seg: 89.5053, loss: 0.2748 2023-11-02 21:08:37,877 - mmseg - INFO - Iter [6350/20000] lr: 2.211e-06, eta: 5:04:29, time: 1.257, data_time: 0.051, memory: 38534, decode.loss_ce: 0.2577, decode.acc_seg: 89.8391, loss: 0.2577 2023-11-02 21:09:38,483 - mmseg - INFO - Iter [6400/20000] lr: 2.203e-06, eta: 5:03:08, time: 1.212, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2525, decode.acc_seg: 90.0119, loss: 0.2525 2023-11-02 21:10:39,058 - mmseg - INFO - Iter [6450/20000] lr: 2.195e-06, eta: 5:01:48, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2752, decode.acc_seg: 89.3387, loss: 0.2752 2023-11-02 21:11:39,615 - mmseg - INFO - Iter [6500/20000] lr: 2.187e-06, eta: 5:00:29, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2498, decode.acc_seg: 90.3267, loss: 0.2498 2023-11-02 21:12:40,162 - mmseg - INFO - Iter [6550/20000] lr: 2.179e-06, eta: 4:59:09, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2576, decode.acc_seg: 89.6314, loss: 0.2576 2023-11-02 21:13:40,701 - mmseg - INFO - Iter [6600/20000] lr: 2.171e-06, eta: 4:57:50, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2461, decode.acc_seg: 90.1588, loss: 0.2461 2023-11-02 21:14:43,665 - mmseg - INFO - Iter [6650/20000] lr: 2.163e-06, eta: 4:56:36, time: 1.259, data_time: 0.054, memory: 38534, decode.loss_ce: 0.2628, decode.acc_seg: 89.6897, loss: 0.2628 2023-11-02 21:15:44,229 - mmseg - INFO - Iter [6700/20000] lr: 2.155e-06, eta: 4:55:17, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2423, decode.acc_seg: 90.4554, loss: 0.2423 2023-11-02 21:16:44,765 - mmseg - INFO - Iter [6750/20000] lr: 2.147e-06, eta: 4:53:58, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2506, decode.acc_seg: 90.1885, loss: 0.2506 2023-11-02 21:17:45,310 - mmseg - INFO - Iter [6800/20000] lr: 2.138e-06, eta: 4:52:40, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2608, decode.acc_seg: 89.8524, loss: 0.2608 2023-11-02 21:18:45,863 - mmseg - INFO - Iter [6850/20000] lr: 2.130e-06, eta: 4:51:22, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2578, decode.acc_seg: 89.7580, loss: 0.2578 2023-11-02 21:19:46,425 - mmseg - INFO - Iter [6900/20000] lr: 2.122e-06, eta: 4:50:04, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2763, decode.acc_seg: 89.3839, loss: 0.2763 2023-11-02 21:20:46,985 - mmseg - INFO - Iter [6950/20000] lr: 2.114e-06, eta: 4:48:47, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2769, decode.acc_seg: 89.0564, loss: 0.2769 2023-11-02 21:21:49,867 - mmseg - INFO - Saving checkpoint at 7000 iterations 2023-11-02 21:22:47,760 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 21:22:47,761 - mmseg - INFO - Iter [7000/20000] lr: 2.106e-06, eta: 4:49:22, time: 2.415, data_time: 0.054, memory: 38534, decode.loss_ce: 0.2390, decode.acc_seg: 90.6156, loss: 0.2390 2023-11-02 21:23:45,666 - mmseg - INFO - per class results: 2023-11-02 21:23:45,672 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 79.43 | 88.56 | | building | 82.84 | 92.0 | | sky | 94.14 | 97.0 | | floor | 81.35 | 90.81 | | tree | 74.66 | 90.32 | | ceiling | 84.92 | 92.07 | | road | 84.34 | 90.48 | | bed | 91.19 | 96.02 | | windowpane | 64.55 | 80.05 | | grass | 73.67 | 89.09 | | cabinet | 61.82 | 73.0 | | sidewalk | 66.42 | 83.61 | | person | 81.56 | 89.77 | | earth | 35.33 | 48.13 | | door | 57.22 | 74.61 | | table | 65.51 | 76.61 | | mountain | 61.11 | 76.7 | | plant | 51.89 | 64.68 | | curtain | 75.67 | 85.84 | | chair | 58.91 | 73.99 | | car | 84.59 | 90.74 | | water | 52.77 | 66.1 | | painting | 72.43 | 87.94 | | sofa | 76.53 | 83.4 | | shelf | 44.12 | 62.55 | | house | 45.05 | 65.78 | | sea | 58.16 | 90.11 | | mirror | 74.17 | 88.18 | | rug | 66.54 | 80.79 | | field | 37.54 | 53.02 | | armchair | 56.23 | 74.86 | | seat | 65.94 | 86.31 | | fence | 45.44 | 64.47 | | desk | 52.57 | 76.51 | | rock | 46.48 | 60.92 | | wardrobe | 51.52 | 73.78 | | lamp | 65.32 | 78.95 | | bathtub | 87.9 | 92.88 | | railing | 38.7 | 52.3 | | cushion | 61.66 | 77.85 | | base | 29.9 | 37.32 | | box | 30.81 | 41.07 | | column | 49.25 | 59.82 | | signboard | 35.84 | 48.2 | | chest of drawers | 38.24 | 59.2 | | counter | 45.58 | 65.91 | | sand | 36.86 | 51.24 | | sink | 75.66 | 82.08 | | skyscraper | 47.21 | 64.87 | | fireplace | 69.54 | 90.14 | | refrigerator | 80.21 | 93.44 | | grandstand | 50.52 | 76.25 | | path | 19.11 | 26.11 | | stairs | 28.93 | 33.53 | | runway | 69.88 | 89.0 | | case | 56.16 | 73.48 | | pool table | 92.82 | 97.43 | | pillow | 61.14 | 71.98 | | screen door | 78.09 | 82.33 | | stairway | 45.36 | 60.57 | | river | 18.54 | 25.1 | | bridge | 75.93 | 89.85 | | bookcase | 36.09 | 57.63 | | blind | 36.92 | 38.45 | | coffee table | 63.93 | 83.68 | | toilet | 88.24 | 92.12 | | flower | 38.31 | 50.34 | | book | 47.63 | 66.08 | | hill | 7.69 | 11.64 | | bench | 55.21 | 61.62 | | countertop | 56.95 | 75.85 | | stove | 79.45 | 87.19 | | palm | 48.44 | 77.57 | | kitchen island | 54.25 | 64.6 | | computer | 76.1 | 89.67 | | swivel chair | 45.25 | 74.55 | | boat | 52.26 | 91.66 | | bar | 50.41 | 53.71 | | arcade machine | 77.45 | 79.88 | | hovel | 13.8 | 14.68 | | bus | 90.06 | 95.15 | | towel | 69.51 | 82.07 | | light | 48.64 | 59.52 | | truck | 40.48 | 51.75 | | tower | 12.56 | 22.42 | | chandelier | 64.28 | 81.39 | | awning | 34.48 | 46.19 | | streetlight | 24.19 | 31.39 | | booth | 32.78 | 34.07 | | television receiver | 69.85 | 90.76 | | airplane | 58.94 | 65.95 | | dirt track | 5.65 | 8.32 | | apparel | 58.22 | 70.76 | | pole | 21.35 | 25.71 | | land | 4.34 | 5.72 | | bannister | 17.22 | 20.8 | | escalator | 51.83 | 64.74 | | ottoman | 46.76 | 69.15 | | bottle | 23.47 | 32.82 | | buffet | 56.3 | 60.38 | | poster | 27.79 | 43.76 | | stage | 14.71 | 27.35 | | van | 45.56 | 69.5 | | ship | 0.03 | 0.03 | | fountain | 22.78 | 23.2 | | conveyer belt | 78.64 | 93.73 | | canopy | 55.09 | 66.88 | | washer | 80.81 | 86.15 | | plaything | 27.97 | 44.51 | | swimming pool | 55.55 | 83.48 | | stool | 47.29 | 62.65 | | barrel | 52.9 | 58.69 | | basket | 42.35 | 57.6 | | waterfall | 54.62 | 70.56 | | tent | 90.97 | 98.52 | | bag | 18.73 | 22.07 | | minibike | 70.32 | 80.93 | | cradle | 77.48 | 85.05 | | oven | 65.62 | 76.03 | | ball | 39.22 | 40.62 | | food | 59.48 | 63.83 | | step | 18.93 | 23.1 | | tank | 51.45 | 65.02 | | trade name | 30.13 | 37.86 | | microwave | 86.49 | 92.6 | | pot | 51.78 | 57.72 | | animal | 67.12 | 69.43 | | bicycle | 59.78 | 75.59 | | lake | 52.32 | 68.93 | | dishwasher | 75.45 | 80.58 | | screen | 29.22 | 34.84 | | blanket | 14.87 | 16.47 | | sculpture | 59.9 | 66.13 | | hood | 55.64 | 64.62 | | sconce | 51.64 | 68.36 | | vase | 39.85 | 58.64 | | traffic light | 30.78 | 52.69 | | tray | 8.78 | 12.62 | | ashcan | 50.67 | 58.92 | | fan | 60.02 | 76.75 | | pier | 38.81 | 43.87 | | crt screen | 11.05 | 38.7 | | plate | 55.12 | 78.35 | | monitor | 10.3 | 11.25 | | bulletin board | 61.68 | 72.96 | | shower | 0.13 | 0.13 | | radiator | 58.22 | 66.32 | | glass | 19.99 | 24.12 | | clock | 29.53 | 32.44 | | flag | 67.65 | 75.89 | +---------------------+-------+-------+ 2023-11-02 21:23:45,672 - mmseg - INFO - Summary: 2023-11-02 21:23:45,672 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 84.18 | 51.87 | 63.66 | +-------+-------+-------+ 2023-11-02 21:23:45,672 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 21:23:45,673 - mmseg - INFO - Iter(val) [250] aAcc: 0.8418, mIoU: 0.5187, mAcc: 0.6366, IoU.wall: 0.7943, IoU.building: 0.8284, IoU.sky: 0.9414, IoU.floor: 0.8135, IoU.tree: 0.7466, IoU.ceiling: 0.8492, IoU.road: 0.8434, IoU.bed : 0.9119, IoU.windowpane: 0.6455, IoU.grass: 0.7367, IoU.cabinet: 0.6182, IoU.sidewalk: 0.6642, IoU.person: 0.8156, IoU.earth: 0.3533, IoU.door: 0.5722, IoU.table: 0.6551, IoU.mountain: 0.6111, IoU.plant: 0.5189, IoU.curtain: 0.7567, IoU.chair: 0.5891, IoU.car: 0.8459, IoU.water: 0.5277, IoU.painting: 0.7243, IoU.sofa: 0.7653, IoU.shelf: 0.4412, IoU.house: 0.4505, IoU.sea: 0.5816, IoU.mirror: 0.7417, IoU.rug: 0.6654, IoU.field: 0.3754, IoU.armchair: 0.5623, IoU.seat: 0.6594, IoU.fence: 0.4544, IoU.desk: 0.5257, IoU.rock: 0.4648, IoU.wardrobe: 0.5152, IoU.lamp: 0.6532, IoU.bathtub: 0.8790, IoU.railing: 0.3870, IoU.cushion: 0.6166, IoU.base: 0.2990, IoU.box: 0.3081, IoU.column: 0.4925, IoU.signboard: 0.3584, IoU.chest of drawers: 0.3824, IoU.counter: 0.4558, IoU.sand: 0.3686, IoU.sink: 0.7566, IoU.skyscraper: 0.4721, IoU.fireplace: 0.6954, IoU.refrigerator: 0.8021, IoU.grandstand: 0.5052, IoU.path: 0.1911, IoU.stairs: 0.2893, IoU.runway: 0.6988, IoU.case: 0.5616, IoU.pool table: 0.9282, IoU.pillow: 0.6114, IoU.screen door: 0.7809, IoU.stairway: 0.4536, IoU.river: 0.1854, IoU.bridge: 0.7593, IoU.bookcase: 0.3609, IoU.blind: 0.3692, IoU.coffee table: 0.6393, IoU.toilet: 0.8824, IoU.flower: 0.3831, IoU.book: 0.4763, IoU.hill: 0.0769, IoU.bench: 0.5521, IoU.countertop: 0.5695, IoU.stove: 0.7945, IoU.palm: 0.4844, IoU.kitchen island: 0.5425, IoU.computer: 0.7610, IoU.swivel chair: 0.4525, IoU.boat: 0.5226, IoU.bar: 0.5041, IoU.arcade machine: 0.7745, IoU.hovel: 0.1380, IoU.bus: 0.9006, IoU.towel: 0.6951, IoU.light: 0.4864, IoU.truck: 0.4048, IoU.tower: 0.1256, IoU.chandelier: 0.6428, IoU.awning: 0.3448, IoU.streetlight: 0.2419, IoU.booth: 0.3278, IoU.television receiver: 0.6985, IoU.airplane: 0.5894, IoU.dirt track: 0.0565, IoU.apparel: 0.5822, IoU.pole: 0.2135, IoU.land: 0.0434, IoU.bannister: 0.1722, IoU.escalator: 0.5183, IoU.ottoman: 0.4676, IoU.bottle: 0.2347, IoU.buffet: 0.5630, IoU.poster: 0.2779, IoU.stage: 0.1471, IoU.van: 0.4556, IoU.ship: 0.0003, IoU.fountain: 0.2278, IoU.conveyer belt: 0.7864, IoU.canopy: 0.5509, IoU.washer: 0.8081, IoU.plaything: 0.2797, IoU.swimming pool: 0.5555, IoU.stool: 0.4729, IoU.barrel: 0.5290, IoU.basket: 0.4235, IoU.waterfall: 0.5462, IoU.tent: 0.9097, IoU.bag: 0.1873, IoU.minibike: 0.7032, IoU.cradle: 0.7748, IoU.oven: 0.6562, IoU.ball: 0.3922, IoU.food: 0.5948, IoU.step: 0.1893, IoU.tank: 0.5145, IoU.trade name: 0.3013, IoU.microwave: 0.8649, IoU.pot: 0.5178, IoU.animal: 0.6712, IoU.bicycle: 0.5978, IoU.lake: 0.5232, IoU.dishwasher: 0.7545, IoU.screen: 0.2922, IoU.blanket: 0.1487, IoU.sculpture: 0.5990, IoU.hood: 0.5564, IoU.sconce: 0.5164, IoU.vase: 0.3985, IoU.traffic light: 0.3078, IoU.tray: 0.0878, IoU.ashcan: 0.5067, IoU.fan: 0.6002, IoU.pier: 0.3881, IoU.crt screen: 0.1105, IoU.plate: 0.5512, IoU.monitor: 0.1030, IoU.bulletin board: 0.6168, IoU.shower: 0.0013, IoU.radiator: 0.5822, IoU.glass: 0.1999, IoU.clock: 0.2953, IoU.flag: 0.6765, Acc.wall: 0.8856, Acc.building: 0.9200, Acc.sky: 0.9700, Acc.floor: 0.9081, Acc.tree: 0.9032, Acc.ceiling: 0.9207, Acc.road: 0.9048, Acc.bed : 0.9602, Acc.windowpane: 0.8005, Acc.grass: 0.8909, Acc.cabinet: 0.7300, Acc.sidewalk: 0.8361, Acc.person: 0.8977, Acc.earth: 0.4813, Acc.door: 0.7461, Acc.table: 0.7661, Acc.mountain: 0.7670, Acc.plant: 0.6468, Acc.curtain: 0.8584, Acc.chair: 0.7399, Acc.car: 0.9074, Acc.water: 0.6610, Acc.painting: 0.8794, Acc.sofa: 0.8340, Acc.shelf: 0.6255, Acc.house: 0.6578, Acc.sea: 0.9011, Acc.mirror: 0.8818, Acc.rug: 0.8079, Acc.field: 0.5302, Acc.armchair: 0.7486, Acc.seat: 0.8631, Acc.fence: 0.6447, Acc.desk: 0.7651, Acc.rock: 0.6092, Acc.wardrobe: 0.7378, Acc.lamp: 0.7895, Acc.bathtub: 0.9288, Acc.railing: 0.5230, Acc.cushion: 0.7785, Acc.base: 0.3732, Acc.box: 0.4107, Acc.column: 0.5982, Acc.signboard: 0.4820, Acc.chest of drawers: 0.5920, Acc.counter: 0.6591, Acc.sand: 0.5124, Acc.sink: 0.8208, Acc.skyscraper: 0.6487, Acc.fireplace: 0.9014, Acc.refrigerator: 0.9344, Acc.grandstand: 0.7625, Acc.path: 0.2611, Acc.stairs: 0.3353, Acc.runway: 0.8900, Acc.case: 0.7348, Acc.pool table: 0.9743, Acc.pillow: 0.7198, Acc.screen door: 0.8233, Acc.stairway: 0.6057, Acc.river: 0.2510, Acc.bridge: 0.8985, Acc.bookcase: 0.5763, Acc.blind: 0.3845, Acc.coffee table: 0.8368, Acc.toilet: 0.9212, Acc.flower: 0.5034, Acc.book: 0.6608, Acc.hill: 0.1164, Acc.bench: 0.6162, Acc.countertop: 0.7585, Acc.stove: 0.8719, Acc.palm: 0.7757, Acc.kitchen island: 0.6460, Acc.computer: 0.8967, Acc.swivel chair: 0.7455, Acc.boat: 0.9166, Acc.bar: 0.5371, Acc.arcade machine: 0.7988, Acc.hovel: 0.1468, Acc.bus: 0.9515, Acc.towel: 0.8207, Acc.light: 0.5952, Acc.truck: 0.5175, Acc.tower: 0.2242, Acc.chandelier: 0.8139, Acc.awning: 0.4619, Acc.streetlight: 0.3139, Acc.booth: 0.3407, Acc.television receiver: 0.9076, Acc.airplane: 0.6595, Acc.dirt track: 0.0832, Acc.apparel: 0.7076, Acc.pole: 0.2571, Acc.land: 0.0572, Acc.bannister: 0.2080, Acc.escalator: 0.6474, Acc.ottoman: 0.6915, Acc.bottle: 0.3282, Acc.buffet: 0.6038, Acc.poster: 0.4376, Acc.stage: 0.2735, Acc.van: 0.6950, Acc.ship: 0.0003, Acc.fountain: 0.2320, Acc.conveyer belt: 0.9373, Acc.canopy: 0.6688, Acc.washer: 0.8615, Acc.plaything: 0.4451, Acc.swimming pool: 0.8348, Acc.stool: 0.6265, Acc.barrel: 0.5869, Acc.basket: 0.5760, Acc.waterfall: 0.7056, Acc.tent: 0.9852, Acc.bag: 0.2207, Acc.minibike: 0.8093, Acc.cradle: 0.8505, Acc.oven: 0.7603, Acc.ball: 0.4062, Acc.food: 0.6383, Acc.step: 0.2310, Acc.tank: 0.6502, Acc.trade name: 0.3786, Acc.microwave: 0.9260, Acc.pot: 0.5772, Acc.animal: 0.6943, Acc.bicycle: 0.7559, Acc.lake: 0.6893, Acc.dishwasher: 0.8058, Acc.screen: 0.3484, Acc.blanket: 0.1647, Acc.sculpture: 0.6613, Acc.hood: 0.6462, Acc.sconce: 0.6836, Acc.vase: 0.5864, Acc.traffic light: 0.5269, Acc.tray: 0.1262, Acc.ashcan: 0.5892, Acc.fan: 0.7675, Acc.pier: 0.4387, Acc.crt screen: 0.3870, Acc.plate: 0.7835, Acc.monitor: 0.1125, Acc.bulletin board: 0.7296, Acc.shower: 0.0013, Acc.radiator: 0.6632, Acc.glass: 0.2412, Acc.clock: 0.3244, Acc.flag: 0.7589 2023-11-02 21:24:46,276 - mmseg - INFO - Iter [7050/20000] lr: 2.098e-06, eta: 4:49:50, time: 2.370, data_time: 1.166, memory: 38534, decode.loss_ce: 0.2501, decode.acc_seg: 90.2302, loss: 0.2501 2023-11-02 21:25:46,764 - mmseg - INFO - Iter [7100/20000] lr: 2.090e-06, eta: 4:48:31, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2426, decode.acc_seg: 90.5465, loss: 0.2426 2023-11-02 21:26:47,330 - mmseg - INFO - Iter [7150/20000] lr: 2.082e-06, eta: 4:47:12, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2601, decode.acc_seg: 89.6417, loss: 0.2601 2023-11-02 21:27:47,832 - mmseg - INFO - Iter [7200/20000] lr: 2.074e-06, eta: 4:45:53, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2568, decode.acc_seg: 89.6594, loss: 0.2568 2023-11-02 21:28:48,359 - mmseg - INFO - Iter [7250/20000] lr: 2.066e-06, eta: 4:44:35, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2551, decode.acc_seg: 89.8411, loss: 0.2551 2023-11-02 21:29:51,202 - mmseg - INFO - Iter [7300/20000] lr: 2.057e-06, eta: 4:43:20, time: 1.257, data_time: 0.053, memory: 38534, decode.loss_ce: 0.2421, decode.acc_seg: 90.5091, loss: 0.2421 2023-11-02 21:30:51,778 - mmseg - INFO - Iter [7350/20000] lr: 2.049e-06, eta: 4:42:03, time: 1.212, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2366, decode.acc_seg: 90.3921, loss: 0.2366 2023-11-02 21:31:52,248 - mmseg - INFO - Iter [7400/20000] lr: 2.041e-06, eta: 4:40:45, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2560, decode.acc_seg: 90.0604, loss: 0.2560 2023-11-02 21:32:56,821 - mmseg - INFO - Iter [7450/20000] lr: 2.033e-06, eta: 4:39:34, time: 1.291, data_time: 0.087, memory: 38534, decode.loss_ce: 0.2456, decode.acc_seg: 90.4508, loss: 0.2456 2023-11-02 21:33:57,360 - mmseg - INFO - Iter [7500/20000] lr: 2.025e-06, eta: 4:38:17, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2512, decode.acc_seg: 90.4380, loss: 0.2512 2023-11-02 21:34:57,889 - mmseg - INFO - Iter [7550/20000] lr: 2.017e-06, eta: 4:37:00, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2454, decode.acc_seg: 90.1389, loss: 0.2454 2023-11-02 21:36:00,728 - mmseg - INFO - Iter [7600/20000] lr: 2.009e-06, eta: 4:35:47, time: 1.257, data_time: 0.053, memory: 38534, decode.loss_ce: 0.2433, decode.acc_seg: 90.3457, loss: 0.2433 2023-11-02 21:37:01,262 - mmseg - INFO - Iter [7650/20000] lr: 2.001e-06, eta: 4:34:30, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2346, decode.acc_seg: 90.7083, loss: 0.2346 2023-11-02 21:38:01,778 - mmseg - INFO - Iter [7700/20000] lr: 1.993e-06, eta: 4:33:13, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2340, decode.acc_seg: 90.7219, loss: 0.2340 2023-11-02 21:39:02,305 - mmseg - INFO - Iter [7750/20000] lr: 1.985e-06, eta: 4:31:57, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2459, decode.acc_seg: 90.2853, loss: 0.2459 2023-11-02 21:40:02,890 - mmseg - INFO - Iter [7800/20000] lr: 1.976e-06, eta: 4:30:41, time: 1.212, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2415, decode.acc_seg: 90.5008, loss: 0.2415 2023-11-02 21:41:03,424 - mmseg - INFO - Iter [7850/20000] lr: 1.968e-06, eta: 4:29:25, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2284, decode.acc_seg: 90.8317, loss: 0.2284 2023-11-02 21:42:03,982 - mmseg - INFO - Iter [7900/20000] lr: 1.960e-06, eta: 4:28:09, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2245, decode.acc_seg: 91.1131, loss: 0.2245 2023-11-02 21:43:06,812 - mmseg - INFO - Iter [7950/20000] lr: 1.952e-06, eta: 4:26:57, time: 1.257, data_time: 0.052, memory: 38534, decode.loss_ce: 0.2311, decode.acc_seg: 90.9436, loss: 0.2311 2023-11-02 21:44:07,326 - mmseg - INFO - Saving checkpoint at 8000 iterations 2023-11-02 21:45:04,681 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 21:45:04,681 - mmseg - INFO - Iter [8000/20000] lr: 1.944e-06, eta: 4:27:08, time: 2.357, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2309, decode.acc_seg: 90.9793, loss: 0.2309 2023-11-02 21:46:03,704 - mmseg - INFO - per class results: 2023-11-02 21:46:03,713 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 78.99 | 87.48 | | building | 82.6 | 91.67 | | sky | 94.18 | 97.07 | | floor | 81.34 | 89.99 | | tree | 74.32 | 89.66 | | ceiling | 85.25 | 92.97 | | road | 83.67 | 90.99 | | bed | 90.41 | 96.96 | | windowpane | 64.25 | 82.42 | | grass | 68.57 | 88.54 | | cabinet | 61.24 | 70.81 | | sidewalk | 65.16 | 80.46 | | person | 82.16 | 91.18 | | earth | 29.85 | 38.04 | | door | 56.57 | 78.11 | | table | 66.17 | 76.62 | | mountain | 62.87 | 79.46 | | plant | 49.84 | 57.88 | | curtain | 76.54 | 86.3 | | chair | 57.78 | 68.4 | | car | 84.51 | 92.76 | | water | 54.64 | 67.82 | | painting | 73.15 | 88.7 | | sofa | 77.06 | 93.18 | | shelf | 44.13 | 64.73 | | house | 42.38 | 64.36 | | sea | 57.53 | 83.33 | | mirror | 70.33 | 79.57 | | rug | 56.24 | 61.88 | | field | 29.17 | 60.76 | | armchair | 50.52 | 67.15 | | seat | 64.1 | 88.92 | | fence | 47.03 | 69.19 | | desk | 53.96 | 74.58 | | rock | 46.57 | 60.34 | | wardrobe | 50.52 | 67.93 | | lamp | 65.61 | 79.96 | | bathtub | 88.15 | 92.95 | | railing | 39.48 | 51.3 | | cushion | 60.49 | 75.88 | | base | 34.15 | 46.43 | | box | 29.49 | 39.71 | | column | 50.09 | 64.24 | | signboard | 37.44 | 49.99 | | chest of drawers | 38.59 | 76.1 | | counter | 47.81 | 59.69 | | sand | 36.71 | 51.6 | | sink | 75.74 | 85.53 | | skyscraper | 49.1 | 60.69 | | fireplace | 68.94 | 92.59 | | refrigerator | 81.6 | 91.3 | | grandstand | 48.27 | 71.03 | | path | 18.83 | 26.76 | | stairs | 25.23 | 30.3 | | runway | 72.15 | 91.82 | | case | 57.53 | 69.7 | | pool table | 92.29 | 98.08 | | pillow | 53.53 | 61.15 | | screen door | 71.05 | 82.54 | | stairway | 42.92 | 64.01 | | river | 23.39 | 45.2 | | bridge | 68.77 | 82.5 | | bookcase | 34.3 | 65.0 | | blind | 43.1 | 49.0 | | coffee table | 64.58 | 83.11 | | toilet | 88.49 | 94.92 | | flower | 37.37 | 48.69 | | book | 45.71 | 60.67 | | hill | 6.95 | 12.92 | | bench | 51.77 | 58.73 | | countertop | 58.19 | 75.04 | | stove | 81.58 | 88.05 | | palm | 47.33 | 70.96 | | kitchen island | 56.54 | 78.49 | | computer | 76.33 | 87.54 | | swivel chair | 44.29 | 74.35 | | boat | 37.39 | 90.79 | | bar | 57.92 | 65.46 | | arcade machine | 75.33 | 77.55 | | hovel | 11.39 | 12.16 | | bus | 91.2 | 95.1 | | towel | 68.22 | 80.98 | | light | 49.07 | 60.1 | | truck | 38.88 | 51.09 | | tower | 10.42 | 18.32 | | chandelier | 65.07 | 77.83 | | awning | 36.42 | 45.96 | | streetlight | 24.61 | 33.88 | | booth | 32.56 | 36.66 | | television receiver | 72.86 | 83.71 | | airplane | 58.86 | 63.06 | | dirt track | 0.7 | 0.9 | | apparel | 52.27 | 75.05 | | pole | 20.56 | 25.8 | | land | 3.29 | 5.69 | | bannister | 18.35 | 25.67 | | escalator | 62.66 | 78.56 | | ottoman | 53.29 | 73.46 | | bottle | 23.28 | 31.67 | | buffet | 51.57 | 64.23 | | poster | 28.06 | 41.21 | | stage | 12.45 | 25.43 | | van | 46.11 | 66.6 | | ship | 11.5 | 13.24 | | fountain | 26.21 | 26.44 | | conveyer belt | 80.27 | 93.68 | | canopy | 55.04 | 71.04 | | washer | 80.8 | 84.96 | | plaything | 29.33 | 41.34 | | swimming pool | 56.7 | 80.74 | | stool | 47.62 | 64.48 | | barrel | 60.95 | 74.12 | | basket | 42.01 | 52.45 | | waterfall | 48.43 | 59.4 | | tent | 94.45 | 98.23 | | bag | 25.36 | 32.83 | | minibike | 71.48 | 82.83 | | cradle | 78.3 | 96.68 | | oven | 65.25 | 79.29 | | ball | 23.76 | 24.77 | | food | 63.24 | 73.75 | | step | 19.16 | 25.18 | | tank | 52.34 | 63.91 | | trade name | 25.1 | 29.16 | | microwave | 86.85 | 91.07 | | pot | 51.49 | 59.16 | | animal | 73.99 | 78.45 | | bicycle | 58.66 | 79.73 | | lake | 57.52 | 63.65 | | dishwasher | 71.22 | 82.12 | | screen | 48.6 | 72.2 | | blanket | 9.72 | 10.82 | | sculpture | 60.25 | 67.57 | | hood | 58.5 | 70.74 | | sconce | 51.39 | 70.38 | | vase | 40.7 | 55.4 | | traffic light | 30.96 | 51.83 | | tray | 10.02 | 16.06 | | ashcan | 48.99 | 64.31 | | fan | 60.32 | 74.1 | | pier | 38.61 | 43.19 | | crt screen | 4.83 | 13.59 | | plate | 57.42 | 76.91 | | monitor | 19.96 | 20.89 | | bulletin board | 61.96 | 75.2 | | shower | 0.61 | 0.61 | | radiator | 58.19 | 69.68 | | glass | 17.22 | 18.39 | | clock | 29.52 | 34.62 | | flag | 68.82 | 78.59 | +---------------------+-------+-------+ 2023-11-02 21:46:03,713 - mmseg - INFO - Summary: 2023-11-02 21:46:03,713 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 83.72 | 51.76 | 64.16 | +-------+-------+-------+ 2023-11-02 21:46:03,715 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 21:46:03,715 - mmseg - INFO - Iter(val) [250] aAcc: 0.8372, mIoU: 0.5176, mAcc: 0.6416, IoU.wall: 0.7899, IoU.building: 0.8260, IoU.sky: 0.9418, IoU.floor: 0.8134, IoU.tree: 0.7432, IoU.ceiling: 0.8525, IoU.road: 0.8367, IoU.bed : 0.9041, IoU.windowpane: 0.6425, IoU.grass: 0.6857, IoU.cabinet: 0.6124, IoU.sidewalk: 0.6516, IoU.person: 0.8216, IoU.earth: 0.2985, IoU.door: 0.5657, IoU.table: 0.6617, IoU.mountain: 0.6287, IoU.plant: 0.4984, IoU.curtain: 0.7654, IoU.chair: 0.5778, IoU.car: 0.8451, IoU.water: 0.5464, IoU.painting: 0.7315, IoU.sofa: 0.7706, IoU.shelf: 0.4413, IoU.house: 0.4238, IoU.sea: 0.5753, IoU.mirror: 0.7033, IoU.rug: 0.5624, IoU.field: 0.2917, IoU.armchair: 0.5052, IoU.seat: 0.6410, IoU.fence: 0.4703, IoU.desk: 0.5396, IoU.rock: 0.4657, IoU.wardrobe: 0.5052, IoU.lamp: 0.6561, IoU.bathtub: 0.8815, IoU.railing: 0.3948, IoU.cushion: 0.6049, IoU.base: 0.3415, IoU.box: 0.2949, IoU.column: 0.5009, IoU.signboard: 0.3744, IoU.chest of drawers: 0.3859, IoU.counter: 0.4781, IoU.sand: 0.3671, IoU.sink: 0.7574, IoU.skyscraper: 0.4910, IoU.fireplace: 0.6894, IoU.refrigerator: 0.8160, IoU.grandstand: 0.4827, IoU.path: 0.1883, IoU.stairs: 0.2523, IoU.runway: 0.7215, IoU.case: 0.5753, IoU.pool table: 0.9229, IoU.pillow: 0.5353, IoU.screen door: 0.7105, IoU.stairway: 0.4292, IoU.river: 0.2339, IoU.bridge: 0.6877, IoU.bookcase: 0.3430, IoU.blind: 0.4310, IoU.coffee table: 0.6458, IoU.toilet: 0.8849, IoU.flower: 0.3737, IoU.book: 0.4571, IoU.hill: 0.0695, IoU.bench: 0.5177, IoU.countertop: 0.5819, IoU.stove: 0.8158, IoU.palm: 0.4733, IoU.kitchen island: 0.5654, IoU.computer: 0.7633, IoU.swivel chair: 0.4429, IoU.boat: 0.3739, IoU.bar: 0.5792, IoU.arcade machine: 0.7533, IoU.hovel: 0.1139, IoU.bus: 0.9120, IoU.towel: 0.6822, IoU.light: 0.4907, IoU.truck: 0.3888, IoU.tower: 0.1042, IoU.chandelier: 0.6507, IoU.awning: 0.3642, IoU.streetlight: 0.2461, IoU.booth: 0.3256, IoU.television receiver: 0.7286, IoU.airplane: 0.5886, IoU.dirt track: 0.0070, IoU.apparel: 0.5227, IoU.pole: 0.2056, IoU.land: 0.0329, IoU.bannister: 0.1835, IoU.escalator: 0.6266, IoU.ottoman: 0.5329, IoU.bottle: 0.2328, IoU.buffet: 0.5157, IoU.poster: 0.2806, IoU.stage: 0.1245, IoU.van: 0.4611, IoU.ship: 0.1150, IoU.fountain: 0.2621, IoU.conveyer belt: 0.8027, IoU.canopy: 0.5504, IoU.washer: 0.8080, IoU.plaything: 0.2933, IoU.swimming pool: 0.5670, IoU.stool: 0.4762, IoU.barrel: 0.6095, IoU.basket: 0.4201, IoU.waterfall: 0.4843, IoU.tent: 0.9445, IoU.bag: 0.2536, IoU.minibike: 0.7148, IoU.cradle: 0.7830, IoU.oven: 0.6525, IoU.ball: 0.2376, IoU.food: 0.6324, IoU.step: 0.1916, IoU.tank: 0.5234, IoU.trade name: 0.2510, IoU.microwave: 0.8685, IoU.pot: 0.5149, IoU.animal: 0.7399, IoU.bicycle: 0.5866, IoU.lake: 0.5752, IoU.dishwasher: 0.7122, IoU.screen: 0.4860, IoU.blanket: 0.0972, IoU.sculpture: 0.6025, IoU.hood: 0.5850, IoU.sconce: 0.5139, IoU.vase: 0.4070, IoU.traffic light: 0.3096, IoU.tray: 0.1002, IoU.ashcan: 0.4899, IoU.fan: 0.6032, IoU.pier: 0.3861, IoU.crt screen: 0.0483, IoU.plate: 0.5742, IoU.monitor: 0.1996, IoU.bulletin board: 0.6196, IoU.shower: 0.0061, IoU.radiator: 0.5819, IoU.glass: 0.1722, IoU.clock: 0.2952, IoU.flag: 0.6882, Acc.wall: 0.8748, Acc.building: 0.9167, Acc.sky: 0.9707, Acc.floor: 0.8999, Acc.tree: 0.8966, Acc.ceiling: 0.9297, Acc.road: 0.9099, Acc.bed : 0.9696, Acc.windowpane: 0.8242, Acc.grass: 0.8854, Acc.cabinet: 0.7081, Acc.sidewalk: 0.8046, Acc.person: 0.9118, Acc.earth: 0.3804, Acc.door: 0.7811, Acc.table: 0.7662, Acc.mountain: 0.7946, Acc.plant: 0.5788, Acc.curtain: 0.8630, Acc.chair: 0.6840, Acc.car: 0.9276, Acc.water: 0.6782, Acc.painting: 0.8870, Acc.sofa: 0.9318, Acc.shelf: 0.6473, Acc.house: 0.6436, Acc.sea: 0.8333, Acc.mirror: 0.7957, Acc.rug: 0.6188, Acc.field: 0.6076, Acc.armchair: 0.6715, Acc.seat: 0.8892, Acc.fence: 0.6919, Acc.desk: 0.7458, Acc.rock: 0.6034, Acc.wardrobe: 0.6793, Acc.lamp: 0.7996, Acc.bathtub: 0.9295, Acc.railing: 0.5130, Acc.cushion: 0.7588, Acc.base: 0.4643, Acc.box: 0.3971, Acc.column: 0.6424, Acc.signboard: 0.4999, Acc.chest of drawers: 0.7610, Acc.counter: 0.5969, Acc.sand: 0.5160, Acc.sink: 0.8553, Acc.skyscraper: 0.6069, Acc.fireplace: 0.9259, Acc.refrigerator: 0.9130, Acc.grandstand: 0.7103, Acc.path: 0.2676, Acc.stairs: 0.3030, Acc.runway: 0.9182, Acc.case: 0.6970, Acc.pool table: 0.9808, Acc.pillow: 0.6115, Acc.screen door: 0.8254, Acc.stairway: 0.6401, Acc.river: 0.4520, Acc.bridge: 0.8250, Acc.bookcase: 0.6500, Acc.blind: 0.4900, Acc.coffee table: 0.8311, Acc.toilet: 0.9492, Acc.flower: 0.4869, Acc.book: 0.6067, Acc.hill: 0.1292, Acc.bench: 0.5873, Acc.countertop: 0.7504, Acc.stove: 0.8805, Acc.palm: 0.7096, Acc.kitchen island: 0.7849, Acc.computer: 0.8754, Acc.swivel chair: 0.7435, Acc.boat: 0.9079, Acc.bar: 0.6546, Acc.arcade machine: 0.7755, Acc.hovel: 0.1216, Acc.bus: 0.9510, Acc.towel: 0.8098, Acc.light: 0.6010, Acc.truck: 0.5109, Acc.tower: 0.1832, Acc.chandelier: 0.7783, Acc.awning: 0.4596, Acc.streetlight: 0.3388, Acc.booth: 0.3666, Acc.television receiver: 0.8371, Acc.airplane: 0.6306, Acc.dirt track: 0.0090, Acc.apparel: 0.7505, Acc.pole: 0.2580, Acc.land: 0.0569, Acc.bannister: 0.2567, Acc.escalator: 0.7856, Acc.ottoman: 0.7346, Acc.bottle: 0.3167, Acc.buffet: 0.6423, Acc.poster: 0.4121, Acc.stage: 0.2543, Acc.van: 0.6660, Acc.ship: 0.1324, Acc.fountain: 0.2644, Acc.conveyer belt: 0.9368, Acc.canopy: 0.7104, Acc.washer: 0.8496, Acc.plaything: 0.4134, Acc.swimming pool: 0.8074, Acc.stool: 0.6448, Acc.barrel: 0.7412, Acc.basket: 0.5245, Acc.waterfall: 0.5940, Acc.tent: 0.9823, Acc.bag: 0.3283, Acc.minibike: 0.8283, Acc.cradle: 0.9668, Acc.oven: 0.7929, Acc.ball: 0.2477, Acc.food: 0.7375, Acc.step: 0.2518, Acc.tank: 0.6391, Acc.trade name: 0.2916, Acc.microwave: 0.9107, Acc.pot: 0.5916, Acc.animal: 0.7845, Acc.bicycle: 0.7973, Acc.lake: 0.6365, Acc.dishwasher: 0.8212, Acc.screen: 0.7220, Acc.blanket: 0.1082, Acc.sculpture: 0.6757, Acc.hood: 0.7074, Acc.sconce: 0.7038, Acc.vase: 0.5540, Acc.traffic light: 0.5183, Acc.tray: 0.1606, Acc.ashcan: 0.6431, Acc.fan: 0.7410, Acc.pier: 0.4319, Acc.crt screen: 0.1359, Acc.plate: 0.7691, Acc.monitor: 0.2089, Acc.bulletin board: 0.7520, Acc.shower: 0.0061, Acc.radiator: 0.6968, Acc.glass: 0.1839, Acc.clock: 0.3462, Acc.flag: 0.7859 2023-11-02 21:47:04,329 - mmseg - INFO - Iter [8050/20000] lr: 1.936e-06, eta: 4:27:20, time: 2.393, data_time: 1.188, memory: 38534, decode.loss_ce: 0.2317, decode.acc_seg: 90.7601, loss: 0.2317 2023-11-02 21:48:04,850 - mmseg - INFO - Iter [8100/20000] lr: 1.928e-06, eta: 4:26:03, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2331, decode.acc_seg: 90.4812, loss: 0.2331 2023-11-02 21:49:05,361 - mmseg - INFO - Iter [8150/20000] lr: 1.920e-06, eta: 4:24:46, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2283, decode.acc_seg: 90.9003, loss: 0.2283 2023-11-02 21:50:05,915 - mmseg - INFO - Iter [8200/20000] lr: 1.912e-06, eta: 4:23:30, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2316, decode.acc_seg: 90.6722, loss: 0.2316 2023-11-02 21:51:09,061 - mmseg - INFO - Iter [8250/20000] lr: 1.904e-06, eta: 4:22:17, time: 1.263, data_time: 0.059, memory: 38534, decode.loss_ce: 0.2289, decode.acc_seg: 90.9262, loss: 0.2289 2023-11-02 21:52:09,653 - mmseg - INFO - Iter [8300/20000] lr: 1.895e-06, eta: 4:21:01, time: 1.212, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2227, decode.acc_seg: 91.1583, loss: 0.2227 2023-11-02 21:53:10,245 - mmseg - INFO - Iter [8350/20000] lr: 1.887e-06, eta: 4:19:46, time: 1.212, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2162, decode.acc_seg: 91.3562, loss: 0.2162 2023-11-02 21:54:10,825 - mmseg - INFO - Iter [8400/20000] lr: 1.879e-06, eta: 4:18:30, time: 1.212, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2567, decode.acc_seg: 90.3585, loss: 0.2567 2023-11-02 21:55:11,408 - mmseg - INFO - Iter [8450/20000] lr: 1.871e-06, eta: 4:17:15, time: 1.212, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2240, decode.acc_seg: 91.1746, loss: 0.2240 2023-11-02 21:56:12,022 - mmseg - INFO - Iter [8500/20000] lr: 1.863e-06, eta: 4:15:59, time: 1.212, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2409, decode.acc_seg: 90.4679, loss: 0.2409 2023-11-02 21:57:14,999 - mmseg - INFO - Iter [8550/20000] lr: 1.855e-06, eta: 4:14:48, time: 1.260, data_time: 0.054, memory: 38534, decode.loss_ce: 0.2237, decode.acc_seg: 90.8200, loss: 0.2237 2023-11-02 21:58:15,539 - mmseg - INFO - Iter [8600/20000] lr: 1.847e-06, eta: 4:13:33, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2185, decode.acc_seg: 91.4089, loss: 0.2185 2023-11-02 21:59:16,068 - mmseg - INFO - Iter [8650/20000] lr: 1.839e-06, eta: 4:12:18, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2212, decode.acc_seg: 91.2823, loss: 0.2212 2023-11-02 22:00:16,658 - mmseg - INFO - Iter [8700/20000] lr: 1.831e-06, eta: 4:11:03, time: 1.212, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2210, decode.acc_seg: 91.2013, loss: 0.2210 2023-11-02 22:01:17,215 - mmseg - INFO - Iter [8750/20000] lr: 1.823e-06, eta: 4:09:49, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2239, decode.acc_seg: 90.8048, loss: 0.2239 2023-11-02 22:02:17,800 - mmseg - INFO - Iter [8800/20000] lr: 1.814e-06, eta: 4:08:34, time: 1.212, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2185, decode.acc_seg: 91.0112, loss: 0.2185 2023-11-02 22:03:20,688 - mmseg - INFO - Iter [8850/20000] lr: 1.806e-06, eta: 4:07:23, time: 1.258, data_time: 0.053, memory: 38534, decode.loss_ce: 0.2264, decode.acc_seg: 90.9993, loss: 0.2264 2023-11-02 22:04:21,255 - mmseg - INFO - Iter [8900/20000] lr: 1.798e-06, eta: 4:06:09, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2240, decode.acc_seg: 91.2582, loss: 0.2240 2023-11-02 22:05:21,821 - mmseg - INFO - Iter [8950/20000] lr: 1.790e-06, eta: 4:04:55, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2325, decode.acc_seg: 90.8970, loss: 0.2325 2023-11-02 22:06:22,363 - mmseg - INFO - Saving checkpoint at 9000 iterations 2023-11-02 22:07:20,748 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 22:07:20,749 - mmseg - INFO - Iter [9000/20000] lr: 1.782e-06, eta: 4:04:53, time: 2.379, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2127, decode.acc_seg: 91.3862, loss: 0.2127 2023-11-02 22:08:20,025 - mmseg - INFO - per class results: 2023-11-02 22:08:20,033 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 79.35 | 87.09 | | building | 82.84 | 93.41 | | sky | 93.79 | 97.8 | | floor | 82.37 | 90.91 | | tree | 74.18 | 85.51 | | ceiling | 84.48 | 94.26 | | road | 83.03 | 90.54 | | bed | 90.7 | 96.87 | | windowpane | 64.35 | 79.4 | | grass | 72.59 | 88.62 | | cabinet | 65.75 | 78.82 | | sidewalk | 65.21 | 80.29 | | person | 81.48 | 93.83 | | earth | 33.6 | 43.22 | | door | 54.89 | 71.03 | | table | 66.22 | 77.14 | | mountain | 59.67 | 76.95 | | plant | 51.94 | 68.57 | | curtain | 76.94 | 89.02 | | chair | 58.69 | 72.26 | | car | 84.59 | 93.77 | | water | 55.68 | 69.62 | | painting | 71.72 | 89.59 | | sofa | 77.25 | 87.76 | | shelf | 45.51 | 63.28 | | house | 30.87 | 37.34 | | sea | 60.81 | 85.98 | | mirror | 72.5 | 80.62 | | rug | 68.03 | 75.68 | | field | 40.93 | 68.15 | | armchair | 53.19 | 71.47 | | seat | 64.25 | 89.56 | | fence | 47.19 | 64.66 | | desk | 49.09 | 81.23 | | rock | 44.17 | 57.19 | | wardrobe | 56.31 | 65.22 | | lamp | 66.33 | 82.49 | | bathtub | 85.74 | 88.62 | | railing | 41.49 | 56.21 | | cushion | 59.61 | 72.61 | | base | 36.03 | 48.27 | | box | 32.61 | 42.33 | | column | 50.04 | 68.22 | | signboard | 37.95 | 53.94 | | chest of drawers | 39.66 | 62.72 | | counter | 46.91 | 64.06 | | sand | 37.27 | 52.39 | | sink | 76.48 | 84.6 | | skyscraper | 47.44 | 51.98 | | fireplace | 70.22 | 91.23 | | refrigerator | 78.4 | 90.24 | | grandstand | 52.61 | 76.66 | | path | 19.23 | 27.47 | | stairs | 25.35 | 29.4 | | runway | 71.68 | 92.26 | | case | 62.05 | 70.11 | | pool table | 93.01 | 98.13 | | pillow | 57.75 | 69.6 | | screen door | 62.99 | 66.96 | | stairway | 38.53 | 54.74 | | river | 21.38 | 31.22 | | bridge | 72.72 | 89.41 | | bookcase | 36.41 | 55.36 | | blind | 43.02 | 51.26 | | coffee table | 66.37 | 84.12 | | toilet | 88.92 | 93.58 | | flower | 39.84 | 56.97 | | book | 48.06 | 70.27 | | hill | 7.81 | 13.27 | | bench | 51.56 | 59.31 | | countertop | 59.93 | 74.52 | | stove | 79.02 | 88.19 | | palm | 46.37 | 72.39 | | kitchen island | 58.45 | 72.94 | | computer | 74.64 | 89.18 | | swivel chair | 44.13 | 79.06 | | boat | 59.74 | 91.66 | | bar | 57.19 | 59.92 | | arcade machine | 83.28 | 88.9 | | hovel | 18.08 | 19.5 | | bus | 91.2 | 95.53 | | towel | 67.15 | 89.35 | | light | 49.61 | 61.8 | | truck | 45.74 | 56.98 | | tower | 12.6 | 23.57 | | chandelier | 65.43 | 78.58 | | awning | 34.38 | 44.31 | | streetlight | 24.3 | 33.26 | | booth | 33.66 | 34.85 | | television receiver | 70.76 | 86.56 | | airplane | 58.88 | 64.75 | | dirt track | 7.56 | 26.26 | | apparel | 57.17 | 85.06 | | pole | 20.46 | 25.41 | | land | 3.75 | 6.42 | | bannister | 18.51 | 26.19 | | escalator | 51.7 | 64.69 | | ottoman | 52.05 | 69.68 | | bottle | 23.86 | 32.8 | | buffet | 52.04 | 70.36 | | poster | 29.56 | 43.23 | | stage | 12.16 | 22.03 | | van | 45.68 | 57.25 | | ship | 0.28 | 0.3 | | fountain | 39.13 | 40.0 | | conveyer belt | 79.21 | 96.9 | | canopy | 52.1 | 59.16 | | washer | 81.66 | 85.96 | | plaything | 29.09 | 46.49 | | swimming pool | 60.9 | 91.1 | | stool | 48.13 | 65.92 | | barrel | 48.69 | 62.68 | | basket | 39.47 | 58.46 | | waterfall | 52.18 | 76.61 | | tent | 94.69 | 98.03 | | bag | 23.25 | 28.72 | | minibike | 71.36 | 85.32 | | cradle | 81.06 | 95.99 | | oven | 62.55 | 79.65 | | ball | 56.42 | 62.23 | | food | 64.07 | 72.62 | | step | 17.85 | 21.08 | | tank | 52.15 | 64.38 | | trade name | 31.46 | 38.86 | | microwave | 85.95 | 93.95 | | pot | 52.04 | 60.65 | | animal | 69.26 | 72.04 | | bicycle | 59.52 | 75.25 | | lake | 54.76 | 68.39 | | dishwasher | 73.4 | 80.15 | | screen | 49.86 | 73.54 | | blanket | 13.61 | 15.09 | | sculpture | 69.05 | 79.26 | | hood | 58.99 | 70.68 | | sconce | 53.33 | 68.33 | | vase | 41.36 | 55.24 | | traffic light | 32.04 | 48.78 | | tray | 9.23 | 15.65 | | ashcan | 50.09 | 67.62 | | fan | 60.9 | 75.09 | | pier | 38.45 | 45.27 | | crt screen | 1.7 | 4.31 | | plate | 57.47 | 76.94 | | monitor | 26.09 | 28.91 | | bulletin board | 58.23 | 74.11 | | shower | 0.92 | 0.92 | | radiator | 57.76 | 66.93 | | glass | 20.17 | 23.03 | | clock | 30.63 | 36.28 | | flag | 67.65 | 73.84 | +---------------------+-------+-------+ 2023-11-02 22:08:20,033 - mmseg - INFO - Summary: 2023-11-02 22:08:20,033 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 84.17 | 52.65 | 65.02 | +-------+-------+-------+ 2023-11-02 22:08:20,034 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 22:08:20,034 - mmseg - INFO - Iter(val) [250] aAcc: 0.8417, mIoU: 0.5265, mAcc: 0.6502, IoU.wall: 0.7935, IoU.building: 0.8284, IoU.sky: 0.9379, IoU.floor: 0.8237, IoU.tree: 0.7418, IoU.ceiling: 0.8448, IoU.road: 0.8303, IoU.bed : 0.9070, IoU.windowpane: 0.6435, IoU.grass: 0.7259, IoU.cabinet: 0.6575, IoU.sidewalk: 0.6521, IoU.person: 0.8148, IoU.earth: 0.3360, IoU.door: 0.5489, IoU.table: 0.6622, IoU.mountain: 0.5967, IoU.plant: 0.5194, IoU.curtain: 0.7694, IoU.chair: 0.5869, IoU.car: 0.8459, IoU.water: 0.5568, IoU.painting: 0.7172, IoU.sofa: 0.7725, IoU.shelf: 0.4551, IoU.house: 0.3087, IoU.sea: 0.6081, IoU.mirror: 0.7250, IoU.rug: 0.6803, IoU.field: 0.4093, IoU.armchair: 0.5319, IoU.seat: 0.6425, IoU.fence: 0.4719, IoU.desk: 0.4909, IoU.rock: 0.4417, IoU.wardrobe: 0.5631, IoU.lamp: 0.6633, IoU.bathtub: 0.8574, IoU.railing: 0.4149, IoU.cushion: 0.5961, IoU.base: 0.3603, IoU.box: 0.3261, IoU.column: 0.5004, IoU.signboard: 0.3795, IoU.chest of drawers: 0.3966, IoU.counter: 0.4691, IoU.sand: 0.3727, IoU.sink: 0.7648, IoU.skyscraper: 0.4744, IoU.fireplace: 0.7022, IoU.refrigerator: 0.7840, IoU.grandstand: 0.5261, IoU.path: 0.1923, IoU.stairs: 0.2535, IoU.runway: 0.7168, IoU.case: 0.6205, IoU.pool table: 0.9301, IoU.pillow: 0.5775, IoU.screen door: 0.6299, IoU.stairway: 0.3853, IoU.river: 0.2138, IoU.bridge: 0.7272, IoU.bookcase: 0.3641, IoU.blind: 0.4302, IoU.coffee table: 0.6637, IoU.toilet: 0.8892, IoU.flower: 0.3984, IoU.book: 0.4806, IoU.hill: 0.0781, IoU.bench: 0.5156, IoU.countertop: 0.5993, IoU.stove: 0.7902, IoU.palm: 0.4637, IoU.kitchen island: 0.5845, IoU.computer: 0.7464, IoU.swivel chair: 0.4413, IoU.boat: 0.5974, IoU.bar: 0.5719, IoU.arcade machine: 0.8328, IoU.hovel: 0.1808, IoU.bus: 0.9120, IoU.towel: 0.6715, IoU.light: 0.4961, IoU.truck: 0.4574, IoU.tower: 0.1260, IoU.chandelier: 0.6543, IoU.awning: 0.3438, IoU.streetlight: 0.2430, IoU.booth: 0.3366, IoU.television receiver: 0.7076, IoU.airplane: 0.5888, IoU.dirt track: 0.0756, IoU.apparel: 0.5717, IoU.pole: 0.2046, IoU.land: 0.0375, IoU.bannister: 0.1851, IoU.escalator: 0.5170, IoU.ottoman: 0.5205, IoU.bottle: 0.2386, IoU.buffet: 0.5204, IoU.poster: 0.2956, IoU.stage: 0.1216, IoU.van: 0.4568, IoU.ship: 0.0028, IoU.fountain: 0.3913, IoU.conveyer belt: 0.7921, IoU.canopy: 0.5210, IoU.washer: 0.8166, IoU.plaything: 0.2909, IoU.swimming pool: 0.6090, IoU.stool: 0.4813, IoU.barrel: 0.4869, IoU.basket: 0.3947, IoU.waterfall: 0.5218, IoU.tent: 0.9469, IoU.bag: 0.2325, IoU.minibike: 0.7136, IoU.cradle: 0.8106, IoU.oven: 0.6255, IoU.ball: 0.5642, IoU.food: 0.6407, IoU.step: 0.1785, IoU.tank: 0.5215, IoU.trade name: 0.3146, IoU.microwave: 0.8595, IoU.pot: 0.5204, IoU.animal: 0.6926, IoU.bicycle: 0.5952, IoU.lake: 0.5476, IoU.dishwasher: 0.7340, IoU.screen: 0.4986, IoU.blanket: 0.1361, IoU.sculpture: 0.6905, IoU.hood: 0.5899, IoU.sconce: 0.5333, IoU.vase: 0.4136, IoU.traffic light: 0.3204, IoU.tray: 0.0923, IoU.ashcan: 0.5009, IoU.fan: 0.6090, IoU.pier: 0.3845, IoU.crt screen: 0.0170, IoU.plate: 0.5747, IoU.monitor: 0.2609, IoU.bulletin board: 0.5823, IoU.shower: 0.0092, IoU.radiator: 0.5776, IoU.glass: 0.2017, IoU.clock: 0.3063, IoU.flag: 0.6765, Acc.wall: 0.8709, Acc.building: 0.9341, Acc.sky: 0.9780, Acc.floor: 0.9091, Acc.tree: 0.8551, Acc.ceiling: 0.9426, Acc.road: 0.9054, Acc.bed : 0.9687, Acc.windowpane: 0.7940, Acc.grass: 0.8862, Acc.cabinet: 0.7882, Acc.sidewalk: 0.8029, Acc.person: 0.9383, Acc.earth: 0.4322, Acc.door: 0.7103, Acc.table: 0.7714, Acc.mountain: 0.7695, Acc.plant: 0.6857, Acc.curtain: 0.8902, Acc.chair: 0.7226, Acc.car: 0.9377, Acc.water: 0.6962, Acc.painting: 0.8959, Acc.sofa: 0.8776, Acc.shelf: 0.6328, Acc.house: 0.3734, Acc.sea: 0.8598, Acc.mirror: 0.8062, Acc.rug: 0.7568, Acc.field: 0.6815, Acc.armchair: 0.7147, Acc.seat: 0.8956, Acc.fence: 0.6466, Acc.desk: 0.8123, Acc.rock: 0.5719, Acc.wardrobe: 0.6522, Acc.lamp: 0.8249, Acc.bathtub: 0.8862, Acc.railing: 0.5621, Acc.cushion: 0.7261, Acc.base: 0.4827, Acc.box: 0.4233, Acc.column: 0.6822, Acc.signboard: 0.5394, Acc.chest of drawers: 0.6272, Acc.counter: 0.6406, Acc.sand: 0.5239, Acc.sink: 0.8460, Acc.skyscraper: 0.5198, Acc.fireplace: 0.9123, Acc.refrigerator: 0.9024, Acc.grandstand: 0.7666, Acc.path: 0.2747, Acc.stairs: 0.2940, Acc.runway: 0.9226, Acc.case: 0.7011, Acc.pool table: 0.9813, Acc.pillow: 0.6960, Acc.screen door: 0.6696, Acc.stairway: 0.5474, Acc.river: 0.3122, Acc.bridge: 0.8941, Acc.bookcase: 0.5536, Acc.blind: 0.5126, Acc.coffee table: 0.8412, Acc.toilet: 0.9358, Acc.flower: 0.5697, Acc.book: 0.7027, Acc.hill: 0.1327, Acc.bench: 0.5931, Acc.countertop: 0.7452, Acc.stove: 0.8819, Acc.palm: 0.7239, Acc.kitchen island: 0.7294, Acc.computer: 0.8918, Acc.swivel chair: 0.7906, Acc.boat: 0.9166, Acc.bar: 0.5992, Acc.arcade machine: 0.8890, Acc.hovel: 0.1950, Acc.bus: 0.9553, Acc.towel: 0.8935, Acc.light: 0.6180, Acc.truck: 0.5698, Acc.tower: 0.2357, Acc.chandelier: 0.7858, Acc.awning: 0.4431, Acc.streetlight: 0.3326, Acc.booth: 0.3485, Acc.television receiver: 0.8656, Acc.airplane: 0.6475, Acc.dirt track: 0.2626, Acc.apparel: 0.8506, Acc.pole: 0.2541, Acc.land: 0.0642, Acc.bannister: 0.2619, Acc.escalator: 0.6469, Acc.ottoman: 0.6968, Acc.bottle: 0.3280, Acc.buffet: 0.7036, Acc.poster: 0.4323, Acc.stage: 0.2203, Acc.van: 0.5725, Acc.ship: 0.0030, Acc.fountain: 0.4000, Acc.conveyer belt: 0.9690, Acc.canopy: 0.5916, Acc.washer: 0.8596, Acc.plaything: 0.4649, Acc.swimming pool: 0.9110, Acc.stool: 0.6592, Acc.barrel: 0.6268, Acc.basket: 0.5846, Acc.waterfall: 0.7661, Acc.tent: 0.9803, Acc.bag: 0.2872, Acc.minibike: 0.8532, Acc.cradle: 0.9599, Acc.oven: 0.7965, Acc.ball: 0.6223, Acc.food: 0.7262, Acc.step: 0.2108, Acc.tank: 0.6438, Acc.trade name: 0.3886, Acc.microwave: 0.9395, Acc.pot: 0.6065, Acc.animal: 0.7204, Acc.bicycle: 0.7525, Acc.lake: 0.6839, Acc.dishwasher: 0.8015, Acc.screen: 0.7354, Acc.blanket: 0.1509, Acc.sculpture: 0.7926, Acc.hood: 0.7068, Acc.sconce: 0.6833, Acc.vase: 0.5524, Acc.traffic light: 0.4878, Acc.tray: 0.1565, Acc.ashcan: 0.6762, Acc.fan: 0.7509, Acc.pier: 0.4527, Acc.crt screen: 0.0431, Acc.plate: 0.7694, Acc.monitor: 0.2891, Acc.bulletin board: 0.7411, Acc.shower: 0.0092, Acc.radiator: 0.6693, Acc.glass: 0.2303, Acc.clock: 0.3628, Acc.flag: 0.7384 2023-11-02 22:09:20,617 - mmseg - INFO - Iter [9050/20000] lr: 1.774e-06, eta: 4:04:50, time: 2.397, data_time: 1.193, memory: 38534, decode.loss_ce: 0.2404, decode.acc_seg: 90.5575, loss: 0.2404 2023-11-02 22:10:21,156 - mmseg - INFO - Iter [9100/20000] lr: 1.766e-06, eta: 4:03:35, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2284, decode.acc_seg: 91.1273, loss: 0.2284 2023-11-02 22:11:21,659 - mmseg - INFO - Iter [9150/20000] lr: 1.758e-06, eta: 4:02:20, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2230, decode.acc_seg: 90.8144, loss: 0.2230 2023-11-02 22:12:24,595 - mmseg - INFO - Iter [9200/20000] lr: 1.750e-06, eta: 4:01:09, time: 1.259, data_time: 0.055, memory: 38534, decode.loss_ce: 0.2128, decode.acc_seg: 91.3387, loss: 0.2128 2023-11-02 22:13:25,087 - mmseg - INFO - Iter [9250/20000] lr: 1.742e-06, eta: 3:59:54, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2228, decode.acc_seg: 90.9610, loss: 0.2228 2023-11-02 22:14:25,564 - mmseg - INFO - Iter [9300/20000] lr: 1.733e-06, eta: 3:58:40, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2260, decode.acc_seg: 90.8853, loss: 0.2260 2023-11-02 22:15:26,086 - mmseg - INFO - Iter [9350/20000] lr: 1.725e-06, eta: 3:57:26, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2225, decode.acc_seg: 91.0475, loss: 0.2225 2023-11-02 22:16:26,601 - mmseg - INFO - Iter [9400/20000] lr: 1.717e-06, eta: 3:56:11, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1986, decode.acc_seg: 91.9632, loss: 0.1986 2023-11-02 22:17:27,122 - mmseg - INFO - Iter [9450/20000] lr: 1.709e-06, eta: 3:54:58, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2168, decode.acc_seg: 91.1800, loss: 0.2168 2023-11-02 22:18:29,902 - mmseg - INFO - Iter [9500/20000] lr: 1.701e-06, eta: 3:53:46, time: 1.256, data_time: 0.052, memory: 38534, decode.loss_ce: 0.2109, decode.acc_seg: 91.6784, loss: 0.2109 2023-11-02 22:19:30,425 - mmseg - INFO - Iter [9550/20000] lr: 1.693e-06, eta: 3:52:33, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2074, decode.acc_seg: 91.7490, loss: 0.2074 2023-11-02 22:20:30,952 - mmseg - INFO - Iter [9600/20000] lr: 1.685e-06, eta: 3:51:19, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2142, decode.acc_seg: 91.1363, loss: 0.2142 2023-11-02 22:21:31,445 - mmseg - INFO - Iter [9650/20000] lr: 1.677e-06, eta: 3:50:06, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2207, decode.acc_seg: 91.1977, loss: 0.2207 2023-11-02 22:22:31,967 - mmseg - INFO - Iter [9700/20000] lr: 1.669e-06, eta: 3:48:52, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2149, decode.acc_seg: 91.2772, loss: 0.2149 2023-11-02 22:23:32,489 - mmseg - INFO - Iter [9750/20000] lr: 1.661e-06, eta: 3:47:39, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2149, decode.acc_seg: 91.2819, loss: 0.2149 2023-11-02 22:24:35,500 - mmseg - INFO - Iter [9800/20000] lr: 1.652e-06, eta: 3:46:29, time: 1.260, data_time: 0.054, memory: 38534, decode.loss_ce: 0.2066, decode.acc_seg: 91.8895, loss: 0.2066 2023-11-02 22:25:36,019 - mmseg - INFO - Iter [9850/20000] lr: 1.644e-06, eta: 3:45:16, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2003, decode.acc_seg: 91.9759, loss: 0.2003 2023-11-02 22:26:36,555 - mmseg - INFO - Iter [9900/20000] lr: 1.636e-06, eta: 3:44:03, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2056, decode.acc_seg: 91.3130, loss: 0.2056 2023-11-02 22:27:37,096 - mmseg - INFO - Iter [9950/20000] lr: 1.628e-06, eta: 3:42:51, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2057, decode.acc_seg: 91.7708, loss: 0.2057 2023-11-02 22:28:37,596 - mmseg - INFO - Saving checkpoint at 10000 iterations 2023-11-02 22:29:37,383 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 22:29:37,383 - mmseg - INFO - Iter [10000/20000] lr: 1.620e-06, eta: 3:42:38, time: 2.406, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2048, decode.acc_seg: 91.6766, loss: 0.2048 2023-11-02 22:30:38,235 - mmseg - INFO - per class results: 2023-11-02 22:30:38,240 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 79.44 | 88.36 | | building | 83.04 | 92.93 | | sky | 93.98 | 97.03 | | floor | 81.99 | 90.17 | | tree | 74.18 | 87.57 | | ceiling | 85.08 | 92.01 | | road | 83.08 | 90.86 | | bed | 91.43 | 96.05 | | windowpane | 63.25 | 81.91 | | grass | 69.72 | 85.19 | | cabinet | 62.45 | 72.66 | | sidewalk | 66.15 | 82.04 | | person | 81.97 | 91.65 | | earth | 30.35 | 37.61 | | door | 57.06 | 76.57 | | table | 66.0 | 76.34 | | mountain | 58.31 | 78.17 | | plant | 48.93 | 63.57 | | curtain | 77.98 | 87.35 | | chair | 59.01 | 70.67 | | car | 84.55 | 93.02 | | water | 52.88 | 66.9 | | painting | 73.11 | 87.87 | | sofa | 78.53 | 89.42 | | shelf | 43.89 | 58.45 | | house | 40.23 | 50.25 | | sea | 57.05 | 77.93 | | mirror | 74.34 | 87.61 | | rug | 65.26 | 78.59 | | field | 33.96 | 63.58 | | armchair | 55.88 | 72.51 | | seat | 63.36 | 89.92 | | fence | 46.25 | 61.94 | | desk | 50.87 | 81.12 | | rock | 37.87 | 50.64 | | wardrobe | 50.29 | 72.59 | | lamp | 66.96 | 81.42 | | bathtub | 85.95 | 89.98 | | railing | 40.44 | 58.63 | | cushion | 61.1 | 78.75 | | base | 37.52 | 59.53 | | box | 27.77 | 34.71 | | column | 52.7 | 69.27 | | signboard | 35.61 | 56.69 | | chest of drawers | 39.82 | 58.56 | | counter | 53.2 | 74.91 | | sand | 38.07 | 51.51 | | sink | 76.32 | 83.84 | | skyscraper | 48.72 | 61.44 | | fireplace | 69.46 | 87.46 | | refrigerator | 78.58 | 90.51 | | grandstand | 54.66 | 76.49 | | path | 17.88 | 26.99 | | stairs | 26.88 | 31.34 | | runway | 69.12 | 87.41 | | case | 57.81 | 68.77 | | pool table | 93.12 | 98.0 | | pillow | 60.08 | 69.79 | | screen door | 70.4 | 75.96 | | stairway | 43.12 | 60.25 | | river | 14.58 | 31.56 | | bridge | 71.79 | 86.49 | | bookcase | 32.57 | 46.17 | | blind | 33.98 | 35.71 | | coffee table | 63.1 | 85.65 | | toilet | 89.08 | 93.68 | | flower | 41.07 | 53.7 | | book | 49.19 | 65.93 | | hill | 7.9 | 12.29 | | bench | 51.97 | 58.52 | | countertop | 58.53 | 71.54 | | stove | 80.37 | 90.57 | | palm | 47.24 | 82.41 | | kitchen island | 51.07 | 61.38 | | computer | 75.91 | 89.52 | | swivel chair | 44.19 | 69.4 | | boat | 59.55 | 91.16 | | bar | 58.75 | 64.86 | | arcade machine | 78.33 | 82.53 | | hovel | 22.73 | 25.31 | | bus | 89.39 | 95.94 | | towel | 69.38 | 85.68 | | light | 48.86 | 60.8 | | truck | 44.75 | 62.63 | | tower | 13.18 | 25.6 | | chandelier | 65.09 | 78.08 | | awning | 32.47 | 40.55 | | streetlight | 26.3 | 33.33 | | booth | 35.01 | 36.37 | | television receiver | 74.04 | 87.45 | | airplane | 59.16 | 66.22 | | dirt track | 17.03 | 31.14 | | apparel | 58.64 | 83.74 | | pole | 31.3 | 41.6 | | land | 4.24 | 6.95 | | bannister | 19.0 | 26.08 | | escalator | 59.7 | 73.63 | | ottoman | 45.4 | 65.19 | | bottle | 23.07 | 29.32 | | buffet | 54.76 | 72.42 | | poster | 24.21 | 31.03 | | stage | 13.24 | 23.62 | | van | 45.39 | 61.83 | | ship | 39.49 | 43.96 | | fountain | 33.94 | 35.21 | | conveyer belt | 76.84 | 95.04 | | canopy | 54.7 | 68.3 | | washer | 82.25 | 85.86 | | plaything | 30.13 | 46.05 | | swimming pool | 59.78 | 85.81 | | stool | 42.46 | 72.82 | | barrel | 50.42 | 66.04 | | basket | 41.65 | 59.54 | | waterfall | 53.18 | 63.55 | | tent | 92.85 | 98.51 | | bag | 22.84 | 28.24 | | minibike | 71.83 | 85.76 | | cradle | 81.09 | 97.26 | | oven | 66.08 | 76.4 | | ball | 14.5 | 14.8 | | food | 63.7 | 71.87 | | step | 18.2 | 24.84 | | tank | 53.57 | 64.89 | | trade name | 22.69 | 26.31 | | microwave | 86.43 | 92.83 | | pot | 51.12 | 57.12 | | animal | 70.62 | 74.7 | | bicycle | 58.25 | 70.9 | | lake | 54.5 | 69.99 | | dishwasher | 71.58 | 82.26 | | screen | 53.92 | 78.63 | | blanket | 20.45 | 22.99 | | sculpture | 61.83 | 70.03 | | hood | 60.25 | 75.55 | | sconce | 52.63 | 68.04 | | vase | 42.04 | 57.55 | | traffic light | 34.69 | 55.16 | | tray | 8.99 | 15.02 | | ashcan | 48.85 | 66.81 | | fan | 59.57 | 71.42 | | pier | 38.65 | 44.55 | | crt screen | 2.94 | 5.64 | | plate | 57.91 | 73.04 | | monitor | 42.7 | 50.37 | | bulletin board | 59.65 | 69.46 | | shower | 2.82 | 5.06 | | radiator | 58.77 | 67.78 | | glass | 18.14 | 20.02 | | clock | 31.27 | 38.58 | | flag | 68.97 | 76.53 | +---------------------+-------+-------+ 2023-11-02 22:30:38,241 - mmseg - INFO - Summary: 2023-11-02 22:30:38,241 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 83.98 | 52.68 | 65.08 | +-------+-------+-------+ 2023-11-02 22:30:38,241 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 22:30:38,242 - mmseg - INFO - Iter(val) [250] aAcc: 0.8398, mIoU: 0.5268, mAcc: 0.6508, IoU.wall: 0.7944, IoU.building: 0.8304, IoU.sky: 0.9398, IoU.floor: 0.8199, IoU.tree: 0.7418, IoU.ceiling: 0.8508, IoU.road: 0.8308, IoU.bed : 0.9143, IoU.windowpane: 0.6325, IoU.grass: 0.6972, IoU.cabinet: 0.6245, IoU.sidewalk: 0.6615, IoU.person: 0.8197, IoU.earth: 0.3035, IoU.door: 0.5706, IoU.table: 0.6600, IoU.mountain: 0.5831, IoU.plant: 0.4893, IoU.curtain: 0.7798, IoU.chair: 0.5901, IoU.car: 0.8455, IoU.water: 0.5288, IoU.painting: 0.7311, IoU.sofa: 0.7853, IoU.shelf: 0.4389, IoU.house: 0.4023, IoU.sea: 0.5705, IoU.mirror: 0.7434, IoU.rug: 0.6526, IoU.field: 0.3396, IoU.armchair: 0.5588, IoU.seat: 0.6336, IoU.fence: 0.4625, IoU.desk: 0.5087, IoU.rock: 0.3787, IoU.wardrobe: 0.5029, IoU.lamp: 0.6696, IoU.bathtub: 0.8595, IoU.railing: 0.4044, IoU.cushion: 0.6110, IoU.base: 0.3752, IoU.box: 0.2777, IoU.column: 0.5270, IoU.signboard: 0.3561, IoU.chest of drawers: 0.3982, IoU.counter: 0.5320, IoU.sand: 0.3807, IoU.sink: 0.7632, IoU.skyscraper: 0.4872, IoU.fireplace: 0.6946, IoU.refrigerator: 0.7858, IoU.grandstand: 0.5466, IoU.path: 0.1788, IoU.stairs: 0.2688, IoU.runway: 0.6912, IoU.case: 0.5781, IoU.pool table: 0.9312, IoU.pillow: 0.6008, IoU.screen door: 0.7040, IoU.stairway: 0.4312, IoU.river: 0.1458, IoU.bridge: 0.7179, IoU.bookcase: 0.3257, IoU.blind: 0.3398, IoU.coffee table: 0.6310, IoU.toilet: 0.8908, IoU.flower: 0.4107, IoU.book: 0.4919, IoU.hill: 0.0790, IoU.bench: 0.5197, IoU.countertop: 0.5853, IoU.stove: 0.8037, IoU.palm: 0.4724, IoU.kitchen island: 0.5107, IoU.computer: 0.7591, IoU.swivel chair: 0.4419, IoU.boat: 0.5955, IoU.bar: 0.5875, IoU.arcade machine: 0.7833, IoU.hovel: 0.2273, IoU.bus: 0.8939, IoU.towel: 0.6938, IoU.light: 0.4886, IoU.truck: 0.4475, IoU.tower: 0.1318, IoU.chandelier: 0.6509, IoU.awning: 0.3247, IoU.streetlight: 0.2630, IoU.booth: 0.3501, IoU.television receiver: 0.7404, IoU.airplane: 0.5916, IoU.dirt track: 0.1703, IoU.apparel: 0.5864, IoU.pole: 0.3130, IoU.land: 0.0424, IoU.bannister: 0.1900, IoU.escalator: 0.5970, IoU.ottoman: 0.4540, IoU.bottle: 0.2307, IoU.buffet: 0.5476, IoU.poster: 0.2421, IoU.stage: 0.1324, IoU.van: 0.4539, IoU.ship: 0.3949, IoU.fountain: 0.3394, IoU.conveyer belt: 0.7684, IoU.canopy: 0.5470, IoU.washer: 0.8225, IoU.plaything: 0.3013, IoU.swimming pool: 0.5978, IoU.stool: 0.4246, IoU.barrel: 0.5042, IoU.basket: 0.4165, IoU.waterfall: 0.5318, IoU.tent: 0.9285, IoU.bag: 0.2284, IoU.minibike: 0.7183, IoU.cradle: 0.8109, IoU.oven: 0.6608, IoU.ball: 0.1450, IoU.food: 0.6370, IoU.step: 0.1820, IoU.tank: 0.5357, IoU.trade name: 0.2269, IoU.microwave: 0.8643, IoU.pot: 0.5112, IoU.animal: 0.7062, IoU.bicycle: 0.5825, IoU.lake: 0.5450, IoU.dishwasher: 0.7158, IoU.screen: 0.5392, IoU.blanket: 0.2045, IoU.sculpture: 0.6183, IoU.hood: 0.6025, IoU.sconce: 0.5263, IoU.vase: 0.4204, IoU.traffic light: 0.3469, IoU.tray: 0.0899, IoU.ashcan: 0.4885, IoU.fan: 0.5957, IoU.pier: 0.3865, IoU.crt screen: 0.0294, IoU.plate: 0.5791, IoU.monitor: 0.4270, IoU.bulletin board: 0.5965, IoU.shower: 0.0282, IoU.radiator: 0.5877, IoU.glass: 0.1814, IoU.clock: 0.3127, IoU.flag: 0.6897, Acc.wall: 0.8836, Acc.building: 0.9293, Acc.sky: 0.9703, Acc.floor: 0.9017, Acc.tree: 0.8757, Acc.ceiling: 0.9201, Acc.road: 0.9086, Acc.bed : 0.9605, Acc.windowpane: 0.8191, Acc.grass: 0.8519, Acc.cabinet: 0.7266, Acc.sidewalk: 0.8204, Acc.person: 0.9165, Acc.earth: 0.3761, Acc.door: 0.7657, Acc.table: 0.7634, Acc.mountain: 0.7817, Acc.plant: 0.6357, Acc.curtain: 0.8735, Acc.chair: 0.7067, Acc.car: 0.9302, Acc.water: 0.6690, Acc.painting: 0.8787, Acc.sofa: 0.8942, Acc.shelf: 0.5845, Acc.house: 0.5025, Acc.sea: 0.7793, Acc.mirror: 0.8761, Acc.rug: 0.7859, Acc.field: 0.6358, Acc.armchair: 0.7251, Acc.seat: 0.8992, Acc.fence: 0.6194, Acc.desk: 0.8112, Acc.rock: 0.5064, Acc.wardrobe: 0.7259, Acc.lamp: 0.8142, Acc.bathtub: 0.8998, Acc.railing: 0.5863, Acc.cushion: 0.7875, Acc.base: 0.5953, Acc.box: 0.3471, Acc.column: 0.6927, Acc.signboard: 0.5669, Acc.chest of drawers: 0.5856, Acc.counter: 0.7491, Acc.sand: 0.5151, Acc.sink: 0.8384, Acc.skyscraper: 0.6144, Acc.fireplace: 0.8746, Acc.refrigerator: 0.9051, Acc.grandstand: 0.7649, Acc.path: 0.2699, Acc.stairs: 0.3134, Acc.runway: 0.8741, Acc.case: 0.6877, Acc.pool table: 0.9800, Acc.pillow: 0.6979, Acc.screen door: 0.7596, Acc.stairway: 0.6025, Acc.river: 0.3156, Acc.bridge: 0.8649, Acc.bookcase: 0.4617, Acc.blind: 0.3571, Acc.coffee table: 0.8565, Acc.toilet: 0.9368, Acc.flower: 0.5370, Acc.book: 0.6593, Acc.hill: 0.1229, Acc.bench: 0.5852, Acc.countertop: 0.7154, Acc.stove: 0.9057, Acc.palm: 0.8241, Acc.kitchen island: 0.6138, Acc.computer: 0.8952, Acc.swivel chair: 0.6940, Acc.boat: 0.9116, Acc.bar: 0.6486, Acc.arcade machine: 0.8253, Acc.hovel: 0.2531, Acc.bus: 0.9594, Acc.towel: 0.8568, Acc.light: 0.6080, Acc.truck: 0.6263, Acc.tower: 0.2560, Acc.chandelier: 0.7808, Acc.awning: 0.4055, Acc.streetlight: 0.3333, Acc.booth: 0.3637, Acc.television receiver: 0.8745, Acc.airplane: 0.6622, Acc.dirt track: 0.3114, Acc.apparel: 0.8374, Acc.pole: 0.4160, Acc.land: 0.0695, Acc.bannister: 0.2608, Acc.escalator: 0.7363, Acc.ottoman: 0.6519, Acc.bottle: 0.2932, Acc.buffet: 0.7242, Acc.poster: 0.3103, Acc.stage: 0.2362, Acc.van: 0.6183, Acc.ship: 0.4396, Acc.fountain: 0.3521, Acc.conveyer belt: 0.9504, Acc.canopy: 0.6830, Acc.washer: 0.8586, Acc.plaything: 0.4605, Acc.swimming pool: 0.8581, Acc.stool: 0.7282, Acc.barrel: 0.6604, Acc.basket: 0.5954, Acc.waterfall: 0.6355, Acc.tent: 0.9851, Acc.bag: 0.2824, Acc.minibike: 0.8576, Acc.cradle: 0.9726, Acc.oven: 0.7640, Acc.ball: 0.1480, Acc.food: 0.7187, Acc.step: 0.2484, Acc.tank: 0.6489, Acc.trade name: 0.2631, Acc.microwave: 0.9283, Acc.pot: 0.5712, Acc.animal: 0.7470, Acc.bicycle: 0.7090, Acc.lake: 0.6999, Acc.dishwasher: 0.8226, Acc.screen: 0.7863, Acc.blanket: 0.2299, Acc.sculpture: 0.7003, Acc.hood: 0.7555, Acc.sconce: 0.6804, Acc.vase: 0.5755, Acc.traffic light: 0.5516, Acc.tray: 0.1502, Acc.ashcan: 0.6681, Acc.fan: 0.7142, Acc.pier: 0.4455, Acc.crt screen: 0.0564, Acc.plate: 0.7304, Acc.monitor: 0.5037, Acc.bulletin board: 0.6946, Acc.shower: 0.0506, Acc.radiator: 0.6778, Acc.glass: 0.2002, Acc.clock: 0.3858, Acc.flag: 0.7653 2023-11-02 22:31:38,807 - mmseg - INFO - Iter [10050/20000] lr: 1.612e-06, eta: 3:42:25, time: 2.428, data_time: 1.225, memory: 38534, decode.loss_ce: 0.2134, decode.acc_seg: 91.5215, loss: 0.2134 2023-11-02 22:32:39,291 - mmseg - INFO - Iter [10100/20000] lr: 1.604e-06, eta: 3:41:12, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2060, decode.acc_seg: 91.5425, loss: 0.2060 2023-11-02 22:33:42,504 - mmseg - INFO - Iter [10150/20000] lr: 1.596e-06, eta: 3:40:01, time: 1.264, data_time: 0.053, memory: 38534, decode.loss_ce: 0.1922, decode.acc_seg: 92.1946, loss: 0.1922 2023-11-02 22:34:43,015 - mmseg - INFO - Iter [10200/20000] lr: 1.588e-06, eta: 3:38:48, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2096, decode.acc_seg: 91.5106, loss: 0.2096 2023-11-02 22:35:43,496 - mmseg - INFO - Iter [10250/20000] lr: 1.580e-06, eta: 3:37:34, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2041, decode.acc_seg: 91.6590, loss: 0.2041 2023-11-02 22:36:44,006 - mmseg - INFO - Iter [10300/20000] lr: 1.571e-06, eta: 3:36:21, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2096, decode.acc_seg: 91.6913, loss: 0.2096 2023-11-02 22:37:44,460 - mmseg - INFO - Iter [10350/20000] lr: 1.563e-06, eta: 3:35:09, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1904, decode.acc_seg: 91.9142, loss: 0.1904 2023-11-02 22:38:44,956 - mmseg - INFO - Iter [10400/20000] lr: 1.555e-06, eta: 3:33:56, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2152, decode.acc_seg: 91.4944, loss: 0.2152 2023-11-02 22:39:47,816 - mmseg - INFO - Iter [10450/20000] lr: 1.547e-06, eta: 3:32:45, time: 1.257, data_time: 0.052, memory: 38534, decode.loss_ce: 0.2079, decode.acc_seg: 91.8120, loss: 0.2079 2023-11-02 22:40:48,351 - mmseg - INFO - Iter [10500/20000] lr: 1.539e-06, eta: 3:31:33, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1956, decode.acc_seg: 92.1493, loss: 0.1956 2023-11-02 22:41:48,882 - mmseg - INFO - Iter [10550/20000] lr: 1.531e-06, eta: 3:30:20, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1951, decode.acc_seg: 92.1029, loss: 0.1951 2023-11-02 22:42:49,361 - mmseg - INFO - Iter [10600/20000] lr: 1.523e-06, eta: 3:29:08, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2077, decode.acc_seg: 91.6601, loss: 0.2077 2023-11-02 22:43:49,800 - mmseg - INFO - Iter [10650/20000] lr: 1.515e-06, eta: 3:27:56, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2071, decode.acc_seg: 91.7066, loss: 0.2071 2023-11-02 22:44:50,336 - mmseg - INFO - Iter [10700/20000] lr: 1.507e-06, eta: 3:26:44, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2000, decode.acc_seg: 91.7659, loss: 0.2000 2023-11-02 22:45:53,072 - mmseg - INFO - Iter [10750/20000] lr: 1.499e-06, eta: 3:25:33, time: 1.255, data_time: 0.051, memory: 38534, decode.loss_ce: 0.1962, decode.acc_seg: 92.3179, loss: 0.1962 2023-11-02 22:46:53,515 - mmseg - INFO - Iter [10800/20000] lr: 1.490e-06, eta: 3:24:21, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1942, decode.acc_seg: 92.0020, loss: 0.1942 2023-11-02 22:47:53,962 - mmseg - INFO - Iter [10850/20000] lr: 1.482e-06, eta: 3:23:10, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2045, decode.acc_seg: 92.0035, loss: 0.2045 2023-11-02 22:48:54,427 - mmseg - INFO - Iter [10900/20000] lr: 1.474e-06, eta: 3:21:58, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2283, decode.acc_seg: 91.0763, loss: 0.2283 2023-11-02 22:49:54,921 - mmseg - INFO - Iter [10950/20000] lr: 1.466e-06, eta: 3:20:46, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2040, decode.acc_seg: 91.9354, loss: 0.2040 2023-11-02 22:50:55,392 - mmseg - INFO - Saving checkpoint at 11000 iterations 2023-11-02 22:51:50,673 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 22:51:50,673 - mmseg - INFO - Iter [11000/20000] lr: 1.458e-06, eta: 3:20:20, time: 2.315, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1993, decode.acc_seg: 91.9624, loss: 0.1993 2023-11-02 22:52:53,953 - mmseg - INFO - per class results: 2023-11-02 22:52:53,958 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 79.92 | 88.43 | | building | 83.05 | 93.82 | | sky | 93.68 | 97.12 | | floor | 82.57 | 90.48 | | tree | 73.79 | 86.84 | | ceiling | 84.92 | 92.54 | | road | 83.01 | 91.44 | | bed | 91.32 | 96.58 | | windowpane | 64.38 | 82.49 | | grass | 69.49 | 85.84 | | cabinet | 65.0 | 76.42 | | sidewalk | 66.65 | 81.73 | | person | 81.73 | 90.73 | | earth | 33.38 | 42.11 | | door | 56.62 | 73.59 | | table | 65.86 | 77.91 | | mountain | 59.19 | 75.56 | | plant | 52.59 | 69.24 | | curtain | 77.55 | 86.99 | | chair | 57.87 | 69.86 | | car | 84.87 | 92.25 | | water | 57.89 | 74.95 | | painting | 73.62 | 87.99 | | sofa | 76.84 | 83.42 | | shelf | 41.94 | 59.73 | | house | 36.5 | 43.79 | | sea | 58.71 | 76.13 | | mirror | 74.63 | 84.4 | | rug | 65.75 | 75.86 | | field | 35.17 | 59.17 | | armchair | 54.29 | 79.64 | | seat | 63.79 | 85.05 | | fence | 47.02 | 65.62 | | desk | 52.04 | 78.79 | | rock | 43.06 | 57.59 | | wardrobe | 51.66 | 68.02 | | lamp | 65.27 | 74.97 | | bathtub | 87.23 | 91.01 | | railing | 43.55 | 64.68 | | cushion | 60.13 | 78.5 | | base | 31.06 | 37.8 | | box | 31.87 | 40.44 | | column | 50.8 | 60.69 | | signboard | 36.85 | 51.71 | | chest of drawers | 40.85 | 49.34 | | counter | 56.12 | 76.2 | | sand | 37.74 | 48.85 | | sink | 76.08 | 82.89 | | skyscraper | 49.0 | 60.37 | | fireplace | 71.46 | 89.08 | | refrigerator | 78.95 | 90.82 | | grandstand | 60.23 | 78.55 | | path | 15.51 | 21.95 | | stairs | 31.1 | 36.74 | | runway | 64.53 | 82.43 | | case | 55.62 | 68.08 | | pool table | 93.55 | 97.13 | | pillow | 58.32 | 69.69 | | screen door | 73.99 | 79.7 | | stairway | 47.07 | 60.79 | | river | 22.62 | 37.57 | | bridge | 71.63 | 86.96 | | bookcase | 31.93 | 55.7 | | blind | 40.81 | 46.51 | | coffee table | 63.28 | 87.58 | | toilet | 88.56 | 93.31 | | flower | 40.16 | 55.15 | | book | 48.0 | 71.94 | | hill | 8.71 | 14.53 | | bench | 50.2 | 56.65 | | countertop | 60.67 | 77.4 | | stove | 80.9 | 90.98 | | palm | 47.07 | 83.77 | | kitchen island | 54.93 | 81.13 | | computer | 74.83 | 89.76 | | swivel chair | 42.12 | 69.37 | | boat | 37.41 | 89.91 | | bar | 54.74 | 57.44 | | arcade machine | 78.58 | 81.1 | | hovel | 17.79 | 20.29 | | bus | 89.16 | 95.68 | | towel | 70.3 | 82.12 | | light | 45.74 | 52.6 | | truck | 42.83 | 60.29 | | tower | 13.93 | 25.85 | | chandelier | 64.68 | 84.7 | | awning | 31.68 | 38.84 | | streetlight | 24.28 | 31.69 | | booth | 35.44 | 37.76 | | television receiver | 71.66 | 84.74 | | airplane | 58.79 | 65.52 | | dirt track | 25.01 | 34.31 | | apparel | 58.66 | 84.41 | | pole | 21.29 | 25.41 | | land | 3.48 | 5.54 | | bannister | 18.65 | 24.58 | | escalator | 56.03 | 73.86 | | ottoman | 48.52 | 61.92 | | bottle | 21.35 | 39.49 | | buffet | 56.13 | 72.28 | | poster | 27.03 | 33.97 | | stage | 11.09 | 18.8 | | van | 44.71 | 63.55 | | ship | 0.08 | 0.08 | | fountain | 30.08 | 31.02 | | conveyer belt | 74.54 | 96.0 | | canopy | 52.93 | 72.37 | | washer | 81.81 | 86.33 | | plaything | 30.77 | 42.68 | | swimming pool | 60.92 | 88.26 | | stool | 47.57 | 68.28 | | barrel | 51.92 | 64.93 | | basket | 40.42 | 58.45 | | waterfall | 51.61 | 63.03 | | tent | 95.55 | 98.05 | | bag | 22.99 | 28.77 | | minibike | 71.51 | 87.07 | | cradle | 83.64 | 95.97 | | oven | 63.71 | 71.93 | | ball | 53.79 | 58.26 | | food | 64.04 | 71.15 | | step | 17.55 | 23.29 | | tank | 53.3 | 62.6 | | trade name | 29.16 | 34.66 | | microwave | 87.01 | 93.46 | | pot | 53.55 | 62.58 | | animal | 69.95 | 72.75 | | bicycle | 60.22 | 81.24 | | lake | 61.01 | 68.52 | | dishwasher | 71.85 | 82.19 | | screen | 58.3 | 87.62 | | blanket | 22.96 | 25.91 | | sculpture | 60.85 | 69.55 | | hood | 61.0 | 72.17 | | sconce | 52.54 | 68.16 | | vase | 40.46 | 56.23 | | traffic light | 32.58 | 56.58 | | tray | 8.07 | 16.62 | | ashcan | 52.41 | 60.12 | | fan | 61.12 | 78.77 | | pier | 38.79 | 44.87 | | crt screen | 4.32 | 8.7 | | plate | 56.44 | 75.63 | | monitor | 30.15 | 32.24 | | bulletin board | 54.93 | 62.73 | | shower | 1.29 | 1.29 | | radiator | 57.84 | 69.55 | | glass | 16.17 | 17.22 | | clock | 31.31 | 37.48 | | flag | 68.6 | 75.69 | +---------------------+-------+-------+ 2023-11-02 22:52:53,958 - mmseg - INFO - Summary: 2023-11-02 22:52:53,958 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 84.22 | 52.69 | 64.94 | +-------+-------+-------+ 2023-11-02 22:52:53,959 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 22:52:53,960 - mmseg - INFO - Iter(val) [250] aAcc: 0.8422, mIoU: 0.5269, mAcc: 0.6494, IoU.wall: 0.7992, IoU.building: 0.8305, IoU.sky: 0.9368, IoU.floor: 0.8257, IoU.tree: 0.7379, IoU.ceiling: 0.8492, IoU.road: 0.8301, IoU.bed : 0.9132, IoU.windowpane: 0.6438, IoU.grass: 0.6949, IoU.cabinet: 0.6500, IoU.sidewalk: 0.6665, IoU.person: 0.8173, IoU.earth: 0.3338, IoU.door: 0.5662, IoU.table: 0.6586, IoU.mountain: 0.5919, IoU.plant: 0.5259, IoU.curtain: 0.7755, IoU.chair: 0.5787, IoU.car: 0.8487, IoU.water: 0.5789, IoU.painting: 0.7362, IoU.sofa: 0.7684, IoU.shelf: 0.4194, IoU.house: 0.3650, IoU.sea: 0.5871, IoU.mirror: 0.7463, IoU.rug: 0.6575, IoU.field: 0.3517, IoU.armchair: 0.5429, IoU.seat: 0.6379, IoU.fence: 0.4702, IoU.desk: 0.5204, IoU.rock: 0.4306, IoU.wardrobe: 0.5166, IoU.lamp: 0.6527, IoU.bathtub: 0.8723, IoU.railing: 0.4355, IoU.cushion: 0.6013, IoU.base: 0.3106, IoU.box: 0.3187, IoU.column: 0.5080, IoU.signboard: 0.3685, IoU.chest of drawers: 0.4085, IoU.counter: 0.5612, IoU.sand: 0.3774, IoU.sink: 0.7608, IoU.skyscraper: 0.4900, IoU.fireplace: 0.7146, IoU.refrigerator: 0.7895, IoU.grandstand: 0.6023, IoU.path: 0.1551, IoU.stairs: 0.3110, IoU.runway: 0.6453, IoU.case: 0.5562, IoU.pool table: 0.9355, IoU.pillow: 0.5832, IoU.screen door: 0.7399, IoU.stairway: 0.4707, IoU.river: 0.2262, IoU.bridge: 0.7163, IoU.bookcase: 0.3193, IoU.blind: 0.4081, IoU.coffee table: 0.6328, IoU.toilet: 0.8856, IoU.flower: 0.4016, IoU.book: 0.4800, IoU.hill: 0.0871, IoU.bench: 0.5020, IoU.countertop: 0.6067, IoU.stove: 0.8090, IoU.palm: 0.4707, IoU.kitchen island: 0.5493, IoU.computer: 0.7483, IoU.swivel chair: 0.4212, IoU.boat: 0.3741, IoU.bar: 0.5474, IoU.arcade machine: 0.7858, IoU.hovel: 0.1779, IoU.bus: 0.8916, IoU.towel: 0.7030, IoU.light: 0.4574, IoU.truck: 0.4283, IoU.tower: 0.1393, IoU.chandelier: 0.6468, IoU.awning: 0.3168, IoU.streetlight: 0.2428, IoU.booth: 0.3544, IoU.television receiver: 0.7166, IoU.airplane: 0.5879, IoU.dirt track: 0.2501, IoU.apparel: 0.5866, IoU.pole: 0.2129, IoU.land: 0.0348, IoU.bannister: 0.1865, IoU.escalator: 0.5603, IoU.ottoman: 0.4852, IoU.bottle: 0.2135, IoU.buffet: 0.5613, IoU.poster: 0.2703, IoU.stage: 0.1109, IoU.van: 0.4471, IoU.ship: 0.0008, IoU.fountain: 0.3008, IoU.conveyer belt: 0.7454, IoU.canopy: 0.5293, IoU.washer: 0.8181, IoU.plaything: 0.3077, IoU.swimming pool: 0.6092, IoU.stool: 0.4757, IoU.barrel: 0.5192, IoU.basket: 0.4042, IoU.waterfall: 0.5161, IoU.tent: 0.9555, IoU.bag: 0.2299, IoU.minibike: 0.7151, IoU.cradle: 0.8364, IoU.oven: 0.6371, IoU.ball: 0.5379, IoU.food: 0.6404, IoU.step: 0.1755, IoU.tank: 0.5330, IoU.trade name: 0.2916, IoU.microwave: 0.8701, IoU.pot: 0.5355, IoU.animal: 0.6995, IoU.bicycle: 0.6022, IoU.lake: 0.6101, IoU.dishwasher: 0.7185, IoU.screen: 0.5830, IoU.blanket: 0.2296, IoU.sculpture: 0.6085, IoU.hood: 0.6100, IoU.sconce: 0.5254, IoU.vase: 0.4046, IoU.traffic light: 0.3258, IoU.tray: 0.0807, IoU.ashcan: 0.5241, IoU.fan: 0.6112, IoU.pier: 0.3879, IoU.crt screen: 0.0432, IoU.plate: 0.5644, IoU.monitor: 0.3015, IoU.bulletin board: 0.5493, IoU.shower: 0.0129, IoU.radiator: 0.5784, IoU.glass: 0.1617, IoU.clock: 0.3131, IoU.flag: 0.6860, Acc.wall: 0.8843, Acc.building: 0.9382, Acc.sky: 0.9712, Acc.floor: 0.9048, Acc.tree: 0.8684, Acc.ceiling: 0.9254, Acc.road: 0.9144, Acc.bed : 0.9658, Acc.windowpane: 0.8249, Acc.grass: 0.8584, Acc.cabinet: 0.7642, Acc.sidewalk: 0.8173, Acc.person: 0.9073, Acc.earth: 0.4211, Acc.door: 0.7359, Acc.table: 0.7791, Acc.mountain: 0.7556, Acc.plant: 0.6924, Acc.curtain: 0.8699, Acc.chair: 0.6986, Acc.car: 0.9225, Acc.water: 0.7495, Acc.painting: 0.8799, Acc.sofa: 0.8342, Acc.shelf: 0.5973, Acc.house: 0.4379, Acc.sea: 0.7613, Acc.mirror: 0.8440, Acc.rug: 0.7586, Acc.field: 0.5917, Acc.armchair: 0.7964, Acc.seat: 0.8505, Acc.fence: 0.6562, Acc.desk: 0.7879, Acc.rock: 0.5759, Acc.wardrobe: 0.6802, Acc.lamp: 0.7497, Acc.bathtub: 0.9101, Acc.railing: 0.6468, Acc.cushion: 0.7850, Acc.base: 0.3780, Acc.box: 0.4044, Acc.column: 0.6069, Acc.signboard: 0.5171, Acc.chest of drawers: 0.4934, Acc.counter: 0.7620, Acc.sand: 0.4885, Acc.sink: 0.8289, Acc.skyscraper: 0.6037, Acc.fireplace: 0.8908, Acc.refrigerator: 0.9082, Acc.grandstand: 0.7855, Acc.path: 0.2195, Acc.stairs: 0.3674, Acc.runway: 0.8243, Acc.case: 0.6808, Acc.pool table: 0.9713, Acc.pillow: 0.6969, Acc.screen door: 0.7970, Acc.stairway: 0.6079, Acc.river: 0.3757, Acc.bridge: 0.8696, Acc.bookcase: 0.5570, Acc.blind: 0.4651, Acc.coffee table: 0.8758, Acc.toilet: 0.9331, Acc.flower: 0.5515, Acc.book: 0.7194, Acc.hill: 0.1453, Acc.bench: 0.5665, Acc.countertop: 0.7740, Acc.stove: 0.9098, Acc.palm: 0.8377, Acc.kitchen island: 0.8113, Acc.computer: 0.8976, Acc.swivel chair: 0.6937, Acc.boat: 0.8991, Acc.bar: 0.5744, Acc.arcade machine: 0.8110, Acc.hovel: 0.2029, Acc.bus: 0.9568, Acc.towel: 0.8212, Acc.light: 0.5260, Acc.truck: 0.6029, Acc.tower: 0.2585, Acc.chandelier: 0.8470, Acc.awning: 0.3884, Acc.streetlight: 0.3169, Acc.booth: 0.3776, Acc.television receiver: 0.8474, Acc.airplane: 0.6552, Acc.dirt track: 0.3431, Acc.apparel: 0.8441, Acc.pole: 0.2541, Acc.land: 0.0554, Acc.bannister: 0.2458, Acc.escalator: 0.7386, Acc.ottoman: 0.6192, Acc.bottle: 0.3949, Acc.buffet: 0.7228, Acc.poster: 0.3397, Acc.stage: 0.1880, Acc.van: 0.6355, Acc.ship: 0.0008, Acc.fountain: 0.3102, Acc.conveyer belt: 0.9600, Acc.canopy: 0.7237, Acc.washer: 0.8633, Acc.plaything: 0.4268, Acc.swimming pool: 0.8826, Acc.stool: 0.6828, Acc.barrel: 0.6493, Acc.basket: 0.5845, Acc.waterfall: 0.6303, Acc.tent: 0.9805, Acc.bag: 0.2877, Acc.minibike: 0.8707, Acc.cradle: 0.9597, Acc.oven: 0.7193, Acc.ball: 0.5826, Acc.food: 0.7115, Acc.step: 0.2329, Acc.tank: 0.6260, Acc.trade name: 0.3466, Acc.microwave: 0.9346, Acc.pot: 0.6258, Acc.animal: 0.7275, Acc.bicycle: 0.8124, Acc.lake: 0.6852, Acc.dishwasher: 0.8219, Acc.screen: 0.8762, Acc.blanket: 0.2591, Acc.sculpture: 0.6955, Acc.hood: 0.7217, Acc.sconce: 0.6816, Acc.vase: 0.5623, Acc.traffic light: 0.5658, Acc.tray: 0.1662, Acc.ashcan: 0.6012, Acc.fan: 0.7877, Acc.pier: 0.4487, Acc.crt screen: 0.0870, Acc.plate: 0.7563, Acc.monitor: 0.3224, Acc.bulletin board: 0.6273, Acc.shower: 0.0129, Acc.radiator: 0.6955, Acc.glass: 0.1722, Acc.clock: 0.3748, Acc.flag: 0.7569 2023-11-02 22:53:54,533 - mmseg - INFO - Iter [11050/20000] lr: 1.450e-06, eta: 3:19:59, time: 2.477, data_time: 1.273, memory: 38534, decode.loss_ce: 0.1950, decode.acc_seg: 92.1817, loss: 0.1950 2023-11-02 22:54:57,569 - mmseg - INFO - Iter [11100/20000] lr: 1.442e-06, eta: 3:18:49, time: 1.261, data_time: 0.057, memory: 38534, decode.loss_ce: 0.1936, decode.acc_seg: 92.1426, loss: 0.1936 2023-11-02 22:55:58,012 - mmseg - INFO - Iter [11150/20000] lr: 1.434e-06, eta: 3:17:37, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1882, decode.acc_seg: 92.3766, loss: 0.1882 2023-11-02 22:56:58,457 - mmseg - INFO - Iter [11200/20000] lr: 1.426e-06, eta: 3:16:25, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1855, decode.acc_seg: 92.5694, loss: 0.1855 2023-11-02 22:57:58,909 - mmseg - INFO - Iter [11250/20000] lr: 1.418e-06, eta: 3:15:13, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1975, decode.acc_seg: 91.9855, loss: 0.1975 2023-11-02 22:58:59,348 - mmseg - INFO - Iter [11300/20000] lr: 1.409e-06, eta: 3:14:01, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1931, decode.acc_seg: 92.0688, loss: 0.1931 2023-11-02 22:59:59,858 - mmseg - INFO - Iter [11350/20000] lr: 1.401e-06, eta: 3:12:49, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1861, decode.acc_seg: 92.1785, loss: 0.1861 2023-11-02 23:01:02,928 - mmseg - INFO - Iter [11400/20000] lr: 1.393e-06, eta: 3:11:39, time: 1.261, data_time: 0.058, memory: 38534, decode.loss_ce: 0.2061, decode.acc_seg: 91.6970, loss: 0.2061 2023-11-02 23:02:03,389 - mmseg - INFO - Iter [11450/20000] lr: 1.385e-06, eta: 3:10:28, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1933, decode.acc_seg: 92.2549, loss: 0.1933 2023-11-02 23:03:03,886 - mmseg - INFO - Iter [11500/20000] lr: 1.377e-06, eta: 3:09:16, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1800, decode.acc_seg: 92.5348, loss: 0.1800 2023-11-02 23:04:04,350 - mmseg - INFO - Iter [11550/20000] lr: 1.369e-06, eta: 3:08:05, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1950, decode.acc_seg: 91.9721, loss: 0.1950 2023-11-02 23:05:04,818 - mmseg - INFO - Iter [11600/20000] lr: 1.361e-06, eta: 3:06:53, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1955, decode.acc_seg: 91.9337, loss: 0.1955 2023-11-02 23:06:05,292 - mmseg - INFO - Iter [11650/20000] lr: 1.353e-06, eta: 3:05:42, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1864, decode.acc_seg: 92.5123, loss: 0.1864 2023-11-02 23:07:08,248 - mmseg - INFO - Iter [11700/20000] lr: 1.345e-06, eta: 3:04:33, time: 1.259, data_time: 0.056, memory: 38534, decode.loss_ce: 0.1936, decode.acc_seg: 92.1356, loss: 0.1936 2023-11-02 23:08:08,709 - mmseg - INFO - Iter [11750/20000] lr: 1.337e-06, eta: 3:03:22, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1919, decode.acc_seg: 92.3474, loss: 0.1919 2023-11-02 23:09:09,178 - mmseg - INFO - Iter [11800/20000] lr: 1.328e-06, eta: 3:02:11, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1907, decode.acc_seg: 92.2498, loss: 0.1907 2023-11-02 23:10:09,668 - mmseg - INFO - Iter [11850/20000] lr: 1.320e-06, eta: 3:01:00, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1882, decode.acc_seg: 92.2774, loss: 0.1882 2023-11-02 23:11:10,095 - mmseg - INFO - Iter [11900/20000] lr: 1.312e-06, eta: 2:59:49, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1832, decode.acc_seg: 92.4067, loss: 0.1832 2023-11-02 23:12:10,509 - mmseg - INFO - Iter [11950/20000] lr: 1.304e-06, eta: 2:58:38, time: 1.208, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1856, decode.acc_seg: 92.3162, loss: 0.1856 2023-11-02 23:13:10,960 - mmseg - INFO - Saving checkpoint at 12000 iterations 2023-11-02 23:14:08,874 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 23:14:08,874 - mmseg - INFO - Iter [12000/20000] lr: 1.296e-06, eta: 2:58:06, time: 2.367, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1902, decode.acc_seg: 92.4388, loss: 0.1902 2023-11-02 23:15:07,005 - mmseg - INFO - per class results: 2023-11-02 23:15:07,011 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 79.85 | 88.34 | | building | 83.17 | 91.97 | | sky | 93.77 | 96.3 | | floor | 82.32 | 90.1 | | tree | 73.73 | 91.52 | | ceiling | 85.11 | 92.24 | | road | 82.98 | 92.42 | | bed | 90.99 | 96.67 | | windowpane | 64.81 | 81.64 | | grass | 71.34 | 88.12 | | cabinet | 63.9 | 74.93 | | sidewalk | 66.33 | 79.07 | | person | 82.03 | 92.18 | | earth | 36.26 | 48.92 | | door | 55.91 | 75.73 | | table | 66.72 | 76.45 | | mountain | 58.76 | 79.27 | | plant | 51.02 | 61.89 | | curtain | 77.22 | 89.15 | | chair | 59.73 | 75.16 | | car | 84.65 | 93.03 | | water | 54.79 | 69.61 | | painting | 72.26 | 87.77 | | sofa | 79.14 | 89.01 | | shelf | 41.86 | 60.47 | | house | 39.49 | 50.81 | | sea | 63.61 | 89.61 | | mirror | 75.29 | 85.13 | | rug | 62.48 | 72.57 | | field | 35.1 | 52.65 | | armchair | 55.68 | 74.04 | | seat | 63.42 | 89.54 | | fence | 45.77 | 69.94 | | desk | 51.52 | 77.51 | | rock | 36.49 | 48.89 | | wardrobe | 52.85 | 73.09 | | lamp | 65.31 | 80.27 | | bathtub | 87.85 | 91.5 | | railing | 38.33 | 52.29 | | cushion | 59.67 | 76.54 | | base | 34.76 | 50.22 | | box | 31.21 | 46.37 | | column | 47.86 | 57.36 | | signboard | 35.64 | 48.75 | | chest of drawers | 41.41 | 62.1 | | counter | 48.93 | 61.86 | | sand | 37.92 | 50.34 | | sink | 76.42 | 83.75 | | skyscraper | 50.09 | 58.39 | | fireplace | 70.59 | 92.62 | | refrigerator | 79.02 | 92.67 | | grandstand | 53.71 | 79.97 | | path | 17.6 | 21.69 | | stairs | 30.28 | 35.25 | | runway | 63.2 | 80.43 | | case | 58.26 | 62.36 | | pool table | 92.99 | 98.0 | | pillow | 57.03 | 67.19 | | screen door | 59.1 | 61.88 | | stairway | 46.28 | 66.64 | | river | 23.35 | 34.46 | | bridge | 78.62 | 89.57 | | bookcase | 33.23 | 55.49 | | blind | 39.65 | 42.17 | | coffee table | 60.84 | 88.31 | | toilet | 88.81 | 93.57 | | flower | 40.28 | 56.01 | | book | 49.41 | 68.0 | | hill | 7.41 | 10.57 | | bench | 50.43 | 58.49 | | countertop | 58.8 | 77.31 | | stove | 82.97 | 89.84 | | palm | 52.57 | 73.67 | | kitchen island | 56.66 | 73.58 | | computer | 74.37 | 88.91 | | swivel chair | 39.28 | 59.12 | | boat | 56.64 | 90.61 | | bar | 60.51 | 68.4 | | arcade machine | 77.82 | 80.93 | | hovel | 8.19 | 8.58 | | bus | 90.8 | 95.22 | | towel | 71.61 | 83.29 | | light | 47.49 | 56.12 | | truck | 42.48 | 59.77 | | tower | 10.62 | 18.29 | | chandelier | 65.47 | 82.53 | | awning | 35.72 | 44.97 | | streetlight | 25.37 | 31.53 | | booth | 34.85 | 35.04 | | television receiver | 69.59 | 83.54 | | airplane | 58.98 | 64.88 | | dirt track | 23.44 | 29.28 | | apparel | 62.15 | 84.5 | | pole | 28.84 | 36.35 | | land | 4.86 | 6.37 | | bannister | 18.28 | 26.38 | | escalator | 61.97 | 78.75 | | ottoman | 52.46 | 69.72 | | bottle | 23.93 | 33.74 | | buffet | 49.79 | 59.76 | | poster | 26.97 | 36.89 | | stage | 10.77 | 17.47 | | van | 46.08 | 62.45 | | ship | 0.0 | 0.0 | | fountain | 31.31 | 31.91 | | conveyer belt | 75.27 | 97.22 | | canopy | 53.22 | 64.82 | | washer | 80.11 | 83.34 | | plaything | 30.83 | 44.61 | | swimming pool | 59.47 | 85.17 | | stool | 50.14 | 63.01 | | barrel | 56.98 | 67.3 | | basket | 40.55 | 51.41 | | waterfall | 52.9 | 63.18 | | tent | 96.07 | 97.68 | | bag | 23.25 | 27.76 | | minibike | 70.44 | 87.21 | | cradle | 84.3 | 95.32 | | oven | 65.03 | 72.22 | | ball | 48.46 | 51.66 | | food | 64.17 | 70.84 | | step | 16.86 | 20.69 | | tank | 52.64 | 64.83 | | trade name | 30.13 | 37.19 | | microwave | 85.85 | 93.39 | | pot | 50.37 | 57.15 | | animal | 67.0 | 68.71 | | bicycle | 59.84 | 82.51 | | lake | 55.68 | 63.63 | | dishwasher | 70.74 | 82.09 | | screen | 56.84 | 86.53 | | blanket | 21.37 | 24.19 | | sculpture | 62.64 | 68.48 | | hood | 61.38 | 74.88 | | sconce | 52.96 | 71.08 | | vase | 41.61 | 56.9 | | traffic light | 31.47 | 58.38 | | tray | 14.84 | 19.74 | | ashcan | 51.75 | 65.81 | | fan | 60.92 | 74.26 | | pier | 39.21 | 43.78 | | crt screen | 3.85 | 8.72 | | plate | 55.7 | 75.99 | | monitor | 20.35 | 21.51 | | bulletin board | 56.68 | 67.11 | | shower | 5.85 | 5.86 | | radiator | 57.35 | 69.48 | | glass | 18.84 | 21.41 | | clock | 31.46 | 37.37 | | flag | 68.2 | 78.69 | +---------------------+-------+-------+ 2023-11-02 23:15:07,011 - mmseg - INFO - Summary: 2023-11-02 23:15:07,012 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 84.23 | 52.74 | 64.56 | +-------+-------+-------+ 2023-11-02 23:15:07,012 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 23:15:07,013 - mmseg - INFO - Iter(val) [250] aAcc: 0.8423, mIoU: 0.5274, mAcc: 0.6456, IoU.wall: 0.7985, IoU.building: 0.8317, IoU.sky: 0.9377, IoU.floor: 0.8232, IoU.tree: 0.7373, IoU.ceiling: 0.8511, IoU.road: 0.8298, IoU.bed : 0.9099, IoU.windowpane: 0.6481, IoU.grass: 0.7134, IoU.cabinet: 0.6390, IoU.sidewalk: 0.6633, IoU.person: 0.8203, IoU.earth: 0.3626, IoU.door: 0.5591, IoU.table: 0.6672, IoU.mountain: 0.5876, IoU.plant: 0.5102, IoU.curtain: 0.7722, IoU.chair: 0.5973, IoU.car: 0.8465, IoU.water: 0.5479, IoU.painting: 0.7226, IoU.sofa: 0.7914, IoU.shelf: 0.4186, IoU.house: 0.3949, IoU.sea: 0.6361, IoU.mirror: 0.7529, IoU.rug: 0.6248, IoU.field: 0.3510, IoU.armchair: 0.5568, IoU.seat: 0.6342, IoU.fence: 0.4577, IoU.desk: 0.5152, IoU.rock: 0.3649, IoU.wardrobe: 0.5285, IoU.lamp: 0.6531, IoU.bathtub: 0.8785, IoU.railing: 0.3833, IoU.cushion: 0.5967, IoU.base: 0.3476, IoU.box: 0.3121, IoU.column: 0.4786, IoU.signboard: 0.3564, IoU.chest of drawers: 0.4141, IoU.counter: 0.4893, IoU.sand: 0.3792, IoU.sink: 0.7642, IoU.skyscraper: 0.5009, IoU.fireplace: 0.7059, IoU.refrigerator: 0.7902, IoU.grandstand: 0.5371, IoU.path: 0.1760, IoU.stairs: 0.3028, IoU.runway: 0.6320, IoU.case: 0.5826, IoU.pool table: 0.9299, IoU.pillow: 0.5703, IoU.screen door: 0.5910, IoU.stairway: 0.4628, IoU.river: 0.2335, IoU.bridge: 0.7862, IoU.bookcase: 0.3323, IoU.blind: 0.3965, IoU.coffee table: 0.6084, IoU.toilet: 0.8881, IoU.flower: 0.4028, IoU.book: 0.4941, IoU.hill: 0.0741, IoU.bench: 0.5043, IoU.countertop: 0.5880, IoU.stove: 0.8297, IoU.palm: 0.5257, IoU.kitchen island: 0.5666, IoU.computer: 0.7437, IoU.swivel chair: 0.3928, IoU.boat: 0.5664, IoU.bar: 0.6051, IoU.arcade machine: 0.7782, IoU.hovel: 0.0819, IoU.bus: 0.9080, IoU.towel: 0.7161, IoU.light: 0.4749, IoU.truck: 0.4248, IoU.tower: 0.1062, IoU.chandelier: 0.6547, IoU.awning: 0.3572, IoU.streetlight: 0.2537, IoU.booth: 0.3485, IoU.television receiver: 0.6959, IoU.airplane: 0.5898, IoU.dirt track: 0.2344, IoU.apparel: 0.6215, IoU.pole: 0.2884, IoU.land: 0.0486, IoU.bannister: 0.1828, IoU.escalator: 0.6197, IoU.ottoman: 0.5246, IoU.bottle: 0.2393, IoU.buffet: 0.4979, IoU.poster: 0.2697, IoU.stage: 0.1077, IoU.van: 0.4608, IoU.ship: 0.0000, IoU.fountain: 0.3131, IoU.conveyer belt: 0.7527, IoU.canopy: 0.5322, IoU.washer: 0.8011, IoU.plaything: 0.3083, IoU.swimming pool: 0.5947, IoU.stool: 0.5014, IoU.barrel: 0.5698, IoU.basket: 0.4055, IoU.waterfall: 0.5290, IoU.tent: 0.9607, IoU.bag: 0.2325, IoU.minibike: 0.7044, IoU.cradle: 0.8430, IoU.oven: 0.6503, IoU.ball: 0.4846, IoU.food: 0.6417, IoU.step: 0.1686, IoU.tank: 0.5264, IoU.trade name: 0.3013, IoU.microwave: 0.8585, IoU.pot: 0.5037, IoU.animal: 0.6700, IoU.bicycle: 0.5984, IoU.lake: 0.5568, IoU.dishwasher: 0.7074, IoU.screen: 0.5684, IoU.blanket: 0.2137, IoU.sculpture: 0.6264, IoU.hood: 0.6138, IoU.sconce: 0.5296, IoU.vase: 0.4161, IoU.traffic light: 0.3147, IoU.tray: 0.1484, IoU.ashcan: 0.5175, IoU.fan: 0.6092, IoU.pier: 0.3921, IoU.crt screen: 0.0385, IoU.plate: 0.5570, IoU.monitor: 0.2035, IoU.bulletin board: 0.5668, IoU.shower: 0.0585, IoU.radiator: 0.5735, IoU.glass: 0.1884, IoU.clock: 0.3146, IoU.flag: 0.6820, Acc.wall: 0.8834, Acc.building: 0.9197, Acc.sky: 0.9630, Acc.floor: 0.9010, Acc.tree: 0.9152, Acc.ceiling: 0.9224, Acc.road: 0.9242, Acc.bed : 0.9667, Acc.windowpane: 0.8164, Acc.grass: 0.8812, Acc.cabinet: 0.7493, Acc.sidewalk: 0.7907, Acc.person: 0.9218, Acc.earth: 0.4892, Acc.door: 0.7573, Acc.table: 0.7645, Acc.mountain: 0.7927, Acc.plant: 0.6189, Acc.curtain: 0.8915, Acc.chair: 0.7516, Acc.car: 0.9303, Acc.water: 0.6961, Acc.painting: 0.8777, Acc.sofa: 0.8901, Acc.shelf: 0.6047, Acc.house: 0.5081, Acc.sea: 0.8961, Acc.mirror: 0.8513, Acc.rug: 0.7257, Acc.field: 0.5265, Acc.armchair: 0.7404, Acc.seat: 0.8954, Acc.fence: 0.6994, Acc.desk: 0.7751, Acc.rock: 0.4889, Acc.wardrobe: 0.7309, Acc.lamp: 0.8027, Acc.bathtub: 0.9150, Acc.railing: 0.5229, Acc.cushion: 0.7654, Acc.base: 0.5022, Acc.box: 0.4637, Acc.column: 0.5736, Acc.signboard: 0.4875, Acc.chest of drawers: 0.6210, Acc.counter: 0.6186, Acc.sand: 0.5034, Acc.sink: 0.8375, Acc.skyscraper: 0.5839, Acc.fireplace: 0.9262, Acc.refrigerator: 0.9267, Acc.grandstand: 0.7997, Acc.path: 0.2169, Acc.stairs: 0.3525, Acc.runway: 0.8043, Acc.case: 0.6236, Acc.pool table: 0.9800, Acc.pillow: 0.6719, Acc.screen door: 0.6188, Acc.stairway: 0.6664, Acc.river: 0.3446, Acc.bridge: 0.8957, Acc.bookcase: 0.5549, Acc.blind: 0.4217, Acc.coffee table: 0.8831, Acc.toilet: 0.9357, Acc.flower: 0.5601, Acc.book: 0.6800, Acc.hill: 0.1057, Acc.bench: 0.5849, Acc.countertop: 0.7731, Acc.stove: 0.8984, Acc.palm: 0.7367, Acc.kitchen island: 0.7358, Acc.computer: 0.8891, Acc.swivel chair: 0.5912, Acc.boat: 0.9061, Acc.bar: 0.6840, Acc.arcade machine: 0.8093, Acc.hovel: 0.0858, Acc.bus: 0.9522, Acc.towel: 0.8329, Acc.light: 0.5612, Acc.truck: 0.5977, Acc.tower: 0.1829, Acc.chandelier: 0.8253, Acc.awning: 0.4497, Acc.streetlight: 0.3153, Acc.booth: 0.3504, Acc.television receiver: 0.8354, Acc.airplane: 0.6488, Acc.dirt track: 0.2928, Acc.apparel: 0.8450, Acc.pole: 0.3635, Acc.land: 0.0637, Acc.bannister: 0.2638, Acc.escalator: 0.7875, Acc.ottoman: 0.6972, Acc.bottle: 0.3374, Acc.buffet: 0.5976, Acc.poster: 0.3689, Acc.stage: 0.1747, Acc.van: 0.6245, Acc.ship: 0.0000, Acc.fountain: 0.3191, Acc.conveyer belt: 0.9722, Acc.canopy: 0.6482, Acc.washer: 0.8334, Acc.plaything: 0.4461, Acc.swimming pool: 0.8517, Acc.stool: 0.6301, Acc.barrel: 0.6730, Acc.basket: 0.5141, Acc.waterfall: 0.6318, Acc.tent: 0.9768, Acc.bag: 0.2776, Acc.minibike: 0.8721, Acc.cradle: 0.9532, Acc.oven: 0.7222, Acc.ball: 0.5166, Acc.food: 0.7084, Acc.step: 0.2069, Acc.tank: 0.6483, Acc.trade name: 0.3719, Acc.microwave: 0.9339, Acc.pot: 0.5715, Acc.animal: 0.6871, Acc.bicycle: 0.8251, Acc.lake: 0.6363, Acc.dishwasher: 0.8209, Acc.screen: 0.8653, Acc.blanket: 0.2419, Acc.sculpture: 0.6848, Acc.hood: 0.7488, Acc.sconce: 0.7108, Acc.vase: 0.5690, Acc.traffic light: 0.5838, Acc.tray: 0.1974, Acc.ashcan: 0.6581, Acc.fan: 0.7426, Acc.pier: 0.4378, Acc.crt screen: 0.0872, Acc.plate: 0.7599, Acc.monitor: 0.2151, Acc.bulletin board: 0.6711, Acc.shower: 0.0586, Acc.radiator: 0.6948, Acc.glass: 0.2141, Acc.clock: 0.3737, Acc.flag: 0.7869 2023-11-02 23:16:10,014 - mmseg - INFO - Iter [12050/20000] lr: 1.288e-06, eta: 2:57:35, time: 2.423, data_time: 1.218, memory: 38534, decode.loss_ce: 0.1960, decode.acc_seg: 91.7965, loss: 0.1960 2023-11-02 23:17:10,478 - mmseg - INFO - Iter [12100/20000] lr: 1.280e-06, eta: 2:56:24, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1848, decode.acc_seg: 92.6104, loss: 0.1848 2023-11-02 23:18:10,996 - mmseg - INFO - Iter [12150/20000] lr: 1.272e-06, eta: 2:55:13, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1832, decode.acc_seg: 92.4688, loss: 0.1832 2023-11-02 23:19:14,287 - mmseg - INFO - Iter [12200/20000] lr: 1.264e-06, eta: 2:54:03, time: 1.266, data_time: 0.062, memory: 38534, decode.loss_ce: 0.1831, decode.acc_seg: 92.3387, loss: 0.1831 2023-11-02 23:20:14,802 - mmseg - INFO - Iter [12250/20000] lr: 1.256e-06, eta: 2:52:52, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1791, decode.acc_seg: 92.5182, loss: 0.1791 2023-11-02 23:21:15,282 - mmseg - INFO - Iter [12300/20000] lr: 1.247e-06, eta: 2:51:41, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1817, decode.acc_seg: 92.3554, loss: 0.1817 2023-11-02 23:22:18,283 - mmseg - INFO - Iter [12350/20000] lr: 1.239e-06, eta: 2:50:32, time: 1.260, data_time: 0.054, memory: 38534, decode.loss_ce: 0.1750, decode.acc_seg: 92.6300, loss: 0.1750 2023-11-02 23:23:18,743 - mmseg - INFO - Iter [12400/20000] lr: 1.231e-06, eta: 2:49:21, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1768, decode.acc_seg: 92.8284, loss: 0.1768 2023-11-02 23:24:19,220 - mmseg - INFO - Iter [12450/20000] lr: 1.223e-06, eta: 2:48:11, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1824, decode.acc_seg: 92.6570, loss: 0.1824 2023-11-02 23:25:19,676 - mmseg - INFO - Iter [12500/20000] lr: 1.215e-06, eta: 2:47:00, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1719, decode.acc_seg: 92.8675, loss: 0.1719 2023-11-02 23:26:20,160 - mmseg - INFO - Iter [12550/20000] lr: 1.207e-06, eta: 2:45:49, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1805, decode.acc_seg: 92.4950, loss: 0.1805 2023-11-02 23:27:20,649 - mmseg - INFO - Iter [12600/20000] lr: 1.199e-06, eta: 2:44:39, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1807, decode.acc_seg: 92.5668, loss: 0.1807 2023-11-02 23:28:23,442 - mmseg - INFO - Iter [12650/20000] lr: 1.191e-06, eta: 2:43:30, time: 1.256, data_time: 0.052, memory: 38534, decode.loss_ce: 0.1849, decode.acc_seg: 92.3714, loss: 0.1849 2023-11-02 23:29:23,919 - mmseg - INFO - Iter [12700/20000] lr: 1.183e-06, eta: 2:42:19, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1698, decode.acc_seg: 93.0537, loss: 0.1698 2023-11-02 23:30:24,368 - mmseg - INFO - Iter [12750/20000] lr: 1.175e-06, eta: 2:41:09, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1834, decode.acc_seg: 92.5852, loss: 0.1834 2023-11-02 23:31:24,866 - mmseg - INFO - Iter [12800/20000] lr: 1.166e-06, eta: 2:39:59, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1902, decode.acc_seg: 92.2074, loss: 0.1902 2023-11-02 23:32:25,316 - mmseg - INFO - Iter [12850/20000] lr: 1.158e-06, eta: 2:38:49, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1760, decode.acc_seg: 92.8562, loss: 0.1760 2023-11-02 23:33:25,844 - mmseg - INFO - Iter [12900/20000] lr: 1.150e-06, eta: 2:37:39, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1822, decode.acc_seg: 92.2683, loss: 0.1822 2023-11-02 23:34:26,296 - mmseg - INFO - Iter [12950/20000] lr: 1.142e-06, eta: 2:36:29, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1828, decode.acc_seg: 92.2659, loss: 0.1828 2023-11-02 23:35:29,067 - mmseg - INFO - Saving checkpoint at 13000 iterations 2023-11-02 23:36:27,629 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 23:36:27,629 - mmseg - INFO - Iter [13000/20000] lr: 1.134e-06, eta: 2:35:52, time: 2.427, data_time: 0.052, memory: 38534, decode.loss_ce: 0.1730, decode.acc_seg: 92.9976, loss: 0.1730 2023-11-02 23:37:26,673 - mmseg - INFO - per class results: 2023-11-02 23:37:26,678 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 80.22 | 89.42 | | building | 82.97 | 93.55 | | sky | 93.94 | 96.73 | | floor | 82.24 | 89.94 | | tree | 74.56 | 86.96 | | ceiling | 85.19 | 92.15 | | road | 83.95 | 91.13 | | bed | 91.17 | 96.09 | | windowpane | 65.15 | 77.88 | | grass | 70.69 | 89.37 | | cabinet | 63.39 | 72.84 | | sidewalk | 66.85 | 83.79 | | person | 82.35 | 91.69 | | earth | 36.93 | 48.2 | | door | 57.62 | 72.49 | | table | 67.31 | 78.63 | | mountain | 62.82 | 79.04 | | plant | 54.88 | 68.57 | | curtain | 77.16 | 88.2 | | chair | 58.54 | 74.01 | | car | 84.79 | 93.28 | | water | 56.85 | 71.94 | | painting | 73.42 | 87.82 | | sofa | 79.11 | 89.4 | | shelf | 45.42 | 67.01 | | house | 41.4 | 57.53 | | sea | 64.25 | 87.94 | | mirror | 74.13 | 81.48 | | rug | 65.58 | 75.98 | | field | 29.97 | 48.92 | | armchair | 56.56 | 74.26 | | seat | 63.53 | 87.7 | | fence | 45.86 | 67.9 | | desk | 53.15 | 76.54 | | rock | 44.51 | 57.94 | | wardrobe | 51.58 | 69.13 | | lamp | 67.27 | 79.19 | | bathtub | 84.96 | 87.75 | | railing | 38.92 | 52.91 | | cushion | 61.42 | 74.96 | | base | 29.92 | 38.61 | | box | 33.61 | 43.91 | | column | 50.68 | 61.53 | | signboard | 34.6 | 50.67 | | chest of drawers | 39.14 | 63.49 | | counter | 51.01 | 68.92 | | sand | 37.69 | 51.51 | | sink | 76.58 | 85.32 | | skyscraper | 49.37 | 59.86 | | fireplace | 70.2 | 87.03 | | refrigerator | 76.86 | 93.98 | | grandstand | 53.56 | 75.45 | | path | 17.6 | 21.77 | | stairs | 26.12 | 29.44 | | runway | 65.37 | 83.41 | | case | 57.47 | 65.86 | | pool table | 93.41 | 97.71 | | pillow | 60.65 | 73.28 | | screen door | 77.18 | 86.97 | | stairway | 41.69 | 62.59 | | river | 24.17 | 37.74 | | bridge | 76.8 | 86.51 | | bookcase | 36.22 | 51.82 | | blind | 44.92 | 52.11 | | coffee table | 64.65 | 86.14 | | toilet | 88.57 | 93.28 | | flower | 40.87 | 55.94 | | book | 49.85 | 67.46 | | hill | 8.27 | 11.53 | | bench | 50.82 | 59.49 | | countertop | 62.21 | 73.16 | | stove | 83.02 | 91.12 | | palm | 47.17 | 79.33 | | kitchen island | 55.71 | 72.1 | | computer | 75.36 | 90.04 | | swivel chair | 44.04 | 80.23 | | boat | 51.98 | 91.03 | | bar | 60.47 | 66.46 | | arcade machine | 78.8 | 81.61 | | hovel | 19.54 | 21.75 | | bus | 90.52 | 94.91 | | towel | 71.51 | 84.99 | | light | 49.45 | 66.13 | | truck | 44.63 | 57.56 | | tower | 11.1 | 18.24 | | chandelier | 65.62 | 83.2 | | awning | 34.14 | 41.17 | | streetlight | 23.55 | 32.23 | | booth | 34.93 | 35.07 | | television receiver | 68.57 | 86.86 | | airplane | 59.11 | 65.68 | | dirt track | 17.78 | 21.56 | | apparel | 59.57 | 83.38 | | pole | 16.86 | 19.57 | | land | 4.19 | 5.48 | | bannister | 19.11 | 28.08 | | escalator | 54.95 | 67.05 | | ottoman | 48.02 | 65.95 | | bottle | 22.16 | 27.38 | | buffet | 51.27 | 69.59 | | poster | 25.96 | 35.26 | | stage | 11.25 | 18.77 | | van | 48.69 | 66.3 | | ship | 3.36 | 3.46 | | fountain | 19.3 | 19.68 | | conveyer belt | 75.53 | 96.04 | | canopy | 49.22 | 56.49 | | washer | 82.35 | 86.22 | | plaything | 31.41 | 41.08 | | swimming pool | 58.43 | 85.63 | | stool | 46.86 | 70.59 | | barrel | 52.46 | 65.26 | | basket | 39.11 | 53.92 | | waterfall | 51.33 | 63.63 | | tent | 94.98 | 98.57 | | bag | 22.61 | 26.89 | | minibike | 72.19 | 84.8 | | cradle | 84.92 | 96.82 | | oven | 60.9 | 74.13 | | ball | 56.37 | 62.11 | | food | 64.53 | 74.35 | | step | 17.35 | 22.74 | | tank | 53.08 | 63.39 | | trade name | 24.24 | 28.25 | | microwave | 86.31 | 92.41 | | pot | 54.32 | 63.6 | | animal | 72.51 | 76.03 | | bicycle | 59.13 | 74.21 | | lake | 52.61 | 63.71 | | dishwasher | 72.2 | 78.35 | | screen | 57.32 | 88.84 | | blanket | 23.1 | 25.87 | | sculpture | 61.57 | 68.1 | | hood | 58.82 | 71.62 | | sconce | 52.29 | 64.46 | | vase | 41.82 | 61.23 | | traffic light | 32.86 | 53.79 | | tray | 10.89 | 17.99 | | ashcan | 53.16 | 63.13 | | fan | 61.72 | 80.41 | | pier | 39.71 | 43.59 | | crt screen | 2.66 | 3.02 | | plate | 57.78 | 75.68 | | monitor | 64.33 | 70.38 | | bulletin board | 56.09 | 68.24 | | shower | 7.34 | 7.93 | | radiator | 56.2 | 67.85 | | glass | 18.81 | 20.92 | | clock | 31.72 | 39.13 | | flag | 68.97 | 75.73 | +---------------------+-------+-------+ 2023-11-02 23:37:26,678 - mmseg - INFO - Summary: 2023-11-02 23:37:26,678 - mmseg - INFO - +-------+-------+------+ | aAcc | mIoU | mAcc | +-------+-------+------+ | 84.54 | 53.16 | 65.1 | +-------+-------+------+ 2023-11-02 23:37:26,679 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 23:37:26,679 - mmseg - INFO - Iter(val) [250] aAcc: 0.8454, mIoU: 0.5316, mAcc: 0.6510, IoU.wall: 0.8022, IoU.building: 0.8297, IoU.sky: 0.9394, IoU.floor: 0.8224, IoU.tree: 0.7456, IoU.ceiling: 0.8519, IoU.road: 0.8395, IoU.bed : 0.9117, IoU.windowpane: 0.6515, IoU.grass: 0.7069, IoU.cabinet: 0.6339, IoU.sidewalk: 0.6685, IoU.person: 0.8235, IoU.earth: 0.3693, IoU.door: 0.5762, IoU.table: 0.6731, IoU.mountain: 0.6282, IoU.plant: 0.5488, IoU.curtain: 0.7716, IoU.chair: 0.5854, IoU.car: 0.8479, IoU.water: 0.5685, IoU.painting: 0.7342, IoU.sofa: 0.7911, IoU.shelf: 0.4542, IoU.house: 0.4140, IoU.sea: 0.6425, IoU.mirror: 0.7413, IoU.rug: 0.6558, IoU.field: 0.2997, IoU.armchair: 0.5656, IoU.seat: 0.6353, IoU.fence: 0.4586, IoU.desk: 0.5315, IoU.rock: 0.4451, IoU.wardrobe: 0.5158, IoU.lamp: 0.6727, IoU.bathtub: 0.8496, IoU.railing: 0.3892, IoU.cushion: 0.6142, IoU.base: 0.2992, IoU.box: 0.3361, IoU.column: 0.5068, IoU.signboard: 0.3460, IoU.chest of drawers: 0.3914, IoU.counter: 0.5101, IoU.sand: 0.3769, IoU.sink: 0.7658, IoU.skyscraper: 0.4937, IoU.fireplace: 0.7020, IoU.refrigerator: 0.7686, IoU.grandstand: 0.5356, IoU.path: 0.1760, IoU.stairs: 0.2612, IoU.runway: 0.6537, IoU.case: 0.5747, IoU.pool table: 0.9341, IoU.pillow: 0.6065, IoU.screen door: 0.7718, IoU.stairway: 0.4169, IoU.river: 0.2417, IoU.bridge: 0.7680, IoU.bookcase: 0.3622, IoU.blind: 0.4492, IoU.coffee table: 0.6465, IoU.toilet: 0.8857, IoU.flower: 0.4087, IoU.book: 0.4985, IoU.hill: 0.0827, IoU.bench: 0.5082, IoU.countertop: 0.6221, IoU.stove: 0.8302, IoU.palm: 0.4717, IoU.kitchen island: 0.5571, IoU.computer: 0.7536, IoU.swivel chair: 0.4404, IoU.boat: 0.5198, IoU.bar: 0.6047, IoU.arcade machine: 0.7880, IoU.hovel: 0.1954, IoU.bus: 0.9052, IoU.towel: 0.7151, IoU.light: 0.4945, IoU.truck: 0.4463, IoU.tower: 0.1110, IoU.chandelier: 0.6562, IoU.awning: 0.3414, IoU.streetlight: 0.2355, IoU.booth: 0.3493, IoU.television receiver: 0.6857, IoU.airplane: 0.5911, IoU.dirt track: 0.1778, IoU.apparel: 0.5957, IoU.pole: 0.1686, IoU.land: 0.0419, IoU.bannister: 0.1911, IoU.escalator: 0.5495, IoU.ottoman: 0.4802, IoU.bottle: 0.2216, IoU.buffet: 0.5127, IoU.poster: 0.2596, IoU.stage: 0.1125, IoU.van: 0.4869, IoU.ship: 0.0336, IoU.fountain: 0.1930, IoU.conveyer belt: 0.7553, IoU.canopy: 0.4922, IoU.washer: 0.8235, IoU.plaything: 0.3141, IoU.swimming pool: 0.5843, IoU.stool: 0.4686, IoU.barrel: 0.5246, IoU.basket: 0.3911, IoU.waterfall: 0.5133, IoU.tent: 0.9498, IoU.bag: 0.2261, IoU.minibike: 0.7219, IoU.cradle: 0.8492, IoU.oven: 0.6090, IoU.ball: 0.5637, IoU.food: 0.6453, IoU.step: 0.1735, IoU.tank: 0.5308, IoU.trade name: 0.2424, IoU.microwave: 0.8631, IoU.pot: 0.5432, IoU.animal: 0.7251, IoU.bicycle: 0.5913, IoU.lake: 0.5261, IoU.dishwasher: 0.7220, IoU.screen: 0.5732, IoU.blanket: 0.2310, IoU.sculpture: 0.6157, IoU.hood: 0.5882, IoU.sconce: 0.5229, IoU.vase: 0.4182, IoU.traffic light: 0.3286, IoU.tray: 0.1089, IoU.ashcan: 0.5316, IoU.fan: 0.6172, IoU.pier: 0.3971, IoU.crt screen: 0.0266, IoU.plate: 0.5778, IoU.monitor: 0.6433, IoU.bulletin board: 0.5609, IoU.shower: 0.0734, IoU.radiator: 0.5620, IoU.glass: 0.1881, IoU.clock: 0.3172, IoU.flag: 0.6897, Acc.wall: 0.8942, Acc.building: 0.9355, Acc.sky: 0.9673, Acc.floor: 0.8994, Acc.tree: 0.8696, Acc.ceiling: 0.9215, Acc.road: 0.9113, Acc.bed : 0.9609, Acc.windowpane: 0.7788, Acc.grass: 0.8937, Acc.cabinet: 0.7284, Acc.sidewalk: 0.8379, Acc.person: 0.9169, Acc.earth: 0.4820, Acc.door: 0.7249, Acc.table: 0.7863, Acc.mountain: 0.7904, Acc.plant: 0.6857, Acc.curtain: 0.8820, Acc.chair: 0.7401, Acc.car: 0.9328, Acc.water: 0.7194, Acc.painting: 0.8782, Acc.sofa: 0.8940, Acc.shelf: 0.6701, Acc.house: 0.5753, Acc.sea: 0.8794, Acc.mirror: 0.8148, Acc.rug: 0.7598, Acc.field: 0.4892, Acc.armchair: 0.7426, Acc.seat: 0.8770, Acc.fence: 0.6790, Acc.desk: 0.7654, Acc.rock: 0.5794, Acc.wardrobe: 0.6913, Acc.lamp: 0.7919, Acc.bathtub: 0.8775, Acc.railing: 0.5291, Acc.cushion: 0.7496, Acc.base: 0.3861, Acc.box: 0.4391, Acc.column: 0.6153, Acc.signboard: 0.5067, Acc.chest of drawers: 0.6349, Acc.counter: 0.6892, Acc.sand: 0.5151, Acc.sink: 0.8532, Acc.skyscraper: 0.5986, Acc.fireplace: 0.8703, Acc.refrigerator: 0.9398, Acc.grandstand: 0.7545, Acc.path: 0.2177, Acc.stairs: 0.2944, Acc.runway: 0.8341, Acc.case: 0.6586, Acc.pool table: 0.9771, Acc.pillow: 0.7328, Acc.screen door: 0.8697, Acc.stairway: 0.6259, Acc.river: 0.3774, Acc.bridge: 0.8651, Acc.bookcase: 0.5182, Acc.blind: 0.5211, Acc.coffee table: 0.8614, Acc.toilet: 0.9328, Acc.flower: 0.5594, Acc.book: 0.6746, Acc.hill: 0.1153, Acc.bench: 0.5949, Acc.countertop: 0.7316, Acc.stove: 0.9112, Acc.palm: 0.7933, Acc.kitchen island: 0.7210, Acc.computer: 0.9004, Acc.swivel chair: 0.8023, Acc.boat: 0.9103, Acc.bar: 0.6646, Acc.arcade machine: 0.8161, Acc.hovel: 0.2175, Acc.bus: 0.9491, Acc.towel: 0.8499, Acc.light: 0.6613, Acc.truck: 0.5756, Acc.tower: 0.1824, Acc.chandelier: 0.8320, Acc.awning: 0.4117, Acc.streetlight: 0.3223, Acc.booth: 0.3507, Acc.television receiver: 0.8686, Acc.airplane: 0.6568, Acc.dirt track: 0.2156, Acc.apparel: 0.8338, Acc.pole: 0.1957, Acc.land: 0.0548, Acc.bannister: 0.2808, Acc.escalator: 0.6705, Acc.ottoman: 0.6595, Acc.bottle: 0.2738, Acc.buffet: 0.6959, Acc.poster: 0.3526, Acc.stage: 0.1877, Acc.van: 0.6630, Acc.ship: 0.0346, Acc.fountain: 0.1968, Acc.conveyer belt: 0.9604, Acc.canopy: 0.5649, Acc.washer: 0.8622, Acc.plaything: 0.4108, Acc.swimming pool: 0.8563, Acc.stool: 0.7059, Acc.barrel: 0.6526, Acc.basket: 0.5392, Acc.waterfall: 0.6363, Acc.tent: 0.9857, Acc.bag: 0.2689, Acc.minibike: 0.8480, Acc.cradle: 0.9682, Acc.oven: 0.7413, Acc.ball: 0.6211, Acc.food: 0.7435, Acc.step: 0.2274, Acc.tank: 0.6339, Acc.trade name: 0.2825, Acc.microwave: 0.9241, Acc.pot: 0.6360, Acc.animal: 0.7603, Acc.bicycle: 0.7421, Acc.lake: 0.6371, Acc.dishwasher: 0.7835, Acc.screen: 0.8884, Acc.blanket: 0.2587, Acc.sculpture: 0.6810, Acc.hood: 0.7162, Acc.sconce: 0.6446, Acc.vase: 0.6123, Acc.traffic light: 0.5379, Acc.tray: 0.1799, Acc.ashcan: 0.6313, Acc.fan: 0.8041, Acc.pier: 0.4359, Acc.crt screen: 0.0302, Acc.plate: 0.7568, Acc.monitor: 0.7038, Acc.bulletin board: 0.6824, Acc.shower: 0.0793, Acc.radiator: 0.6785, Acc.glass: 0.2092, Acc.clock: 0.3913, Acc.flag: 0.7573 2023-11-02 23:38:27,179 - mmseg - INFO - Iter [13050/20000] lr: 1.126e-06, eta: 2:35:13, time: 2.391, data_time: 1.188, memory: 38534, decode.loss_ce: 0.1789, decode.acc_seg: 92.4302, loss: 0.1789 2023-11-02 23:39:27,615 - mmseg - INFO - Iter [13100/20000] lr: 1.118e-06, eta: 2:34:03, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1771, decode.acc_seg: 92.6591, loss: 0.1771 2023-11-02 23:40:28,065 - mmseg - INFO - Iter [13150/20000] lr: 1.110e-06, eta: 2:32:52, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1787, decode.acc_seg: 92.7521, loss: 0.1787 2023-11-02 23:41:28,502 - mmseg - INFO - Iter [13200/20000] lr: 1.102e-06, eta: 2:31:42, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1623, decode.acc_seg: 93.2247, loss: 0.1623 2023-11-02 23:42:28,975 - mmseg - INFO - Iter [13250/20000] lr: 1.094e-06, eta: 2:30:32, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1914, decode.acc_seg: 92.2252, loss: 0.1914 2023-11-02 23:43:31,981 - mmseg - INFO - Iter [13300/20000] lr: 1.085e-06, eta: 2:29:23, time: 1.260, data_time: 0.053, memory: 38534, decode.loss_ce: 0.1655, decode.acc_seg: 92.9682, loss: 0.1655 2023-11-02 23:44:32,464 - mmseg - INFO - Iter [13350/20000] lr: 1.077e-06, eta: 2:28:13, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1689, decode.acc_seg: 93.0357, loss: 0.1689 2023-11-02 23:45:33,005 - mmseg - INFO - Iter [13400/20000] lr: 1.069e-06, eta: 2:27:03, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1722, decode.acc_seg: 92.7579, loss: 0.1722 2023-11-02 23:46:33,509 - mmseg - INFO - Iter [13450/20000] lr: 1.061e-06, eta: 2:25:53, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1768, decode.acc_seg: 92.7962, loss: 0.1768 2023-11-02 23:47:33,963 - mmseg - INFO - Iter [13500/20000] lr: 1.053e-06, eta: 2:24:43, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1791, decode.acc_seg: 92.6032, loss: 0.1791 2023-11-02 23:48:34,449 - mmseg - INFO - Iter [13550/20000] lr: 1.045e-06, eta: 2:23:33, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1724, decode.acc_seg: 93.0293, loss: 0.1724 2023-11-02 23:49:37,373 - mmseg - INFO - Iter [13600/20000] lr: 1.037e-06, eta: 2:22:25, time: 1.258, data_time: 0.055, memory: 38534, decode.loss_ce: 0.1757, decode.acc_seg: 92.6877, loss: 0.1757 2023-11-02 23:50:37,869 - mmseg - INFO - Iter [13650/20000] lr: 1.029e-06, eta: 2:21:15, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1758, decode.acc_seg: 92.6761, loss: 0.1758 2023-11-02 23:51:38,387 - mmseg - INFO - Iter [13700/20000] lr: 1.021e-06, eta: 2:20:05, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1677, decode.acc_seg: 93.0458, loss: 0.1677 2023-11-02 23:52:38,887 - mmseg - INFO - Iter [13750/20000] lr: 1.013e-06, eta: 2:18:56, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1707, decode.acc_seg: 92.9836, loss: 0.1707 2023-11-02 23:53:39,354 - mmseg - INFO - Iter [13800/20000] lr: 1.004e-06, eta: 2:17:46, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1826, decode.acc_seg: 92.6628, loss: 0.1826 2023-11-02 23:54:39,900 - mmseg - INFO - Iter [13850/20000] lr: 9.964e-07, eta: 2:16:37, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1662, decode.acc_seg: 93.1288, loss: 0.1662 2023-11-02 23:55:40,371 - mmseg - INFO - Iter [13900/20000] lr: 9.883e-07, eta: 2:15:28, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1846, decode.acc_seg: 92.5497, loss: 0.1846 2023-11-02 23:56:43,332 - mmseg - INFO - Iter [13950/20000] lr: 9.802e-07, eta: 2:14:19, time: 1.259, data_time: 0.053, memory: 38534, decode.loss_ce: 0.1657, decode.acc_seg: 93.1003, loss: 0.1657 2023-11-02 23:57:43,855 - mmseg - INFO - Saving checkpoint at 14000 iterations 2023-11-02 23:58:43,277 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 23:58:43,277 - mmseg - INFO - Iter [14000/20000] lr: 9.721e-07, eta: 2:13:36, time: 2.399, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1827, decode.acc_seg: 92.6043, loss: 0.1827 2023-11-02 23:59:41,669 - mmseg - INFO - per class results: 2023-11-02 23:59:41,674 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 80.17 | 88.98 | | building | 83.29 | 93.49 | | sky | 93.92 | 96.83 | | floor | 82.05 | 90.91 | | tree | 74.07 | 87.71 | | ceiling | 85.57 | 93.17 | | road | 84.0 | 91.04 | | bed | 91.47 | 96.13 | | windowpane | 65.16 | 84.03 | | grass | 71.7 | 88.65 | | cabinet | 62.6 | 72.57 | | sidewalk | 67.13 | 82.26 | | person | 82.24 | 91.74 | | earth | 38.0 | 51.27 | | door | 57.07 | 69.38 | | table | 65.61 | 75.34 | | mountain | 61.71 | 76.56 | | plant | 52.86 | 64.2 | | curtain | 77.6 | 88.62 | | chair | 58.56 | 69.63 | | car | 84.95 | 92.93 | | water | 54.07 | 67.82 | | painting | 73.81 | 87.75 | | sofa | 78.73 | 90.3 | | shelf | 44.21 | 66.17 | | house | 40.55 | 53.81 | | sea | 61.09 | 82.99 | | mirror | 72.29 | 80.89 | | rug | 58.96 | 66.81 | | field | 35.58 | 56.79 | | armchair | 55.75 | 72.61 | | seat | 64.98 | 87.78 | | fence | 45.6 | 66.62 | | desk | 51.22 | 80.04 | | rock | 47.72 | 65.1 | | wardrobe | 49.96 | 72.59 | | lamp | 66.79 | 80.89 | | bathtub | 86.72 | 89.56 | | railing | 37.54 | 50.55 | | cushion | 59.65 | 72.79 | | base | 33.67 | 43.67 | | box | 33.78 | 44.24 | | column | 51.04 | 61.53 | | signboard | 34.95 | 50.47 | | chest of drawers | 37.57 | 62.62 | | counter | 48.63 | 58.68 | | sand | 38.02 | 52.34 | | sink | 76.8 | 83.27 | | skyscraper | 48.28 | 62.91 | | fireplace | 69.81 | 90.18 | | refrigerator | 81.92 | 91.34 | | grandstand | 56.71 | 74.66 | | path | 17.58 | 22.96 | | stairs | 30.28 | 34.18 | | runway | 68.11 | 86.8 | | case | 58.33 | 70.52 | | pool table | 93.48 | 97.83 | | pillow | 60.55 | 75.39 | | screen door | 75.55 | 85.77 | | stairway | 47.08 | 59.46 | | river | 20.2 | 45.52 | | bridge | 67.96 | 88.37 | | bookcase | 36.08 | 55.2 | | blind | 42.39 | 46.66 | | coffee table | 62.24 | 85.12 | | toilet | 88.66 | 94.48 | | flower | 41.75 | 58.05 | | book | 49.48 | 67.7 | | hill | 7.51 | 10.42 | | bench | 53.45 | 62.32 | | countertop | 59.27 | 75.42 | | stove | 82.28 | 91.81 | | palm | 47.49 | 76.94 | | kitchen island | 56.8 | 73.64 | | computer | 75.27 | 91.37 | | swivel chair | 41.44 | 63.67 | | boat | 57.61 | 90.99 | | bar | 58.43 | 61.49 | | arcade machine | 75.8 | 79.18 | | hovel | 8.44 | 8.77 | | bus | 90.9 | 95.22 | | towel | 71.77 | 84.4 | | light | 48.52 | 57.96 | | truck | 43.14 | 61.06 | | tower | 16.76 | 30.31 | | chandelier | 65.62 | 83.87 | | awning | 37.24 | 45.09 | | streetlight | 24.3 | 30.08 | | booth | 35.75 | 35.93 | | television receiver | 71.72 | 89.61 | | airplane | 59.05 | 65.84 | | dirt track | 26.53 | 35.23 | | apparel | 57.61 | 84.7 | | pole | 27.78 | 33.94 | | land | 5.11 | 6.08 | | bannister | 17.72 | 22.29 | | escalator | 61.9 | 79.61 | | ottoman | 49.01 | 71.88 | | bottle | 23.42 | 31.17 | | buffet | 56.41 | 74.24 | | poster | 29.28 | 41.33 | | stage | 11.8 | 17.54 | | van | 44.52 | 59.15 | | ship | 3.61 | 3.81 | | fountain | 15.63 | 16.05 | | conveyer belt | 77.41 | 94.81 | | canopy | 51.01 | 61.25 | | washer | 83.78 | 88.29 | | plaything | 30.49 | 45.36 | | swimming pool | 56.9 | 81.17 | | stool | 50.51 | 63.78 | | barrel | 56.13 | 66.29 | | basket | 40.55 | 57.9 | | waterfall | 48.9 | 57.84 | | tent | 95.73 | 98.11 | | bag | 25.05 | 31.93 | | minibike | 72.83 | 83.6 | | cradle | 79.81 | 96.31 | | oven | 65.99 | 74.58 | | ball | 42.32 | 44.78 | | food | 64.18 | 70.23 | | step | 18.89 | 23.36 | | tank | 52.79 | 62.97 | | trade name | 28.14 | 33.81 | | microwave | 87.04 | 92.18 | | pot | 54.81 | 62.83 | | animal | 69.87 | 72.54 | | bicycle | 58.83 | 74.14 | | lake | 60.08 | 66.99 | | dishwasher | 73.68 | 82.39 | | screen | 59.87 | 92.17 | | blanket | 24.92 | 29.21 | | sculpture | 61.31 | 68.39 | | hood | 60.09 | 72.25 | | sconce | 49.37 | 57.74 | | vase | 42.16 | 59.92 | | traffic light | 32.57 | 57.25 | | tray | 13.4 | 18.95 | | ashcan | 50.93 | 64.34 | | fan | 61.08 | 72.92 | | pier | 39.63 | 43.22 | | crt screen | 5.04 | 10.88 | | plate | 58.31 | 75.44 | | monitor | 21.29 | 22.17 | | bulletin board | 54.98 | 70.65 | | shower | 9.11 | 9.48 | | radiator | 56.38 | 67.25 | | glass | 18.95 | 21.14 | | clock | 31.77 | 38.76 | | flag | 69.57 | 75.93 | +---------------------+-------+-------+ 2023-11-02 23:59:41,674 - mmseg - INFO - Summary: 2023-11-02 23:59:41,674 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 84.47 | 53.07 | 64.97 | +-------+-------+-------+ 2023-11-02 23:59:41,675 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-02 23:59:41,675 - mmseg - INFO - Iter(val) [250] aAcc: 0.8447, mIoU: 0.5307, mAcc: 0.6497, IoU.wall: 0.8017, IoU.building: 0.8329, IoU.sky: 0.9392, IoU.floor: 0.8205, IoU.tree: 0.7407, IoU.ceiling: 0.8557, IoU.road: 0.8400, IoU.bed : 0.9147, IoU.windowpane: 0.6516, IoU.grass: 0.7170, IoU.cabinet: 0.6260, IoU.sidewalk: 0.6713, IoU.person: 0.8224, IoU.earth: 0.3800, IoU.door: 0.5707, IoU.table: 0.6561, IoU.mountain: 0.6171, IoU.plant: 0.5286, IoU.curtain: 0.7760, IoU.chair: 0.5856, IoU.car: 0.8495, IoU.water: 0.5407, IoU.painting: 0.7381, IoU.sofa: 0.7873, IoU.shelf: 0.4421, IoU.house: 0.4055, IoU.sea: 0.6109, IoU.mirror: 0.7229, IoU.rug: 0.5896, IoU.field: 0.3558, IoU.armchair: 0.5575, IoU.seat: 0.6498, IoU.fence: 0.4560, IoU.desk: 0.5122, IoU.rock: 0.4772, IoU.wardrobe: 0.4996, IoU.lamp: 0.6679, IoU.bathtub: 0.8672, IoU.railing: 0.3754, IoU.cushion: 0.5965, IoU.base: 0.3367, IoU.box: 0.3378, IoU.column: 0.5104, IoU.signboard: 0.3495, IoU.chest of drawers: 0.3757, IoU.counter: 0.4863, IoU.sand: 0.3802, IoU.sink: 0.7680, IoU.skyscraper: 0.4828, IoU.fireplace: 0.6981, IoU.refrigerator: 0.8192, IoU.grandstand: 0.5671, IoU.path: 0.1758, IoU.stairs: 0.3028, IoU.runway: 0.6811, IoU.case: 0.5833, IoU.pool table: 0.9348, IoU.pillow: 0.6055, IoU.screen door: 0.7555, IoU.stairway: 0.4708, IoU.river: 0.2020, IoU.bridge: 0.6796, IoU.bookcase: 0.3608, IoU.blind: 0.4239, IoU.coffee table: 0.6224, IoU.toilet: 0.8866, IoU.flower: 0.4175, IoU.book: 0.4948, IoU.hill: 0.0751, IoU.bench: 0.5345, IoU.countertop: 0.5927, IoU.stove: 0.8228, IoU.palm: 0.4749, IoU.kitchen island: 0.5680, IoU.computer: 0.7527, IoU.swivel chair: 0.4144, IoU.boat: 0.5761, IoU.bar: 0.5843, IoU.arcade machine: 0.7580, IoU.hovel: 0.0844, IoU.bus: 0.9090, IoU.towel: 0.7177, IoU.light: 0.4852, IoU.truck: 0.4314, IoU.tower: 0.1676, IoU.chandelier: 0.6562, IoU.awning: 0.3724, IoU.streetlight: 0.2430, IoU.booth: 0.3575, IoU.television receiver: 0.7172, IoU.airplane: 0.5905, IoU.dirt track: 0.2653, IoU.apparel: 0.5761, IoU.pole: 0.2778, IoU.land: 0.0511, IoU.bannister: 0.1772, IoU.escalator: 0.6190, IoU.ottoman: 0.4901, IoU.bottle: 0.2342, IoU.buffet: 0.5641, IoU.poster: 0.2928, IoU.stage: 0.1180, IoU.van: 0.4452, IoU.ship: 0.0361, IoU.fountain: 0.1563, IoU.conveyer belt: 0.7741, IoU.canopy: 0.5101, IoU.washer: 0.8378, IoU.plaything: 0.3049, IoU.swimming pool: 0.5690, IoU.stool: 0.5051, IoU.barrel: 0.5613, IoU.basket: 0.4055, IoU.waterfall: 0.4890, IoU.tent: 0.9573, IoU.bag: 0.2505, IoU.minibike: 0.7283, IoU.cradle: 0.7981, IoU.oven: 0.6599, IoU.ball: 0.4232, IoU.food: 0.6418, IoU.step: 0.1889, IoU.tank: 0.5279, IoU.trade name: 0.2814, IoU.microwave: 0.8704, IoU.pot: 0.5481, IoU.animal: 0.6987, IoU.bicycle: 0.5883, IoU.lake: 0.6008, IoU.dishwasher: 0.7368, IoU.screen: 0.5987, IoU.blanket: 0.2492, IoU.sculpture: 0.6131, IoU.hood: 0.6009, IoU.sconce: 0.4937, IoU.vase: 0.4216, IoU.traffic light: 0.3257, IoU.tray: 0.1340, IoU.ashcan: 0.5093, IoU.fan: 0.6108, IoU.pier: 0.3963, IoU.crt screen: 0.0504, IoU.plate: 0.5831, IoU.monitor: 0.2129, IoU.bulletin board: 0.5498, IoU.shower: 0.0911, IoU.radiator: 0.5638, IoU.glass: 0.1895, IoU.clock: 0.3177, IoU.flag: 0.6957, Acc.wall: 0.8898, Acc.building: 0.9349, Acc.sky: 0.9683, Acc.floor: 0.9091, Acc.tree: 0.8771, Acc.ceiling: 0.9317, Acc.road: 0.9104, Acc.bed : 0.9613, Acc.windowpane: 0.8403, Acc.grass: 0.8865, Acc.cabinet: 0.7257, Acc.sidewalk: 0.8226, Acc.person: 0.9174, Acc.earth: 0.5127, Acc.door: 0.6938, Acc.table: 0.7534, Acc.mountain: 0.7656, Acc.plant: 0.6420, Acc.curtain: 0.8862, Acc.chair: 0.6963, Acc.car: 0.9293, Acc.water: 0.6782, Acc.painting: 0.8775, Acc.sofa: 0.9030, Acc.shelf: 0.6617, Acc.house: 0.5381, Acc.sea: 0.8299, Acc.mirror: 0.8089, Acc.rug: 0.6681, Acc.field: 0.5679, Acc.armchair: 0.7261, Acc.seat: 0.8778, Acc.fence: 0.6662, Acc.desk: 0.8004, Acc.rock: 0.6510, Acc.wardrobe: 0.7259, Acc.lamp: 0.8089, Acc.bathtub: 0.8956, Acc.railing: 0.5055, Acc.cushion: 0.7279, Acc.base: 0.4367, Acc.box: 0.4424, Acc.column: 0.6153, Acc.signboard: 0.5047, Acc.chest of drawers: 0.6262, Acc.counter: 0.5868, Acc.sand: 0.5234, Acc.sink: 0.8327, Acc.skyscraper: 0.6291, Acc.fireplace: 0.9018, Acc.refrigerator: 0.9134, Acc.grandstand: 0.7466, Acc.path: 0.2296, Acc.stairs: 0.3418, Acc.runway: 0.8680, Acc.case: 0.7052, Acc.pool table: 0.9783, Acc.pillow: 0.7539, Acc.screen door: 0.8577, Acc.stairway: 0.5946, Acc.river: 0.4552, Acc.bridge: 0.8837, Acc.bookcase: 0.5520, Acc.blind: 0.4666, Acc.coffee table: 0.8512, Acc.toilet: 0.9448, Acc.flower: 0.5805, Acc.book: 0.6770, Acc.hill: 0.1042, Acc.bench: 0.6232, Acc.countertop: 0.7542, Acc.stove: 0.9181, Acc.palm: 0.7694, Acc.kitchen island: 0.7364, Acc.computer: 0.9137, Acc.swivel chair: 0.6367, Acc.boat: 0.9099, Acc.bar: 0.6149, Acc.arcade machine: 0.7918, Acc.hovel: 0.0877, Acc.bus: 0.9522, Acc.towel: 0.8440, Acc.light: 0.5796, Acc.truck: 0.6106, Acc.tower: 0.3031, Acc.chandelier: 0.8387, Acc.awning: 0.4509, Acc.streetlight: 0.3008, Acc.booth: 0.3593, Acc.television receiver: 0.8961, Acc.airplane: 0.6584, Acc.dirt track: 0.3523, Acc.apparel: 0.8470, Acc.pole: 0.3394, Acc.land: 0.0608, Acc.bannister: 0.2229, Acc.escalator: 0.7961, Acc.ottoman: 0.7188, Acc.bottle: 0.3117, Acc.buffet: 0.7424, Acc.poster: 0.4133, Acc.stage: 0.1754, Acc.van: 0.5915, Acc.ship: 0.0381, Acc.fountain: 0.1605, Acc.conveyer belt: 0.9481, Acc.canopy: 0.6125, Acc.washer: 0.8829, Acc.plaything: 0.4536, Acc.swimming pool: 0.8117, Acc.stool: 0.6378, Acc.barrel: 0.6629, Acc.basket: 0.5790, Acc.waterfall: 0.5784, Acc.tent: 0.9811, Acc.bag: 0.3193, Acc.minibike: 0.8360, Acc.cradle: 0.9631, Acc.oven: 0.7458, Acc.ball: 0.4478, Acc.food: 0.7023, Acc.step: 0.2336, Acc.tank: 0.6297, Acc.trade name: 0.3381, Acc.microwave: 0.9218, Acc.pot: 0.6283, Acc.animal: 0.7254, Acc.bicycle: 0.7414, Acc.lake: 0.6699, Acc.dishwasher: 0.8239, Acc.screen: 0.9217, Acc.blanket: 0.2921, Acc.sculpture: 0.6839, Acc.hood: 0.7225, Acc.sconce: 0.5774, Acc.vase: 0.5992, Acc.traffic light: 0.5725, Acc.tray: 0.1895, Acc.ashcan: 0.6434, Acc.fan: 0.7292, Acc.pier: 0.4322, Acc.crt screen: 0.1088, Acc.plate: 0.7544, Acc.monitor: 0.2217, Acc.bulletin board: 0.7065, Acc.shower: 0.0948, Acc.radiator: 0.6725, Acc.glass: 0.2114, Acc.clock: 0.3876, Acc.flag: 0.7593 2023-11-03 00:00:42,287 - mmseg - INFO - Iter [14050/20000] lr: 9.640e-07, eta: 2:12:51, time: 2.380, data_time: 1.175, memory: 38534, decode.loss_ce: 0.1789, decode.acc_seg: 92.7059, loss: 0.1789 2023-11-03 00:01:42,764 - mmseg - INFO - Iter [14100/20000] lr: 9.559e-07, eta: 2:11:41, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1650, decode.acc_seg: 93.1150, loss: 0.1650 2023-11-03 00:02:43,300 - mmseg - INFO - Iter [14150/20000] lr: 9.478e-07, eta: 2:10:32, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1633, decode.acc_seg: 93.1789, loss: 0.1633 2023-11-03 00:03:43,811 - mmseg - INFO - Iter [14200/20000] lr: 9.397e-07, eta: 2:09:22, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1618, decode.acc_seg: 93.1885, loss: 0.1618 2023-11-03 00:04:46,631 - mmseg - INFO - Iter [14250/20000] lr: 9.316e-07, eta: 2:08:13, time: 1.256, data_time: 0.052, memory: 38534, decode.loss_ce: 0.1706, decode.acc_seg: 92.9986, loss: 0.1706 2023-11-03 00:05:47,092 - mmseg - INFO - Iter [14300/20000] lr: 9.235e-07, eta: 2:07:04, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1573, decode.acc_seg: 93.3897, loss: 0.1573 2023-11-03 00:06:47,578 - mmseg - INFO - Iter [14350/20000] lr: 9.154e-07, eta: 2:05:55, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1757, decode.acc_seg: 92.6202, loss: 0.1757 2023-11-03 00:07:48,081 - mmseg - INFO - Iter [14400/20000] lr: 9.073e-07, eta: 2:04:45, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1713, decode.acc_seg: 92.7515, loss: 0.1713 2023-11-03 00:08:48,563 - mmseg - INFO - Iter [14450/20000] lr: 8.992e-07, eta: 2:03:36, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1615, decode.acc_seg: 93.3378, loss: 0.1615 2023-11-03 00:09:49,029 - mmseg - INFO - Iter [14500/20000] lr: 8.911e-07, eta: 2:02:27, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1725, decode.acc_seg: 92.7750, loss: 0.1725 2023-11-03 00:10:51,903 - mmseg - INFO - Iter [14550/20000] lr: 8.830e-07, eta: 2:01:18, time: 1.257, data_time: 0.054, memory: 38534, decode.loss_ce: 0.1668, decode.acc_seg: 92.9563, loss: 0.1668 2023-11-03 00:11:52,389 - mmseg - INFO - Iter [14600/20000] lr: 8.749e-07, eta: 2:00:09, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1625, decode.acc_seg: 93.2020, loss: 0.1625 2023-11-03 00:12:52,872 - mmseg - INFO - Iter [14650/20000] lr: 8.668e-07, eta: 1:59:00, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1672, decode.acc_seg: 93.0136, loss: 0.1672 2023-11-03 00:13:53,404 - mmseg - INFO - Iter [14700/20000] lr: 8.587e-07, eta: 1:57:51, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1642, decode.acc_seg: 92.9813, loss: 0.1642 2023-11-03 00:14:53,872 - mmseg - INFO - Iter [14750/20000] lr: 8.506e-07, eta: 1:56:42, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1710, decode.acc_seg: 93.0378, loss: 0.1710 2023-11-03 00:15:58,813 - mmseg - INFO - Iter [14800/20000] lr: 8.425e-07, eta: 1:55:35, time: 1.299, data_time: 0.095, memory: 38534, decode.loss_ce: 0.1613, decode.acc_seg: 93.3383, loss: 0.1613 2023-11-03 00:16:59,318 - mmseg - INFO - Iter [14850/20000] lr: 8.344e-07, eta: 1:54:26, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1766, decode.acc_seg: 92.5557, loss: 0.1766 2023-11-03 00:18:02,259 - mmseg - INFO - Iter [14900/20000] lr: 8.263e-07, eta: 1:53:18, time: 1.259, data_time: 0.053, memory: 38534, decode.loss_ce: 0.1653, decode.acc_seg: 93.0730, loss: 0.1653 2023-11-03 00:19:02,731 - mmseg - INFO - Iter [14950/20000] lr: 8.182e-07, eta: 1:52:10, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1650, decode.acc_seg: 93.0623, loss: 0.1650 2023-11-03 00:20:03,238 - mmseg - INFO - Saving checkpoint at 15000 iterations 2023-11-03 00:21:02,176 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-03 00:21:02,176 - mmseg - INFO - Iter [15000/20000] lr: 8.101e-07, eta: 1:51:21, time: 2.389, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1719, decode.acc_seg: 93.0172, loss: 0.1719 2023-11-03 00:22:06,923 - mmseg - INFO - per class results: 2023-11-03 00:22:06,928 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 80.3 | 89.5 | | building | 83.5 | 93.05 | | sky | 93.96 | 97.23 | | floor | 82.91 | 91.01 | | tree | 74.07 | 89.37 | | ceiling | 85.46 | 93.98 | | road | 83.96 | 91.05 | | bed | 91.43 | 96.52 | | windowpane | 64.98 | 79.74 | | grass | 70.96 | 89.31 | | cabinet | 63.72 | 74.89 | | sidewalk | 66.11 | 80.92 | | person | 82.12 | 92.36 | | earth | 37.19 | 49.3 | | door | 57.53 | 73.54 | | table | 66.9 | 77.74 | | mountain | 61.63 | 77.35 | | plant | 52.88 | 64.71 | | curtain | 77.81 | 87.49 | | chair | 59.83 | 71.13 | | car | 85.24 | 92.43 | | water | 60.98 | 77.39 | | painting | 73.87 | 87.54 | | sofa | 80.26 | 89.95 | | shelf | 42.74 | 59.24 | | house | 41.74 | 54.02 | | sea | 63.67 | 78.62 | | mirror | 74.56 | 82.6 | | rug | 65.83 | 74.76 | | field | 31.26 | 47.03 | | armchair | 57.86 | 76.81 | | seat | 64.13 | 87.77 | | fence | 46.29 | 61.71 | | desk | 51.94 | 80.51 | | rock | 41.4 | 51.38 | | wardrobe | 49.9 | 67.9 | | lamp | 67.13 | 79.54 | | bathtub | 85.91 | 87.81 | | railing | 42.38 | 58.19 | | cushion | 60.21 | 73.64 | | base | 35.47 | 48.01 | | box | 33.7 | 48.39 | | column | 51.46 | 64.85 | | signboard | 36.67 | 53.88 | | chest of drawers | 39.33 | 65.64 | | counter | 53.07 | 63.29 | | sand | 38.61 | 51.93 | | sink | 76.55 | 82.09 | | skyscraper | 49.06 | 58.87 | | fireplace | 69.55 | 90.43 | | refrigerator | 83.84 | 90.58 | | grandstand | 49.83 | 74.82 | | path | 17.52 | 24.23 | | stairs | 21.59 | 24.25 | | runway | 68.25 | 87.47 | | case | 57.36 | 71.3 | | pool table | 93.74 | 97.57 | | pillow | 60.83 | 74.23 | | screen door | 72.6 | 78.04 | | stairway | 38.98 | 60.89 | | river | 15.87 | 28.93 | | bridge | 77.42 | 89.33 | | bookcase | 32.59 | 50.77 | | blind | 42.12 | 45.76 | | coffee table | 64.28 | 83.01 | | toilet | 88.67 | 91.57 | | flower | 40.0 | 52.24 | | book | 48.87 | 71.68 | | hill | 7.53 | 11.35 | | bench | 49.63 | 56.94 | | countertop | 59.24 | 75.03 | | stove | 81.87 | 88.4 | | palm | 43.62 | 64.71 | | kitchen island | 56.09 | 73.09 | | computer | 76.95 | 89.26 | | swivel chair | 44.39 | 63.11 | | boat | 51.74 | 90.69 | | bar | 62.04 | 70.61 | | arcade machine | 75.93 | 77.96 | | hovel | 14.26 | 14.7 | | bus | 90.99 | 95.8 | | towel | 71.42 | 81.61 | | light | 47.25 | 55.21 | | truck | 44.61 | 58.69 | | tower | 9.84 | 17.24 | | chandelier | 64.33 | 79.15 | | awning | 37.87 | 47.68 | | streetlight | 24.2 | 30.31 | | booth | 35.66 | 35.86 | | television receiver | 73.68 | 86.63 | | airplane | 59.45 | 64.9 | | dirt track | 23.15 | 34.7 | | apparel | 57.46 | 82.85 | | pole | 23.32 | 28.06 | | land | 4.53 | 6.19 | | bannister | 18.92 | 25.5 | | escalator | 59.02 | 75.06 | | ottoman | 47.37 | 66.52 | | bottle | 22.76 | 29.16 | | buffet | 52.47 | 65.46 | | poster | 30.5 | 39.33 | | stage | 12.35 | 22.72 | | van | 46.25 | 65.74 | | ship | 5.67 | 5.87 | | fountain | 27.25 | 28.15 | | conveyer belt | 79.71 | 94.99 | | canopy | 53.61 | 64.26 | | washer | 80.94 | 83.87 | | plaything | 31.74 | 44.08 | | swimming pool | 55.77 | 85.33 | | stool | 48.67 | 66.39 | | barrel | 55.54 | 66.57 | | basket | 38.48 | 50.36 | | waterfall | 54.02 | 66.66 | | tent | 95.83 | 98.21 | | bag | 25.94 | 31.69 | | minibike | 72.04 | 85.46 | | cradle | 85.62 | 96.05 | | oven | 64.29 | 77.23 | | ball | 30.78 | 31.9 | | food | 65.54 | 72.63 | | step | 18.65 | 23.89 | | tank | 52.18 | 63.09 | | trade name | 28.6 | 35.47 | | microwave | 84.88 | 92.49 | | pot | 52.83 | 60.26 | | animal | 70.44 | 73.34 | | bicycle | 56.52 | 68.17 | | lake | 50.48 | 66.93 | | dishwasher | 72.7 | 82.31 | | screen | 59.94 | 90.86 | | blanket | 21.68 | 24.24 | | sculpture | 61.55 | 67.55 | | hood | 59.9 | 70.89 | | sconce | 51.05 | 60.23 | | vase | 43.22 | 57.67 | | traffic light | 33.33 | 54.72 | | tray | 10.21 | 15.3 | | ashcan | 52.44 | 62.71 | | fan | 59.75 | 69.6 | | pier | 40.03 | 44.34 | | crt screen | 6.79 | 15.12 | | plate | 58.5 | 72.01 | | monitor | 20.95 | 22.2 | | bulletin board | 57.59 | 74.13 | | shower | 6.77 | 6.88 | | radiator | 57.51 | 66.73 | | glass | 17.63 | 18.99 | | clock | 32.83 | 38.82 | | flag | 68.85 | 76.38 | +---------------------+-------+-------+ 2023-11-03 00:22:06,928 - mmseg - INFO - Summary: 2023-11-03 00:22:06,929 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 84.62 | 52.95 | 64.32 | +-------+-------+-------+ 2023-11-03 00:22:06,929 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-03 00:22:06,930 - mmseg - INFO - Iter(val) [250] aAcc: 0.8462, mIoU: 0.5295, mAcc: 0.6432, IoU.wall: 0.8030, IoU.building: 0.8350, IoU.sky: 0.9396, IoU.floor: 0.8291, IoU.tree: 0.7407, IoU.ceiling: 0.8546, IoU.road: 0.8396, IoU.bed : 0.9143, IoU.windowpane: 0.6498, IoU.grass: 0.7096, IoU.cabinet: 0.6372, IoU.sidewalk: 0.6611, IoU.person: 0.8212, IoU.earth: 0.3719, IoU.door: 0.5753, IoU.table: 0.6690, IoU.mountain: 0.6163, IoU.plant: 0.5288, IoU.curtain: 0.7781, IoU.chair: 0.5983, IoU.car: 0.8524, IoU.water: 0.6098, IoU.painting: 0.7387, IoU.sofa: 0.8026, IoU.shelf: 0.4274, IoU.house: 0.4174, IoU.sea: 0.6367, IoU.mirror: 0.7456, IoU.rug: 0.6583, IoU.field: 0.3126, IoU.armchair: 0.5786, IoU.seat: 0.6413, IoU.fence: 0.4629, IoU.desk: 0.5194, IoU.rock: 0.4140, IoU.wardrobe: 0.4990, IoU.lamp: 0.6713, IoU.bathtub: 0.8591, IoU.railing: 0.4238, IoU.cushion: 0.6021, IoU.base: 0.3547, IoU.box: 0.3370, IoU.column: 0.5146, IoU.signboard: 0.3667, IoU.chest of drawers: 0.3933, IoU.counter: 0.5307, IoU.sand: 0.3861, IoU.sink: 0.7655, IoU.skyscraper: 0.4906, IoU.fireplace: 0.6955, IoU.refrigerator: 0.8384, IoU.grandstand: 0.4983, IoU.path: 0.1752, IoU.stairs: 0.2159, IoU.runway: 0.6825, IoU.case: 0.5736, IoU.pool table: 0.9374, IoU.pillow: 0.6083, IoU.screen door: 0.7260, IoU.stairway: 0.3898, IoU.river: 0.1587, IoU.bridge: 0.7742, IoU.bookcase: 0.3259, IoU.blind: 0.4212, IoU.coffee table: 0.6428, IoU.toilet: 0.8867, IoU.flower: 0.4000, IoU.book: 0.4887, IoU.hill: 0.0753, IoU.bench: 0.4963, IoU.countertop: 0.5924, IoU.stove: 0.8187, IoU.palm: 0.4362, IoU.kitchen island: 0.5609, IoU.computer: 0.7695, IoU.swivel chair: 0.4439, IoU.boat: 0.5174, IoU.bar: 0.6204, IoU.arcade machine: 0.7593, IoU.hovel: 0.1426, IoU.bus: 0.9099, IoU.towel: 0.7142, IoU.light: 0.4725, IoU.truck: 0.4461, IoU.tower: 0.0984, IoU.chandelier: 0.6433, IoU.awning: 0.3787, IoU.streetlight: 0.2420, IoU.booth: 0.3566, IoU.television receiver: 0.7368, IoU.airplane: 0.5945, IoU.dirt track: 0.2315, IoU.apparel: 0.5746, IoU.pole: 0.2332, IoU.land: 0.0453, IoU.bannister: 0.1892, IoU.escalator: 0.5902, IoU.ottoman: 0.4737, IoU.bottle: 0.2276, IoU.buffet: 0.5247, IoU.poster: 0.3050, IoU.stage: 0.1235, IoU.van: 0.4625, IoU.ship: 0.0567, IoU.fountain: 0.2725, IoU.conveyer belt: 0.7971, IoU.canopy: 0.5361, IoU.washer: 0.8094, IoU.plaything: 0.3174, IoU.swimming pool: 0.5577, IoU.stool: 0.4867, IoU.barrel: 0.5554, IoU.basket: 0.3848, IoU.waterfall: 0.5402, IoU.tent: 0.9583, IoU.bag: 0.2594, IoU.minibike: 0.7204, IoU.cradle: 0.8562, IoU.oven: 0.6429, IoU.ball: 0.3078, IoU.food: 0.6554, IoU.step: 0.1865, IoU.tank: 0.5218, IoU.trade name: 0.2860, IoU.microwave: 0.8488, IoU.pot: 0.5283, IoU.animal: 0.7044, IoU.bicycle: 0.5652, IoU.lake: 0.5048, IoU.dishwasher: 0.7270, IoU.screen: 0.5994, IoU.blanket: 0.2168, IoU.sculpture: 0.6155, IoU.hood: 0.5990, IoU.sconce: 0.5105, IoU.vase: 0.4322, IoU.traffic light: 0.3333, IoU.tray: 0.1021, IoU.ashcan: 0.5244, IoU.fan: 0.5975, IoU.pier: 0.4003, IoU.crt screen: 0.0679, IoU.plate: 0.5850, IoU.monitor: 0.2095, IoU.bulletin board: 0.5759, IoU.shower: 0.0677, IoU.radiator: 0.5751, IoU.glass: 0.1763, IoU.clock: 0.3283, IoU.flag: 0.6885, Acc.wall: 0.8950, Acc.building: 0.9305, Acc.sky: 0.9723, Acc.floor: 0.9101, Acc.tree: 0.8937, Acc.ceiling: 0.9398, Acc.road: 0.9105, Acc.bed : 0.9652, Acc.windowpane: 0.7974, Acc.grass: 0.8931, Acc.cabinet: 0.7489, Acc.sidewalk: 0.8092, Acc.person: 0.9236, Acc.earth: 0.4930, Acc.door: 0.7354, Acc.table: 0.7774, Acc.mountain: 0.7735, Acc.plant: 0.6471, Acc.curtain: 0.8749, Acc.chair: 0.7113, Acc.car: 0.9243, Acc.water: 0.7739, Acc.painting: 0.8754, Acc.sofa: 0.8995, Acc.shelf: 0.5924, Acc.house: 0.5402, Acc.sea: 0.7862, Acc.mirror: 0.8260, Acc.rug: 0.7476, Acc.field: 0.4703, Acc.armchair: 0.7681, Acc.seat: 0.8777, Acc.fence: 0.6171, Acc.desk: 0.8051, Acc.rock: 0.5138, Acc.wardrobe: 0.6790, Acc.lamp: 0.7954, Acc.bathtub: 0.8781, Acc.railing: 0.5819, Acc.cushion: 0.7364, Acc.base: 0.4801, Acc.box: 0.4839, Acc.column: 0.6485, Acc.signboard: 0.5388, Acc.chest of drawers: 0.6564, Acc.counter: 0.6329, Acc.sand: 0.5193, Acc.sink: 0.8209, Acc.skyscraper: 0.5887, Acc.fireplace: 0.9043, Acc.refrigerator: 0.9058, Acc.grandstand: 0.7482, Acc.path: 0.2423, Acc.stairs: 0.2425, Acc.runway: 0.8747, Acc.case: 0.7130, Acc.pool table: 0.9757, Acc.pillow: 0.7423, Acc.screen door: 0.7804, Acc.stairway: 0.6089, Acc.river: 0.2893, Acc.bridge: 0.8933, Acc.bookcase: 0.5077, Acc.blind: 0.4576, Acc.coffee table: 0.8301, Acc.toilet: 0.9157, Acc.flower: 0.5224, Acc.book: 0.7168, Acc.hill: 0.1135, Acc.bench: 0.5694, Acc.countertop: 0.7503, Acc.stove: 0.8840, Acc.palm: 0.6471, Acc.kitchen island: 0.7309, Acc.computer: 0.8926, Acc.swivel chair: 0.6311, Acc.boat: 0.9069, Acc.bar: 0.7061, Acc.arcade machine: 0.7796, Acc.hovel: 0.1470, Acc.bus: 0.9580, Acc.towel: 0.8161, Acc.light: 0.5521, Acc.truck: 0.5869, Acc.tower: 0.1724, Acc.chandelier: 0.7915, Acc.awning: 0.4768, Acc.streetlight: 0.3031, Acc.booth: 0.3586, Acc.television receiver: 0.8663, Acc.airplane: 0.6490, Acc.dirt track: 0.3470, Acc.apparel: 0.8285, Acc.pole: 0.2806, Acc.land: 0.0619, Acc.bannister: 0.2550, Acc.escalator: 0.7506, Acc.ottoman: 0.6652, Acc.bottle: 0.2916, Acc.buffet: 0.6546, Acc.poster: 0.3933, Acc.stage: 0.2272, Acc.van: 0.6574, Acc.ship: 0.0587, Acc.fountain: 0.2815, Acc.conveyer belt: 0.9499, Acc.canopy: 0.6426, Acc.washer: 0.8387, Acc.plaything: 0.4408, Acc.swimming pool: 0.8533, Acc.stool: 0.6639, Acc.barrel: 0.6657, Acc.basket: 0.5036, Acc.waterfall: 0.6666, Acc.tent: 0.9821, Acc.bag: 0.3169, Acc.minibike: 0.8546, Acc.cradle: 0.9605, Acc.oven: 0.7723, Acc.ball: 0.3190, Acc.food: 0.7263, Acc.step: 0.2389, Acc.tank: 0.6309, Acc.trade name: 0.3547, Acc.microwave: 0.9249, Acc.pot: 0.6026, Acc.animal: 0.7334, Acc.bicycle: 0.6817, Acc.lake: 0.6693, Acc.dishwasher: 0.8231, Acc.screen: 0.9086, Acc.blanket: 0.2424, Acc.sculpture: 0.6755, Acc.hood: 0.7089, Acc.sconce: 0.6023, Acc.vase: 0.5767, Acc.traffic light: 0.5472, Acc.tray: 0.1530, Acc.ashcan: 0.6271, Acc.fan: 0.6960, Acc.pier: 0.4434, Acc.crt screen: 0.1512, Acc.plate: 0.7201, Acc.monitor: 0.2220, Acc.bulletin board: 0.7413, Acc.shower: 0.0688, Acc.radiator: 0.6673, Acc.glass: 0.1899, Acc.clock: 0.3882, Acc.flag: 0.7638 2023-11-03 00:23:07,482 - mmseg - INFO - Iter [15050/20000] lr: 8.020e-07, eta: 1:50:33, time: 2.506, data_time: 1.302, memory: 38534, decode.loss_ce: 0.1719, decode.acc_seg: 92.9629, loss: 0.1719 2023-11-03 00:24:07,940 - mmseg - INFO - Iter [15100/20000] lr: 7.939e-07, eta: 1:49:24, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1609, decode.acc_seg: 93.1867, loss: 0.1609 2023-11-03 00:25:08,420 - mmseg - INFO - Iter [15150/20000] lr: 7.858e-07, eta: 1:48:15, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1580, decode.acc_seg: 93.3189, loss: 0.1580 2023-11-03 00:26:11,300 - mmseg - INFO - Iter [15200/20000] lr: 7.777e-07, eta: 1:47:07, time: 1.258, data_time: 0.054, memory: 38534, decode.loss_ce: 0.1631, decode.acc_seg: 93.0787, loss: 0.1631 2023-11-03 00:27:11,752 - mmseg - INFO - Iter [15250/20000] lr: 7.696e-07, eta: 1:45:58, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1570, decode.acc_seg: 93.3567, loss: 0.1570 2023-11-03 00:28:12,287 - mmseg - INFO - Iter [15300/20000] lr: 7.615e-07, eta: 1:44:49, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1624, decode.acc_seg: 93.1994, loss: 0.1624 2023-11-03 00:29:12,763 - mmseg - INFO - Iter [15350/20000] lr: 7.534e-07, eta: 1:43:40, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1722, decode.acc_seg: 92.8515, loss: 0.1722 2023-11-03 00:30:13,253 - mmseg - INFO - Iter [15400/20000] lr: 7.453e-07, eta: 1:42:31, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1670, decode.acc_seg: 93.0797, loss: 0.1670 2023-11-03 00:31:13,751 - mmseg - INFO - Iter [15450/20000] lr: 7.372e-07, eta: 1:41:22, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1687, decode.acc_seg: 92.9243, loss: 0.1687 2023-11-03 00:32:16,685 - mmseg - INFO - Iter [15500/20000] lr: 7.291e-07, eta: 1:40:14, time: 1.259, data_time: 0.052, memory: 38534, decode.loss_ce: 0.1590, decode.acc_seg: 93.2323, loss: 0.1590 2023-11-03 00:33:17,171 - mmseg - INFO - Iter [15550/20000] lr: 7.210e-07, eta: 1:39:06, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1628, decode.acc_seg: 93.2639, loss: 0.1628 2023-11-03 00:34:17,643 - mmseg - INFO - Iter [15600/20000] lr: 7.129e-07, eta: 1:37:57, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1657, decode.acc_seg: 93.1438, loss: 0.1657 2023-11-03 00:35:18,107 - mmseg - INFO - Iter [15650/20000] lr: 7.048e-07, eta: 1:36:48, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1620, decode.acc_seg: 93.2948, loss: 0.1620 2023-11-03 00:36:18,616 - mmseg - INFO - Iter [15700/20000] lr: 6.967e-07, eta: 1:35:40, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1571, decode.acc_seg: 93.3951, loss: 0.1571 2023-11-03 00:37:19,101 - mmseg - INFO - Iter [15750/20000] lr: 6.886e-07, eta: 1:34:32, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1596, decode.acc_seg: 93.2564, loss: 0.1596 2023-11-03 00:38:19,582 - mmseg - INFO - Iter [15800/20000] lr: 6.805e-07, eta: 1:33:23, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1642, decode.acc_seg: 93.2647, loss: 0.1642 2023-11-03 00:39:22,955 - mmseg - INFO - Iter [15850/20000] lr: 6.724e-07, eta: 1:32:16, time: 1.267, data_time: 0.061, memory: 38534, decode.loss_ce: 0.1586, decode.acc_seg: 93.4807, loss: 0.1586 2023-11-03 00:40:23,467 - mmseg - INFO - Iter [15900/20000] lr: 6.643e-07, eta: 1:31:07, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1545, decode.acc_seg: 93.4676, loss: 0.1545 2023-11-03 00:41:23,958 - mmseg - INFO - Iter [15950/20000] lr: 6.562e-07, eta: 1:29:59, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1532, decode.acc_seg: 93.6003, loss: 0.1532 2023-11-03 00:42:24,451 - mmseg - INFO - Saving checkpoint at 16000 iterations 2023-11-03 00:43:26,474 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-03 00:43:26,474 - mmseg - INFO - Iter [16000/20000] lr: 6.481e-07, eta: 1:29:06, time: 2.450, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1680, decode.acc_seg: 92.8056, loss: 0.1680 2023-11-03 00:44:26,430 - mmseg - INFO - per class results: 2023-11-03 00:44:26,436 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 80.44 | 89.06 | | building | 83.34 | 92.89 | | sky | 94.04 | 97.16 | | floor | 82.69 | 90.86 | | tree | 74.76 | 87.6 | | ceiling | 85.38 | 93.32 | | road | 84.65 | 91.63 | | bed | 91.5 | 96.64 | | windowpane | 65.52 | 80.26 | | grass | 69.4 | 86.5 | | cabinet | 63.53 | 74.89 | | sidewalk | 67.46 | 83.08 | | person | 82.22 | 92.22 | | earth | 37.2 | 48.86 | | door | 57.65 | 73.92 | | table | 66.7 | 77.44 | | mountain | 61.98 | 78.91 | | plant | 53.43 | 68.25 | | curtain | 78.64 | 88.6 | | chair | 60.49 | 73.95 | | car | 85.13 | 91.75 | | water | 57.99 | 72.21 | | painting | 74.38 | 87.12 | | sofa | 79.8 | 91.15 | | shelf | 44.0 | 65.63 | | house | 41.77 | 57.16 | | sea | 61.54 | 83.39 | | mirror | 74.46 | 82.18 | | rug | 61.17 | 68.16 | | field | 30.33 | 53.37 | | armchair | 59.01 | 74.27 | | seat | 62.82 | 90.44 | | fence | 45.89 | 62.24 | | desk | 52.78 | 78.99 | | rock | 44.07 | 55.42 | | wardrobe | 51.18 | 68.89 | | lamp | 66.99 | 80.82 | | bathtub | 85.89 | 88.6 | | railing | 41.33 | 57.13 | | cushion | 60.67 | 74.07 | | base | 33.0 | 43.68 | | box | 33.67 | 45.56 | | column | 50.64 | 62.17 | | signboard | 36.4 | 52.0 | | chest of drawers | 39.11 | 61.28 | | counter | 53.01 | 67.75 | | sand | 37.92 | 52.3 | | sink | 76.33 | 84.54 | | skyscraper | 48.41 | 61.39 | | fireplace | 69.57 | 88.44 | | refrigerator | 81.06 | 91.01 | | grandstand | 55.01 | 76.94 | | path | 19.43 | 25.66 | | stairs | 28.0 | 33.01 | | runway | 66.99 | 85.16 | | case | 59.12 | 64.11 | | pool table | 93.66 | 97.63 | | pillow | 61.26 | 74.65 | | screen door | 73.29 | 78.4 | | stairway | 44.87 | 63.99 | | river | 16.39 | 29.95 | | bridge | 78.15 | 90.25 | | bookcase | 37.56 | 55.29 | | blind | 44.54 | 50.07 | | coffee table | 64.24 | 85.46 | | toilet | 89.05 | 93.71 | | flower | 40.48 | 54.4 | | book | 49.71 | 67.57 | | hill | 8.33 | 12.69 | | bench | 49.5 | 57.99 | | countertop | 57.52 | 74.91 | | stove | 81.2 | 89.58 | | palm | 47.44 | 80.21 | | kitchen island | 52.84 | 64.12 | | computer | 75.95 | 89.44 | | swivel chair | 44.06 | 66.97 | | boat | 52.74 | 90.66 | | bar | 56.09 | 60.19 | | arcade machine | 78.14 | 80.28 | | hovel | 17.08 | 17.94 | | bus | 90.82 | 95.7 | | towel | 71.24 | 85.0 | | light | 49.4 | 60.37 | | truck | 44.88 | 59.68 | | tower | 9.79 | 17.92 | | chandelier | 64.43 | 77.9 | | awning | 35.85 | 46.02 | | streetlight | 25.87 | 32.65 | | booth | 34.79 | 35.53 | | television receiver | 73.92 | 86.88 | | airplane | 59.9 | 65.87 | | dirt track | 23.83 | 33.67 | | apparel | 58.76 | 83.72 | | pole | 26.85 | 32.62 | | land | 4.57 | 6.54 | | bannister | 19.46 | 26.37 | | escalator | 63.81 | 80.2 | | ottoman | 48.76 | 71.33 | | bottle | 23.55 | 31.89 | | buffet | 52.72 | 66.82 | | poster | 29.62 | 41.34 | | stage | 12.98 | 21.65 | | van | 46.05 | 65.01 | | ship | 6.39 | 6.66 | | fountain | 19.62 | 20.08 | | conveyer belt | 79.16 | 94.52 | | canopy | 51.3 | 63.96 | | washer | 82.4 | 85.27 | | plaything | 31.23 | 45.56 | | swimming pool | 56.54 | 87.1 | | stool | 49.94 | 68.17 | | barrel | 56.63 | 65.2 | | basket | 39.84 | 54.76 | | waterfall | 54.91 | 67.69 | | tent | 93.08 | 98.37 | | bag | 24.92 | 30.73 | | minibike | 71.74 | 85.08 | | cradle | 83.22 | 97.01 | | oven | 64.67 | 77.49 | | ball | 44.42 | 46.59 | | food | 65.5 | 75.1 | | step | 18.18 | 23.59 | | tank | 51.91 | 62.16 | | trade name | 28.86 | 35.11 | | microwave | 85.22 | 94.32 | | pot | 52.24 | 60.15 | | animal | 70.59 | 73.0 | | bicycle | 59.67 | 75.7 | | lake | 50.13 | 65.06 | | dishwasher | 73.94 | 82.26 | | screen | 59.14 | 91.21 | | blanket | 19.19 | 21.36 | | sculpture | 60.87 | 68.14 | | hood | 58.94 | 69.48 | | sconce | 52.3 | 63.98 | | vase | 42.47 | 62.43 | | traffic light | 32.42 | 58.34 | | tray | 14.45 | 19.81 | | ashcan | 52.46 | 63.85 | | fan | 60.6 | 72.26 | | pier | 39.44 | 43.22 | | crt screen | 6.48 | 13.85 | | plate | 58.42 | 75.51 | | monitor | 21.94 | 23.42 | | bulletin board | 57.15 | 69.36 | | shower | 8.39 | 10.55 | | radiator | 57.53 | 69.06 | | glass | 19.96 | 23.18 | | clock | 33.34 | 40.21 | | flag | 68.27 | 76.39 | +---------------------+-------+-------+ 2023-11-03 00:44:26,436 - mmseg - INFO - Summary: 2023-11-03 00:44:26,436 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 84.61 | 53.24 | 65.14 | +-------+-------+-------+ 2023-11-03 00:44:26,437 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-03 00:44:26,437 - mmseg - INFO - Iter(val) [250] aAcc: 0.8461, mIoU: 0.5324, mAcc: 0.6514, IoU.wall: 0.8044, IoU.building: 0.8334, IoU.sky: 0.9404, IoU.floor: 0.8269, IoU.tree: 0.7476, IoU.ceiling: 0.8538, IoU.road: 0.8465, IoU.bed : 0.9150, IoU.windowpane: 0.6552, IoU.grass: 0.6940, IoU.cabinet: 0.6353, IoU.sidewalk: 0.6746, IoU.person: 0.8222, IoU.earth: 0.3720, IoU.door: 0.5765, IoU.table: 0.6670, IoU.mountain: 0.6198, IoU.plant: 0.5343, IoU.curtain: 0.7864, IoU.chair: 0.6049, IoU.car: 0.8513, IoU.water: 0.5799, IoU.painting: 0.7438, IoU.sofa: 0.7980, IoU.shelf: 0.4400, IoU.house: 0.4177, IoU.sea: 0.6154, IoU.mirror: 0.7446, IoU.rug: 0.6117, IoU.field: 0.3033, IoU.armchair: 0.5901, IoU.seat: 0.6282, IoU.fence: 0.4589, IoU.desk: 0.5278, IoU.rock: 0.4407, IoU.wardrobe: 0.5118, IoU.lamp: 0.6699, IoU.bathtub: 0.8589, IoU.railing: 0.4133, IoU.cushion: 0.6067, IoU.base: 0.3300, IoU.box: 0.3367, IoU.column: 0.5064, IoU.signboard: 0.3640, IoU.chest of drawers: 0.3911, IoU.counter: 0.5301, IoU.sand: 0.3792, IoU.sink: 0.7633, IoU.skyscraper: 0.4841, IoU.fireplace: 0.6957, IoU.refrigerator: 0.8106, IoU.grandstand: 0.5501, IoU.path: 0.1943, IoU.stairs: 0.2800, IoU.runway: 0.6699, IoU.case: 0.5912, IoU.pool table: 0.9366, IoU.pillow: 0.6126, IoU.screen door: 0.7329, IoU.stairway: 0.4487, IoU.river: 0.1639, IoU.bridge: 0.7815, IoU.bookcase: 0.3756, IoU.blind: 0.4454, IoU.coffee table: 0.6424, IoU.toilet: 0.8905, IoU.flower: 0.4048, IoU.book: 0.4971, IoU.hill: 0.0833, IoU.bench: 0.4950, IoU.countertop: 0.5752, IoU.stove: 0.8120, IoU.palm: 0.4744, IoU.kitchen island: 0.5284, IoU.computer: 0.7595, IoU.swivel chair: 0.4406, IoU.boat: 0.5274, IoU.bar: 0.5609, IoU.arcade machine: 0.7814, IoU.hovel: 0.1708, IoU.bus: 0.9082, IoU.towel: 0.7124, IoU.light: 0.4940, IoU.truck: 0.4488, IoU.tower: 0.0979, IoU.chandelier: 0.6443, IoU.awning: 0.3585, IoU.streetlight: 0.2587, IoU.booth: 0.3479, IoU.television receiver: 0.7392, IoU.airplane: 0.5990, IoU.dirt track: 0.2383, IoU.apparel: 0.5876, IoU.pole: 0.2685, IoU.land: 0.0457, IoU.bannister: 0.1946, IoU.escalator: 0.6381, IoU.ottoman: 0.4876, IoU.bottle: 0.2355, IoU.buffet: 0.5272, IoU.poster: 0.2962, IoU.stage: 0.1298, IoU.van: 0.4605, IoU.ship: 0.0639, IoU.fountain: 0.1962, IoU.conveyer belt: 0.7916, IoU.canopy: 0.5130, IoU.washer: 0.8240, IoU.plaything: 0.3123, IoU.swimming pool: 0.5654, IoU.stool: 0.4994, IoU.barrel: 0.5663, IoU.basket: 0.3984, IoU.waterfall: 0.5491, IoU.tent: 0.9308, IoU.bag: 0.2492, IoU.minibike: 0.7174, IoU.cradle: 0.8322, IoU.oven: 0.6467, IoU.ball: 0.4442, IoU.food: 0.6550, IoU.step: 0.1818, IoU.tank: 0.5191, IoU.trade name: 0.2886, IoU.microwave: 0.8522, IoU.pot: 0.5224, IoU.animal: 0.7059, IoU.bicycle: 0.5967, IoU.lake: 0.5013, IoU.dishwasher: 0.7394, IoU.screen: 0.5914, IoU.blanket: 0.1919, IoU.sculpture: 0.6087, IoU.hood: 0.5894, IoU.sconce: 0.5230, IoU.vase: 0.4247, IoU.traffic light: 0.3242, IoU.tray: 0.1445, IoU.ashcan: 0.5246, IoU.fan: 0.6060, IoU.pier: 0.3944, IoU.crt screen: 0.0648, IoU.plate: 0.5842, IoU.monitor: 0.2194, IoU.bulletin board: 0.5715, IoU.shower: 0.0839, IoU.radiator: 0.5753, IoU.glass: 0.1996, IoU.clock: 0.3334, IoU.flag: 0.6827, Acc.wall: 0.8906, Acc.building: 0.9289, Acc.sky: 0.9716, Acc.floor: 0.9086, Acc.tree: 0.8760, Acc.ceiling: 0.9332, Acc.road: 0.9163, Acc.bed : 0.9664, Acc.windowpane: 0.8026, Acc.grass: 0.8650, Acc.cabinet: 0.7489, Acc.sidewalk: 0.8308, Acc.person: 0.9222, Acc.earth: 0.4886, Acc.door: 0.7392, Acc.table: 0.7744, Acc.mountain: 0.7891, Acc.plant: 0.6825, Acc.curtain: 0.8860, Acc.chair: 0.7395, Acc.car: 0.9175, Acc.water: 0.7221, Acc.painting: 0.8712, Acc.sofa: 0.9115, Acc.shelf: 0.6563, Acc.house: 0.5716, Acc.sea: 0.8339, Acc.mirror: 0.8218, Acc.rug: 0.6816, Acc.field: 0.5337, Acc.armchair: 0.7427, Acc.seat: 0.9044, Acc.fence: 0.6224, Acc.desk: 0.7899, Acc.rock: 0.5542, Acc.wardrobe: 0.6889, Acc.lamp: 0.8082, Acc.bathtub: 0.8860, Acc.railing: 0.5713, Acc.cushion: 0.7407, Acc.base: 0.4368, Acc.box: 0.4556, Acc.column: 0.6217, Acc.signboard: 0.5200, Acc.chest of drawers: 0.6128, Acc.counter: 0.6775, Acc.sand: 0.5230, Acc.sink: 0.8454, Acc.skyscraper: 0.6139, Acc.fireplace: 0.8844, Acc.refrigerator: 0.9101, Acc.grandstand: 0.7694, Acc.path: 0.2566, Acc.stairs: 0.3301, Acc.runway: 0.8516, Acc.case: 0.6411, Acc.pool table: 0.9763, Acc.pillow: 0.7465, Acc.screen door: 0.7840, Acc.stairway: 0.6399, Acc.river: 0.2995, Acc.bridge: 0.9025, Acc.bookcase: 0.5529, Acc.blind: 0.5007, Acc.coffee table: 0.8546, Acc.toilet: 0.9371, Acc.flower: 0.5440, Acc.book: 0.6757, Acc.hill: 0.1269, Acc.bench: 0.5799, Acc.countertop: 0.7491, Acc.stove: 0.8958, Acc.palm: 0.8021, Acc.kitchen island: 0.6412, Acc.computer: 0.8944, Acc.swivel chair: 0.6697, Acc.boat: 0.9066, Acc.bar: 0.6019, Acc.arcade machine: 0.8028, Acc.hovel: 0.1794, Acc.bus: 0.9570, Acc.towel: 0.8500, Acc.light: 0.6037, Acc.truck: 0.5968, Acc.tower: 0.1792, Acc.chandelier: 0.7790, Acc.awning: 0.4602, Acc.streetlight: 0.3265, Acc.booth: 0.3553, Acc.television receiver: 0.8688, Acc.airplane: 0.6587, Acc.dirt track: 0.3367, Acc.apparel: 0.8372, Acc.pole: 0.3262, Acc.land: 0.0654, Acc.bannister: 0.2637, Acc.escalator: 0.8020, Acc.ottoman: 0.7133, Acc.bottle: 0.3189, Acc.buffet: 0.6682, Acc.poster: 0.4134, Acc.stage: 0.2165, Acc.van: 0.6501, Acc.ship: 0.0666, Acc.fountain: 0.2008, Acc.conveyer belt: 0.9452, Acc.canopy: 0.6396, Acc.washer: 0.8527, Acc.plaything: 0.4556, Acc.swimming pool: 0.8710, Acc.stool: 0.6817, Acc.barrel: 0.6520, Acc.basket: 0.5476, Acc.waterfall: 0.6769, Acc.tent: 0.9837, Acc.bag: 0.3073, Acc.minibike: 0.8508, Acc.cradle: 0.9701, Acc.oven: 0.7749, Acc.ball: 0.4659, Acc.food: 0.7510, Acc.step: 0.2359, Acc.tank: 0.6216, Acc.trade name: 0.3511, Acc.microwave: 0.9432, Acc.pot: 0.6015, Acc.animal: 0.7300, Acc.bicycle: 0.7570, Acc.lake: 0.6506, Acc.dishwasher: 0.8226, Acc.screen: 0.9121, Acc.blanket: 0.2136, Acc.sculpture: 0.6814, Acc.hood: 0.6948, Acc.sconce: 0.6398, Acc.vase: 0.6243, Acc.traffic light: 0.5834, Acc.tray: 0.1981, Acc.ashcan: 0.6385, Acc.fan: 0.7226, Acc.pier: 0.4322, Acc.crt screen: 0.1385, Acc.plate: 0.7551, Acc.monitor: 0.2342, Acc.bulletin board: 0.6936, Acc.shower: 0.1055, Acc.radiator: 0.6906, Acc.glass: 0.2318, Acc.clock: 0.4021, Acc.flag: 0.7639 2023-11-03 00:45:27,005 - mmseg - INFO - Iter [16050/20000] lr: 6.400e-07, eta: 1:28:13, time: 2.411, data_time: 1.206, memory: 38534, decode.loss_ce: 0.1620, decode.acc_seg: 93.0670, loss: 0.1620 2023-11-03 00:46:27,470 - mmseg - INFO - Iter [16100/20000] lr: 6.319e-07, eta: 1:27:04, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1634, decode.acc_seg: 93.2788, loss: 0.1634 2023-11-03 00:47:30,398 - mmseg - INFO - Iter [16150/20000] lr: 6.238e-07, eta: 1:25:56, time: 1.259, data_time: 0.056, memory: 38534, decode.loss_ce: 0.1611, decode.acc_seg: 93.3359, loss: 0.1611 2023-11-03 00:48:30,885 - mmseg - INFO - Iter [16200/20000] lr: 6.157e-07, eta: 1:24:48, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1601, decode.acc_seg: 93.3393, loss: 0.1601 2023-11-03 00:49:31,397 - mmseg - INFO - Iter [16250/20000] lr: 6.076e-07, eta: 1:23:39, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1574, decode.acc_seg: 93.3685, loss: 0.1574 2023-11-03 00:50:31,938 - mmseg - INFO - Iter [16300/20000] lr: 5.995e-07, eta: 1:22:31, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1651, decode.acc_seg: 93.1804, loss: 0.1651 2023-11-03 00:51:32,460 - mmseg - INFO - Iter [16350/20000] lr: 5.914e-07, eta: 1:21:23, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1663, decode.acc_seg: 93.0680, loss: 0.1663 2023-11-03 00:52:32,940 - mmseg - INFO - Iter [16400/20000] lr: 5.833e-07, eta: 1:20:14, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1436, decode.acc_seg: 93.8110, loss: 0.1436 2023-11-03 00:53:35,892 - mmseg - INFO - Iter [16450/20000] lr: 5.752e-07, eta: 1:19:07, time: 1.259, data_time: 0.056, memory: 38534, decode.loss_ce: 0.1601, decode.acc_seg: 93.5143, loss: 0.1601 2023-11-03 00:54:36,365 - mmseg - INFO - Iter [16500/20000] lr: 5.671e-07, eta: 1:17:58, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1630, decode.acc_seg: 93.1820, loss: 0.1630 2023-11-03 00:55:36,892 - mmseg - INFO - Iter [16550/20000] lr: 5.590e-07, eta: 1:16:50, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1530, decode.acc_seg: 93.5631, loss: 0.1530 2023-11-03 00:56:37,368 - mmseg - INFO - Iter [16600/20000] lr: 5.509e-07, eta: 1:15:42, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1597, decode.acc_seg: 93.3829, loss: 0.1597 2023-11-03 00:57:37,936 - mmseg - INFO - Iter [16650/20000] lr: 5.428e-07, eta: 1:14:34, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1540, decode.acc_seg: 93.4017, loss: 0.1540 2023-11-03 00:58:38,405 - mmseg - INFO - Iter [16700/20000] lr: 5.347e-07, eta: 1:13:26, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1685, decode.acc_seg: 92.9226, loss: 0.1685 2023-11-03 00:59:41,324 - mmseg - INFO - Iter [16750/20000] lr: 5.266e-07, eta: 1:12:18, time: 1.258, data_time: 0.056, memory: 38534, decode.loss_ce: 0.1468, decode.acc_seg: 93.6554, loss: 0.1468 2023-11-03 01:00:41,799 - mmseg - INFO - Iter [16800/20000] lr: 5.185e-07, eta: 1:11:10, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1569, decode.acc_seg: 93.2188, loss: 0.1569 2023-11-03 01:01:42,295 - mmseg - INFO - Iter [16850/20000] lr: 5.104e-07, eta: 1:10:03, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1578, decode.acc_seg: 93.3231, loss: 0.1578 2023-11-03 01:02:42,777 - mmseg - INFO - Iter [16900/20000] lr: 5.023e-07, eta: 1:08:55, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1523, decode.acc_seg: 93.5530, loss: 0.1523 2023-11-03 01:03:43,223 - mmseg - INFO - Iter [16950/20000] lr: 4.942e-07, eta: 1:07:47, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1570, decode.acc_seg: 93.3935, loss: 0.1570 2023-11-03 01:04:43,738 - mmseg - INFO - Saving checkpoint at 17000 iterations 2023-11-03 01:05:41,282 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-03 01:05:41,283 - mmseg - INFO - Iter [17000/20000] lr: 4.861e-07, eta: 1:06:49, time: 2.361, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1534, decode.acc_seg: 93.5520, loss: 0.1534 2023-11-03 01:06:44,263 - mmseg - INFO - per class results: 2023-11-03 01:06:44,272 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 80.35 | 89.02 | | building | 83.37 | 93.42 | | sky | 93.86 | 97.42 | | floor | 82.6 | 90.49 | | tree | 73.74 | 87.71 | | ceiling | 85.56 | 93.56 | | road | 83.9 | 91.72 | | bed | 91.2 | 96.82 | | windowpane | 66.08 | 80.05 | | grass | 71.51 | 88.97 | | cabinet | 63.82 | 73.49 | | sidewalk | 65.17 | 78.73 | | person | 81.86 | 92.51 | | earth | 36.35 | 47.36 | | door | 57.37 | 73.34 | | table | 67.39 | 79.41 | | mountain | 61.94 | 77.44 | | plant | 52.62 | 66.82 | | curtain | 77.92 | 88.75 | | chair | 60.23 | 74.86 | | car | 85.38 | 92.61 | | water | 58.93 | 75.09 | | painting | 73.24 | 88.46 | | sofa | 79.63 | 91.57 | | shelf | 43.31 | 63.35 | | house | 39.36 | 52.17 | | sea | 60.69 | 82.22 | | mirror | 73.14 | 81.83 | | rug | 65.12 | 76.19 | | field | 32.11 | 51.8 | | armchair | 57.45 | 73.78 | | seat | 63.67 | 89.43 | | fence | 44.16 | 61.55 | | desk | 52.98 | 80.77 | | rock | 43.98 | 56.9 | | wardrobe | 50.91 | 67.28 | | lamp | 66.91 | 79.57 | | bathtub | 85.58 | 89.06 | | railing | 40.4 | 55.0 | | cushion | 60.7 | 73.35 | | base | 32.79 | 45.98 | | box | 32.32 | 42.27 | | column | 50.64 | 63.13 | | signboard | 35.65 | 48.68 | | chest of drawers | 38.7 | 61.97 | | counter | 54.62 | 76.24 | | sand | 38.04 | 50.96 | | sink | 76.38 | 83.91 | | skyscraper | 49.61 | 58.27 | | fireplace | 68.63 | 89.06 | | refrigerator | 81.37 | 92.95 | | grandstand | 52.63 | 76.43 | | path | 17.15 | 22.0 | | stairs | 24.19 | 28.24 | | runway | 66.97 | 84.75 | | case | 57.45 | 63.63 | | pool table | 93.3 | 98.03 | | pillow | 58.9 | 67.75 | | screen door | 67.43 | 72.12 | | stairway | 41.56 | 59.51 | | river | 22.0 | 39.3 | | bridge | 77.01 | 90.76 | | bookcase | 33.75 | 48.16 | | blind | 46.74 | 53.18 | | coffee table | 64.64 | 84.94 | | toilet | 89.05 | 93.53 | | flower | 40.06 | 52.93 | | book | 49.74 | 70.59 | | hill | 7.96 | 12.27 | | bench | 50.21 | 58.09 | | countertop | 57.55 | 78.38 | | stove | 82.02 | 91.25 | | palm | 44.72 | 73.01 | | kitchen island | 58.05 | 74.16 | | computer | 76.09 | 87.09 | | swivel chair | 43.29 | 65.25 | | boat | 61.58 | 90.54 | | bar | 61.4 | 69.3 | | arcade machine | 78.85 | 81.48 | | hovel | 14.76 | 15.42 | | bus | 91.0 | 95.37 | | towel | 71.95 | 83.63 | | light | 46.56 | 53.24 | | truck | 46.28 | 60.87 | | tower | 8.28 | 13.69 | | chandelier | 65.38 | 84.08 | | awning | 34.0 | 40.75 | | streetlight | 24.6 | 29.53 | | booth | 34.78 | 34.93 | | television receiver | 73.25 | 85.58 | | airplane | 59.37 | 64.95 | | dirt track | 22.36 | 32.04 | | apparel | 54.98 | 82.19 | | pole | 30.12 | 37.17 | | land | 4.18 | 5.68 | | bannister | 18.51 | 26.21 | | escalator | 63.26 | 81.46 | | ottoman | 48.78 | 69.06 | | bottle | 23.7 | 33.03 | | buffet | 55.21 | 76.9 | | poster | 30.62 | 40.06 | | stage | 12.91 | 23.39 | | van | 48.29 | 65.93 | | ship | 5.75 | 5.91 | | fountain | 14.37 | 15.03 | | conveyer belt | 79.66 | 93.93 | | canopy | 48.78 | 58.37 | | washer | 82.0 | 85.36 | | plaything | 30.36 | 44.67 | | swimming pool | 71.38 | 73.45 | | stool | 49.76 | 62.98 | | barrel | 54.9 | 62.73 | | basket | 39.64 | 56.27 | | waterfall | 53.4 | 67.73 | | tent | 96.03 | 98.13 | | bag | 25.05 | 31.08 | | minibike | 71.62 | 85.02 | | cradle | 84.41 | 96.52 | | oven | 67.11 | 77.87 | | ball | 55.98 | 61.11 | | food | 65.14 | 72.85 | | step | 17.57 | 24.57 | | tank | 51.13 | 61.1 | | trade name | 29.8 | 35.94 | | microwave | 86.94 | 93.35 | | pot | 53.43 | 61.22 | | animal | 70.92 | 73.61 | | bicycle | 59.11 | 76.19 | | lake | 57.26 | 63.67 | | dishwasher | 74.14 | 83.15 | | screen | 60.5 | 92.76 | | blanket | 20.36 | 22.59 | | sculpture | 61.51 | 68.0 | | hood | 59.94 | 70.73 | | sconce | 53.53 | 66.13 | | vase | 42.32 | 60.29 | | traffic light | 32.96 | 51.74 | | tray | 15.02 | 21.71 | | ashcan | 52.26 | 63.08 | | fan | 60.7 | 71.33 | | pier | 39.39 | 42.81 | | crt screen | 5.71 | 13.44 | | plate | 58.67 | 76.22 | | monitor | 15.33 | 16.19 | | bulletin board | 58.31 | 69.64 | | shower | 6.24 | 6.84 | | radiator | 56.4 | 66.0 | | glass | 18.45 | 20.2 | | clock | 32.31 | 38.35 | | flag | 69.27 | 75.11 | +---------------------+-------+-------+ 2023-11-03 01:06:44,272 - mmseg - INFO - Summary: 2023-11-03 01:06:44,272 - mmseg - INFO - +-------+------+-------+ | aAcc | mIoU | mAcc | +-------+------+-------+ | 84.57 | 53.3 | 64.76 | +-------+------+-------+ 2023-11-03 01:06:44,274 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-03 01:06:44,274 - mmseg - INFO - Iter(val) [250] aAcc: 0.8457, mIoU: 0.5330, mAcc: 0.6476, IoU.wall: 0.8035, IoU.building: 0.8337, IoU.sky: 0.9386, IoU.floor: 0.8260, IoU.tree: 0.7374, IoU.ceiling: 0.8556, IoU.road: 0.8390, IoU.bed : 0.9120, IoU.windowpane: 0.6608, IoU.grass: 0.7151, IoU.cabinet: 0.6382, IoU.sidewalk: 0.6517, IoU.person: 0.8186, IoU.earth: 0.3635, IoU.door: 0.5737, IoU.table: 0.6739, IoU.mountain: 0.6194, IoU.plant: 0.5262, IoU.curtain: 0.7792, IoU.chair: 0.6023, IoU.car: 0.8538, IoU.water: 0.5893, IoU.painting: 0.7324, IoU.sofa: 0.7963, IoU.shelf: 0.4331, IoU.house: 0.3936, IoU.sea: 0.6069, IoU.mirror: 0.7314, IoU.rug: 0.6512, IoU.field: 0.3211, IoU.armchair: 0.5745, IoU.seat: 0.6367, IoU.fence: 0.4416, IoU.desk: 0.5298, IoU.rock: 0.4398, IoU.wardrobe: 0.5091, IoU.lamp: 0.6691, IoU.bathtub: 0.8558, IoU.railing: 0.4040, IoU.cushion: 0.6070, IoU.base: 0.3279, IoU.box: 0.3232, IoU.column: 0.5064, IoU.signboard: 0.3565, IoU.chest of drawers: 0.3870, IoU.counter: 0.5462, IoU.sand: 0.3804, IoU.sink: 0.7638, IoU.skyscraper: 0.4961, IoU.fireplace: 0.6863, IoU.refrigerator: 0.8137, IoU.grandstand: 0.5263, IoU.path: 0.1715, IoU.stairs: 0.2419, IoU.runway: 0.6697, IoU.case: 0.5745, IoU.pool table: 0.9330, IoU.pillow: 0.5890, IoU.screen door: 0.6743, IoU.stairway: 0.4156, IoU.river: 0.2200, IoU.bridge: 0.7701, IoU.bookcase: 0.3375, IoU.blind: 0.4674, IoU.coffee table: 0.6464, IoU.toilet: 0.8905, IoU.flower: 0.4006, IoU.book: 0.4974, IoU.hill: 0.0796, IoU.bench: 0.5021, IoU.countertop: 0.5755, IoU.stove: 0.8202, IoU.palm: 0.4472, IoU.kitchen island: 0.5805, IoU.computer: 0.7609, IoU.swivel chair: 0.4329, IoU.boat: 0.6158, IoU.bar: 0.6140, IoU.arcade machine: 0.7885, IoU.hovel: 0.1476, IoU.bus: 0.9100, IoU.towel: 0.7195, IoU.light: 0.4656, IoU.truck: 0.4628, IoU.tower: 0.0828, IoU.chandelier: 0.6538, IoU.awning: 0.3400, IoU.streetlight: 0.2460, IoU.booth: 0.3478, IoU.television receiver: 0.7325, IoU.airplane: 0.5937, IoU.dirt track: 0.2236, IoU.apparel: 0.5498, IoU.pole: 0.3012, IoU.land: 0.0418, IoU.bannister: 0.1851, IoU.escalator: 0.6326, IoU.ottoman: 0.4878, IoU.bottle: 0.2370, IoU.buffet: 0.5521, IoU.poster: 0.3062, IoU.stage: 0.1291, IoU.van: 0.4829, IoU.ship: 0.0575, IoU.fountain: 0.1437, IoU.conveyer belt: 0.7966, IoU.canopy: 0.4878, IoU.washer: 0.8200, IoU.plaything: 0.3036, IoU.swimming pool: 0.7138, IoU.stool: 0.4976, IoU.barrel: 0.5490, IoU.basket: 0.3964, IoU.waterfall: 0.5340, IoU.tent: 0.9603, IoU.bag: 0.2505, IoU.minibike: 0.7162, IoU.cradle: 0.8441, IoU.oven: 0.6711, IoU.ball: 0.5598, IoU.food: 0.6514, IoU.step: 0.1757, IoU.tank: 0.5113, IoU.trade name: 0.2980, IoU.microwave: 0.8694, IoU.pot: 0.5343, IoU.animal: 0.7092, IoU.bicycle: 0.5911, IoU.lake: 0.5726, IoU.dishwasher: 0.7414, IoU.screen: 0.6050, IoU.blanket: 0.2036, IoU.sculpture: 0.6151, IoU.hood: 0.5994, IoU.sconce: 0.5353, IoU.vase: 0.4232, IoU.traffic light: 0.3296, IoU.tray: 0.1502, IoU.ashcan: 0.5226, IoU.fan: 0.6070, IoU.pier: 0.3939, IoU.crt screen: 0.0571, IoU.plate: 0.5867, IoU.monitor: 0.1533, IoU.bulletin board: 0.5831, IoU.shower: 0.0624, IoU.radiator: 0.5640, IoU.glass: 0.1845, IoU.clock: 0.3231, IoU.flag: 0.6927, Acc.wall: 0.8902, Acc.building: 0.9342, Acc.sky: 0.9742, Acc.floor: 0.9049, Acc.tree: 0.8771, Acc.ceiling: 0.9356, Acc.road: 0.9172, Acc.bed : 0.9682, Acc.windowpane: 0.8005, Acc.grass: 0.8897, Acc.cabinet: 0.7349, Acc.sidewalk: 0.7873, Acc.person: 0.9251, Acc.earth: 0.4736, Acc.door: 0.7334, Acc.table: 0.7941, Acc.mountain: 0.7744, Acc.plant: 0.6682, Acc.curtain: 0.8875, Acc.chair: 0.7486, Acc.car: 0.9261, Acc.water: 0.7509, Acc.painting: 0.8846, Acc.sofa: 0.9157, Acc.shelf: 0.6335, Acc.house: 0.5217, Acc.sea: 0.8222, Acc.mirror: 0.8183, Acc.rug: 0.7619, Acc.field: 0.5180, Acc.armchair: 0.7378, Acc.seat: 0.8943, Acc.fence: 0.6155, Acc.desk: 0.8077, Acc.rock: 0.5690, Acc.wardrobe: 0.6728, Acc.lamp: 0.7957, Acc.bathtub: 0.8906, Acc.railing: 0.5500, Acc.cushion: 0.7335, Acc.base: 0.4598, Acc.box: 0.4227, Acc.column: 0.6313, Acc.signboard: 0.4868, Acc.chest of drawers: 0.6197, Acc.counter: 0.7624, Acc.sand: 0.5096, Acc.sink: 0.8391, Acc.skyscraper: 0.5827, Acc.fireplace: 0.8906, Acc.refrigerator: 0.9295, Acc.grandstand: 0.7643, Acc.path: 0.2200, Acc.stairs: 0.2824, Acc.runway: 0.8475, Acc.case: 0.6363, Acc.pool table: 0.9803, Acc.pillow: 0.6775, Acc.screen door: 0.7212, Acc.stairway: 0.5951, Acc.river: 0.3930, Acc.bridge: 0.9076, Acc.bookcase: 0.4816, Acc.blind: 0.5318, Acc.coffee table: 0.8494, Acc.toilet: 0.9353, Acc.flower: 0.5293, Acc.book: 0.7059, Acc.hill: 0.1227, Acc.bench: 0.5809, Acc.countertop: 0.7838, Acc.stove: 0.9125, Acc.palm: 0.7301, Acc.kitchen island: 0.7416, Acc.computer: 0.8709, Acc.swivel chair: 0.6525, Acc.boat: 0.9054, Acc.bar: 0.6930, Acc.arcade machine: 0.8148, Acc.hovel: 0.1542, Acc.bus: 0.9537, Acc.towel: 0.8363, Acc.light: 0.5324, Acc.truck: 0.6087, Acc.tower: 0.1369, Acc.chandelier: 0.8408, Acc.awning: 0.4075, Acc.streetlight: 0.2953, Acc.booth: 0.3493, Acc.television receiver: 0.8558, Acc.airplane: 0.6495, Acc.dirt track: 0.3204, Acc.apparel: 0.8219, Acc.pole: 0.3717, Acc.land: 0.0568, Acc.bannister: 0.2621, Acc.escalator: 0.8146, Acc.ottoman: 0.6906, Acc.bottle: 0.3303, Acc.buffet: 0.7690, Acc.poster: 0.4006, Acc.stage: 0.2339, Acc.van: 0.6593, Acc.ship: 0.0591, Acc.fountain: 0.1503, Acc.conveyer belt: 0.9393, Acc.canopy: 0.5837, Acc.washer: 0.8536, Acc.plaything: 0.4467, Acc.swimming pool: 0.7345, Acc.stool: 0.6298, Acc.barrel: 0.6273, Acc.basket: 0.5627, Acc.waterfall: 0.6773, Acc.tent: 0.9813, Acc.bag: 0.3108, Acc.minibike: 0.8502, Acc.cradle: 0.9652, Acc.oven: 0.7787, Acc.ball: 0.6111, Acc.food: 0.7285, Acc.step: 0.2457, Acc.tank: 0.6110, Acc.trade name: 0.3594, Acc.microwave: 0.9335, Acc.pot: 0.6122, Acc.animal: 0.7361, Acc.bicycle: 0.7619, Acc.lake: 0.6367, Acc.dishwasher: 0.8315, Acc.screen: 0.9276, Acc.blanket: 0.2259, Acc.sculpture: 0.6800, Acc.hood: 0.7073, Acc.sconce: 0.6613, Acc.vase: 0.6029, Acc.traffic light: 0.5174, Acc.tray: 0.2171, Acc.ashcan: 0.6308, Acc.fan: 0.7133, Acc.pier: 0.4281, Acc.crt screen: 0.1344, Acc.plate: 0.7622, Acc.monitor: 0.1619, Acc.bulletin board: 0.6964, Acc.shower: 0.0684, Acc.radiator: 0.6600, Acc.glass: 0.2020, Acc.clock: 0.3835, Acc.flag: 0.7511 2023-11-03 01:07:44,846 - mmseg - INFO - Iter [17050/20000] lr: 4.780e-07, eta: 1:05:52, time: 2.471, data_time: 1.267, memory: 38534, decode.loss_ce: 0.1523, decode.acc_seg: 93.5300, loss: 0.1523 2023-11-03 01:08:47,935 - mmseg - INFO - Iter [17100/20000] lr: 4.699e-07, eta: 1:04:45, time: 1.262, data_time: 0.055, memory: 38534, decode.loss_ce: 0.1612, decode.acc_seg: 93.1499, loss: 0.1612 2023-11-03 01:09:48,387 - mmseg - INFO - Iter [17150/20000] lr: 4.618e-07, eta: 1:03:37, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1577, decode.acc_seg: 93.2763, loss: 0.1577 2023-11-03 01:10:48,846 - mmseg - INFO - Iter [17200/20000] lr: 4.537e-07, eta: 1:02:29, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1519, decode.acc_seg: 93.4213, loss: 0.1519 2023-11-03 01:11:49,310 - mmseg - INFO - Iter [17250/20000] lr: 4.456e-07, eta: 1:01:21, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1522, decode.acc_seg: 93.5300, loss: 0.1522 2023-11-03 01:12:49,809 - mmseg - INFO - Iter [17300/20000] lr: 4.375e-07, eta: 1:00:13, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1524, decode.acc_seg: 93.4307, loss: 0.1524 2023-11-03 01:13:50,270 - mmseg - INFO - Iter [17350/20000] lr: 4.294e-07, eta: 0:59:05, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1542, decode.acc_seg: 93.5875, loss: 0.1542 2023-11-03 01:14:53,137 - mmseg - INFO - Iter [17400/20000] lr: 4.213e-07, eta: 0:57:57, time: 1.257, data_time: 0.055, memory: 38534, decode.loss_ce: 0.1477, decode.acc_seg: 93.5592, loss: 0.1477 2023-11-03 01:15:53,597 - mmseg - INFO - Iter [17450/20000] lr: 4.132e-07, eta: 0:56:49, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1564, decode.acc_seg: 93.5237, loss: 0.1564 2023-11-03 01:16:54,059 - mmseg - INFO - Iter [17500/20000] lr: 4.051e-07, eta: 0:55:42, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1501, decode.acc_seg: 93.5548, loss: 0.1501 2023-11-03 01:17:54,498 - mmseg - INFO - Iter [17550/20000] lr: 3.970e-07, eta: 0:54:34, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1506, decode.acc_seg: 93.6558, loss: 0.1506 2023-11-03 01:18:54,966 - mmseg - INFO - Iter [17600/20000] lr: 3.889e-07, eta: 0:53:26, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1506, decode.acc_seg: 93.5173, loss: 0.1506 2023-11-03 01:19:55,458 - mmseg - INFO - Iter [17650/20000] lr: 3.808e-07, eta: 0:52:19, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1432, decode.acc_seg: 93.7758, loss: 0.1432 2023-11-03 01:20:58,219 - mmseg - INFO - Iter [17700/20000] lr: 3.727e-07, eta: 0:51:11, time: 1.255, data_time: 0.052, memory: 38534, decode.loss_ce: 0.1510, decode.acc_seg: 93.6453, loss: 0.1510 2023-11-03 01:21:58,679 - mmseg - INFO - Iter [17750/20000] lr: 3.646e-07, eta: 0:50:04, time: 1.209, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1498, decode.acc_seg: 93.6483, loss: 0.1498 2023-11-03 01:22:59,149 - mmseg - INFO - Iter [17800/20000] lr: 3.565e-07, eta: 0:48:56, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1476, decode.acc_seg: 93.6235, loss: 0.1476 2023-11-03 01:23:59,629 - mmseg - INFO - Iter [17850/20000] lr: 3.484e-07, eta: 0:47:49, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1511, decode.acc_seg: 93.6478, loss: 0.1511 2023-11-03 01:25:00,134 - mmseg - INFO - Iter [17900/20000] lr: 3.403e-07, eta: 0:46:41, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1453, decode.acc_seg: 93.7962, loss: 0.1453 2023-11-03 01:26:00,597 - mmseg - INFO - Iter [17950/20000] lr: 3.322e-07, eta: 0:45:34, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1571, decode.acc_seg: 93.4113, loss: 0.1571 2023-11-03 01:27:01,114 - mmseg - INFO - Saving checkpoint at 18000 iterations 2023-11-03 01:27:57,818 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-03 01:27:57,818 - mmseg - INFO - Iter [18000/20000] lr: 3.241e-07, eta: 0:44:33, time: 2.344, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1516, decode.acc_seg: 93.5435, loss: 0.1516 2023-11-03 01:29:00,470 - mmseg - INFO - per class results: 2023-11-03 01:29:00,476 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 80.4 | 88.91 | | building | 83.33 | 93.32 | | sky | 94.04 | 97.12 | | floor | 83.0 | 90.9 | | tree | 74.24 | 89.25 | | ceiling | 85.51 | 94.3 | | road | 84.58 | 91.53 | | bed | 91.32 | 97.0 | | windowpane | 65.51 | 80.41 | | grass | 70.65 | 90.13 | | cabinet | 63.77 | 74.59 | | sidewalk | 66.38 | 81.81 | | person | 82.46 | 91.5 | | earth | 37.06 | 48.12 | | door | 57.11 | 74.75 | | table | 67.41 | 78.93 | | mountain | 61.57 | 78.35 | | plant | 53.44 | 65.69 | | curtain | 78.05 | 88.43 | | chair | 60.19 | 72.84 | | car | 85.42 | 92.94 | | water | 57.8 | 72.57 | | painting | 74.0 | 88.06 | | sofa | 79.99 | 89.54 | | shelf | 42.92 | 60.28 | | house | 39.57 | 53.05 | | sea | 61.57 | 83.51 | | mirror | 73.98 | 83.75 | | rug | 66.76 | 76.51 | | field | 30.11 | 46.28 | | armchair | 57.26 | 74.66 | | seat | 64.55 | 89.34 | | fence | 44.37 | 63.97 | | desk | 54.5 | 79.0 | | rock | 42.59 | 54.23 | | wardrobe | 50.96 | 70.01 | | lamp | 66.88 | 78.4 | | bathtub | 84.87 | 88.01 | | railing | 40.69 | 55.5 | | cushion | 61.55 | 75.9 | | base | 33.01 | 43.95 | | box | 33.6 | 45.23 | | column | 50.34 | 61.71 | | signboard | 34.76 | 47.03 | | chest of drawers | 38.52 | 61.8 | | counter | 54.91 | 69.8 | | sand | 38.06 | 51.91 | | sink | 76.41 | 83.76 | | skyscraper | 49.73 | 57.03 | | fireplace | 68.63 | 88.08 | | refrigerator | 82.91 | 91.32 | | grandstand | 56.1 | 73.63 | | path | 17.42 | 23.17 | | stairs | 23.71 | 27.47 | | runway | 66.82 | 84.97 | | case | 56.99 | 69.8 | | pool table | 93.36 | 97.98 | | pillow | 60.68 | 71.11 | | screen door | 70.44 | 76.86 | | stairway | 41.2 | 61.69 | | river | 16.37 | 29.4 | | bridge | 77.77 | 90.42 | | bookcase | 35.13 | 50.89 | | blind | 44.31 | 48.72 | | coffee table | 65.38 | 84.42 | | toilet | 89.34 | 94.32 | | flower | 40.21 | 50.74 | | book | 49.0 | 68.53 | | hill | 7.82 | 11.2 | | bench | 50.52 | 57.63 | | countertop | 56.57 | 76.39 | | stove | 82.01 | 90.05 | | palm | 46.88 | 75.16 | | kitchen island | 57.91 | 73.79 | | computer | 76.18 | 89.24 | | swivel chair | 42.97 | 61.85 | | boat | 61.47 | 90.27 | | bar | 60.13 | 66.92 | | arcade machine | 76.45 | 78.44 | | hovel | 11.06 | 11.37 | | bus | 91.54 | 95.24 | | towel | 72.32 | 83.11 | | light | 48.36 | 56.78 | | truck | 47.64 | 58.81 | | tower | 8.7 | 14.35 | | chandelier | 65.83 | 81.28 | | awning | 36.19 | 44.7 | | streetlight | 25.09 | 30.72 | | booth | 35.26 | 35.43 | | television receiver | 73.54 | 87.47 | | airplane | 59.5 | 65.13 | | dirt track | 23.54 | 32.49 | | apparel | 58.48 | 81.0 | | pole | 29.59 | 37.24 | | land | 3.59 | 5.41 | | bannister | 18.43 | 25.52 | | escalator | 63.46 | 78.63 | | ottoman | 47.66 | 69.49 | | bottle | 23.47 | 31.56 | | buffet | 54.24 | 68.22 | | poster | 31.85 | 43.53 | | stage | 11.67 | 19.42 | | van | 48.98 | 64.1 | | ship | 4.92 | 5.06 | | fountain | 15.3 | 16.14 | | conveyer belt | 80.23 | 94.26 | | canopy | 47.13 | 57.51 | | washer | 82.28 | 85.87 | | plaything | 31.19 | 43.75 | | swimming pool | 57.89 | 84.64 | | stool | 49.83 | 66.81 | | barrel | 55.26 | 64.76 | | basket | 40.27 | 55.44 | | waterfall | 52.18 | 62.45 | | tent | 96.15 | 97.78 | | bag | 25.67 | 32.58 | | minibike | 70.71 | 85.68 | | cradle | 84.51 | 97.4 | | oven | 66.93 | 77.36 | | ball | 50.17 | 53.05 | | food | 65.34 | 74.28 | | step | 18.67 | 24.39 | | tank | 51.76 | 61.71 | | trade name | 30.18 | 36.73 | | microwave | 87.38 | 92.83 | | pot | 52.88 | 59.8 | | animal | 70.19 | 72.4 | | bicycle | 59.24 | 75.92 | | lake | 50.29 | 63.72 | | dishwasher | 74.12 | 82.05 | | screen | 61.06 | 91.31 | | blanket | 24.02 | 27.78 | | sculpture | 63.62 | 69.92 | | hood | 60.78 | 72.24 | | sconce | 53.82 | 68.23 | | vase | 43.04 | 58.33 | | traffic light | 32.32 | 54.68 | | tray | 11.89 | 20.34 | | ashcan | 51.19 | 62.85 | | fan | 61.09 | 72.5 | | pier | 39.62 | 43.42 | | crt screen | 5.96 | 13.9 | | plate | 58.32 | 73.77 | | monitor | 15.99 | 17.03 | | bulletin board | 55.88 | 73.19 | | shower | 6.98 | 8.09 | | radiator | 57.07 | 67.15 | | glass | 19.04 | 20.91 | | clock | 33.2 | 39.9 | | flag | 69.3 | 75.45 | +---------------------+-------+-------+ 2023-11-03 01:29:00,476 - mmseg - INFO - Summary: 2023-11-03 01:29:00,476 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 84.65 | 53.26 | 64.64 | +-------+-------+-------+ 2023-11-03 01:29:00,477 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-03 01:29:00,477 - mmseg - INFO - Iter(val) [250] aAcc: 0.8465, mIoU: 0.5326, mAcc: 0.6464, IoU.wall: 0.8040, IoU.building: 0.8333, IoU.sky: 0.9404, IoU.floor: 0.8300, IoU.tree: 0.7424, IoU.ceiling: 0.8551, IoU.road: 0.8458, IoU.bed : 0.9132, IoU.windowpane: 0.6551, IoU.grass: 0.7065, IoU.cabinet: 0.6377, IoU.sidewalk: 0.6638, IoU.person: 0.8246, IoU.earth: 0.3706, IoU.door: 0.5711, IoU.table: 0.6741, IoU.mountain: 0.6157, IoU.plant: 0.5344, IoU.curtain: 0.7805, IoU.chair: 0.6019, IoU.car: 0.8542, IoU.water: 0.5780, IoU.painting: 0.7400, IoU.sofa: 0.7999, IoU.shelf: 0.4292, IoU.house: 0.3957, IoU.sea: 0.6157, IoU.mirror: 0.7398, IoU.rug: 0.6676, IoU.field: 0.3011, IoU.armchair: 0.5726, IoU.seat: 0.6455, IoU.fence: 0.4437, IoU.desk: 0.5450, IoU.rock: 0.4259, IoU.wardrobe: 0.5096, IoU.lamp: 0.6688, IoU.bathtub: 0.8487, IoU.railing: 0.4069, IoU.cushion: 0.6155, IoU.base: 0.3301, IoU.box: 0.3360, IoU.column: 0.5034, IoU.signboard: 0.3476, IoU.chest of drawers: 0.3852, IoU.counter: 0.5491, IoU.sand: 0.3806, IoU.sink: 0.7641, IoU.skyscraper: 0.4973, IoU.fireplace: 0.6863, IoU.refrigerator: 0.8291, IoU.grandstand: 0.5610, IoU.path: 0.1742, IoU.stairs: 0.2371, IoU.runway: 0.6682, IoU.case: 0.5699, IoU.pool table: 0.9336, IoU.pillow: 0.6068, IoU.screen door: 0.7044, IoU.stairway: 0.4120, IoU.river: 0.1637, IoU.bridge: 0.7777, IoU.bookcase: 0.3513, IoU.blind: 0.4431, IoU.coffee table: 0.6538, IoU.toilet: 0.8934, IoU.flower: 0.4021, IoU.book: 0.4900, IoU.hill: 0.0782, IoU.bench: 0.5052, IoU.countertop: 0.5657, IoU.stove: 0.8201, IoU.palm: 0.4688, IoU.kitchen island: 0.5791, IoU.computer: 0.7618, IoU.swivel chair: 0.4297, IoU.boat: 0.6147, IoU.bar: 0.6013, IoU.arcade machine: 0.7645, IoU.hovel: 0.1106, IoU.bus: 0.9154, IoU.towel: 0.7232, IoU.light: 0.4836, IoU.truck: 0.4764, IoU.tower: 0.0870, IoU.chandelier: 0.6583, IoU.awning: 0.3619, IoU.streetlight: 0.2509, IoU.booth: 0.3526, IoU.television receiver: 0.7354, IoU.airplane: 0.5950, IoU.dirt track: 0.2354, IoU.apparel: 0.5848, IoU.pole: 0.2959, IoU.land: 0.0359, IoU.bannister: 0.1843, IoU.escalator: 0.6346, IoU.ottoman: 0.4766, IoU.bottle: 0.2347, IoU.buffet: 0.5424, IoU.poster: 0.3185, IoU.stage: 0.1167, IoU.van: 0.4898, IoU.ship: 0.0492, IoU.fountain: 0.1530, IoU.conveyer belt: 0.8023, IoU.canopy: 0.4713, IoU.washer: 0.8228, IoU.plaything: 0.3119, IoU.swimming pool: 0.5789, IoU.stool: 0.4983, IoU.barrel: 0.5526, IoU.basket: 0.4027, IoU.waterfall: 0.5218, IoU.tent: 0.9615, IoU.bag: 0.2567, IoU.minibike: 0.7071, IoU.cradle: 0.8451, IoU.oven: 0.6693, IoU.ball: 0.5017, IoU.food: 0.6534, IoU.step: 0.1867, IoU.tank: 0.5176, IoU.trade name: 0.3018, IoU.microwave: 0.8738, IoU.pot: 0.5288, IoU.animal: 0.7019, IoU.bicycle: 0.5924, IoU.lake: 0.5029, IoU.dishwasher: 0.7412, IoU.screen: 0.6106, IoU.blanket: 0.2402, IoU.sculpture: 0.6362, IoU.hood: 0.6078, IoU.sconce: 0.5382, IoU.vase: 0.4304, IoU.traffic light: 0.3232, IoU.tray: 0.1189, IoU.ashcan: 0.5119, IoU.fan: 0.6109, IoU.pier: 0.3962, IoU.crt screen: 0.0596, IoU.plate: 0.5832, IoU.monitor: 0.1599, IoU.bulletin board: 0.5588, IoU.shower: 0.0698, IoU.radiator: 0.5707, IoU.glass: 0.1904, IoU.clock: 0.3320, IoU.flag: 0.6930, Acc.wall: 0.8891, Acc.building: 0.9332, Acc.sky: 0.9712, Acc.floor: 0.9090, Acc.tree: 0.8925, Acc.ceiling: 0.9430, Acc.road: 0.9153, Acc.bed : 0.9700, Acc.windowpane: 0.8041, Acc.grass: 0.9013, Acc.cabinet: 0.7459, Acc.sidewalk: 0.8181, Acc.person: 0.9150, Acc.earth: 0.4812, Acc.door: 0.7475, Acc.table: 0.7893, Acc.mountain: 0.7835, Acc.plant: 0.6569, Acc.curtain: 0.8843, Acc.chair: 0.7284, Acc.car: 0.9294, Acc.water: 0.7257, Acc.painting: 0.8806, Acc.sofa: 0.8954, Acc.shelf: 0.6028, Acc.house: 0.5305, Acc.sea: 0.8351, Acc.mirror: 0.8375, Acc.rug: 0.7651, Acc.field: 0.4628, Acc.armchair: 0.7466, Acc.seat: 0.8934, Acc.fence: 0.6397, Acc.desk: 0.7900, Acc.rock: 0.5423, Acc.wardrobe: 0.7001, Acc.lamp: 0.7840, Acc.bathtub: 0.8801, Acc.railing: 0.5550, Acc.cushion: 0.7590, Acc.base: 0.4395, Acc.box: 0.4523, Acc.column: 0.6171, Acc.signboard: 0.4703, Acc.chest of drawers: 0.6180, Acc.counter: 0.6980, Acc.sand: 0.5191, Acc.sink: 0.8376, Acc.skyscraper: 0.5703, Acc.fireplace: 0.8808, Acc.refrigerator: 0.9132, Acc.grandstand: 0.7363, Acc.path: 0.2317, Acc.stairs: 0.2747, Acc.runway: 0.8497, Acc.case: 0.6980, Acc.pool table: 0.9798, Acc.pillow: 0.7111, Acc.screen door: 0.7686, Acc.stairway: 0.6169, Acc.river: 0.2940, Acc.bridge: 0.9042, Acc.bookcase: 0.5089, Acc.blind: 0.4872, Acc.coffee table: 0.8442, Acc.toilet: 0.9432, Acc.flower: 0.5074, Acc.book: 0.6853, Acc.hill: 0.1120, Acc.bench: 0.5763, Acc.countertop: 0.7639, Acc.stove: 0.9005, Acc.palm: 0.7516, Acc.kitchen island: 0.7379, Acc.computer: 0.8924, Acc.swivel chair: 0.6185, Acc.boat: 0.9027, Acc.bar: 0.6692, Acc.arcade machine: 0.7844, Acc.hovel: 0.1137, Acc.bus: 0.9524, Acc.towel: 0.8311, Acc.light: 0.5678, Acc.truck: 0.5881, Acc.tower: 0.1435, Acc.chandelier: 0.8128, Acc.awning: 0.4470, Acc.streetlight: 0.3072, Acc.booth: 0.3543, Acc.television receiver: 0.8747, Acc.airplane: 0.6513, Acc.dirt track: 0.3249, Acc.apparel: 0.8100, Acc.pole: 0.3724, Acc.land: 0.0541, Acc.bannister: 0.2552, Acc.escalator: 0.7863, Acc.ottoman: 0.6949, Acc.bottle: 0.3156, Acc.buffet: 0.6822, Acc.poster: 0.4353, Acc.stage: 0.1942, Acc.van: 0.6410, Acc.ship: 0.0506, Acc.fountain: 0.1614, Acc.conveyer belt: 0.9426, Acc.canopy: 0.5751, Acc.washer: 0.8587, Acc.plaything: 0.4375, Acc.swimming pool: 0.8464, Acc.stool: 0.6681, Acc.barrel: 0.6476, Acc.basket: 0.5544, Acc.waterfall: 0.6245, Acc.tent: 0.9778, Acc.bag: 0.3258, Acc.minibike: 0.8568, Acc.cradle: 0.9740, Acc.oven: 0.7736, Acc.ball: 0.5305, Acc.food: 0.7428, Acc.step: 0.2439, Acc.tank: 0.6171, Acc.trade name: 0.3673, Acc.microwave: 0.9283, Acc.pot: 0.5980, Acc.animal: 0.7240, Acc.bicycle: 0.7592, Acc.lake: 0.6372, Acc.dishwasher: 0.8205, Acc.screen: 0.9131, Acc.blanket: 0.2778, Acc.sculpture: 0.6992, Acc.hood: 0.7224, Acc.sconce: 0.6823, Acc.vase: 0.5833, Acc.traffic light: 0.5468, Acc.tray: 0.2034, Acc.ashcan: 0.6285, Acc.fan: 0.7250, Acc.pier: 0.4342, Acc.crt screen: 0.1390, Acc.plate: 0.7377, Acc.monitor: 0.1703, Acc.bulletin board: 0.7319, Acc.shower: 0.0809, Acc.radiator: 0.6715, Acc.glass: 0.2091, Acc.clock: 0.3990, Acc.flag: 0.7545 2023-11-03 01:30:03,399 - mmseg - INFO - Iter [18050/20000] lr: 3.160e-07, eta: 0:43:32, time: 2.512, data_time: 1.308, memory: 38534, decode.loss_ce: 0.1501, decode.acc_seg: 93.6086, loss: 0.1501 2023-11-03 01:31:03,882 - mmseg - INFO - Iter [18100/20000] lr: 3.079e-07, eta: 0:42:25, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1479, decode.acc_seg: 93.5486, loss: 0.1479 2023-11-03 01:32:04,365 - mmseg - INFO - Iter [18150/20000] lr: 2.998e-07, eta: 0:41:17, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1500, decode.acc_seg: 93.6386, loss: 0.1500 2023-11-03 01:33:04,789 - mmseg - INFO - Iter [18200/20000] lr: 2.917e-07, eta: 0:40:09, time: 1.208, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1411, decode.acc_seg: 93.9384, loss: 0.1411 2023-11-03 01:34:05,268 - mmseg - INFO - Iter [18250/20000] lr: 2.836e-07, eta: 0:39:02, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1488, decode.acc_seg: 93.6221, loss: 0.1488 2023-11-03 01:35:05,689 - mmseg - INFO - Iter [18300/20000] lr: 2.755e-07, eta: 0:37:54, time: 1.208, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1574, decode.acc_seg: 93.2130, loss: 0.1574 2023-11-03 01:36:08,744 - mmseg - INFO - Iter [18350/20000] lr: 2.674e-07, eta: 0:36:47, time: 1.261, data_time: 0.054, memory: 38534, decode.loss_ce: 0.1439, decode.acc_seg: 93.9150, loss: 0.1439 2023-11-03 01:37:09,212 - mmseg - INFO - Iter [18400/20000] lr: 2.593e-07, eta: 0:35:40, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1479, decode.acc_seg: 93.7167, loss: 0.1479 2023-11-03 01:38:09,677 - mmseg - INFO - Iter [18450/20000] lr: 2.512e-07, eta: 0:34:32, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1485, decode.acc_seg: 93.6108, loss: 0.1485 2023-11-03 01:39:10,111 - mmseg - INFO - Iter [18500/20000] lr: 2.431e-07, eta: 0:33:25, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1434, decode.acc_seg: 93.9493, loss: 0.1434 2023-11-03 01:40:10,625 - mmseg - INFO - Iter [18550/20000] lr: 2.350e-07, eta: 0:32:17, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1479, decode.acc_seg: 93.7615, loss: 0.1479 2023-11-03 01:41:11,111 - mmseg - INFO - Iter [18600/20000] lr: 2.269e-07, eta: 0:31:10, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1547, decode.acc_seg: 93.3221, loss: 0.1547 2023-11-03 01:42:13,981 - mmseg - INFO - Iter [18650/20000] lr: 2.188e-07, eta: 0:30:03, time: 1.257, data_time: 0.055, memory: 38534, decode.loss_ce: 0.1510, decode.acc_seg: 93.5836, loss: 0.1510 2023-11-03 01:43:14,482 - mmseg - INFO - Iter [18700/20000] lr: 2.107e-07, eta: 0:28:56, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1383, decode.acc_seg: 94.0564, loss: 0.1383 2023-11-03 01:44:14,968 - mmseg - INFO - Iter [18750/20000] lr: 2.026e-07, eta: 0:27:49, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1558, decode.acc_seg: 93.5136, loss: 0.1558 2023-11-03 01:45:15,502 - mmseg - INFO - Iter [18800/20000] lr: 1.945e-07, eta: 0:26:41, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1508, decode.acc_seg: 93.7020, loss: 0.1508 2023-11-03 01:46:16,018 - mmseg - INFO - Iter [18850/20000] lr: 1.864e-07, eta: 0:25:34, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1525, decode.acc_seg: 93.6285, loss: 0.1525 2023-11-03 01:47:16,520 - mmseg - INFO - Iter [18900/20000] lr: 1.784e-07, eta: 0:24:27, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1502, decode.acc_seg: 93.7140, loss: 0.1502 2023-11-03 01:48:17,048 - mmseg - INFO - Iter [18950/20000] lr: 1.703e-07, eta: 0:23:20, time: 1.211, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1572, decode.acc_seg: 93.4030, loss: 0.1572 2023-11-03 01:49:19,900 - mmseg - INFO - Saving checkpoint at 19000 iterations 2023-11-03 01:50:21,177 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-03 01:50:21,178 - mmseg - INFO - Iter [19000/20000] lr: 1.622e-07, eta: 0:22:16, time: 2.483, data_time: 0.052, memory: 38534, decode.loss_ce: 0.1474, decode.acc_seg: 93.8620, loss: 0.1474 2023-11-03 01:51:20,717 - mmseg - INFO - per class results: 2023-11-03 01:51:20,722 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 80.37 | 89.46 | | building | 83.28 | 93.79 | | sky | 94.0 | 97.01 | | floor | 82.44 | 91.61 | | tree | 74.33 | 86.91 | | ceiling | 85.62 | 93.41 | | road | 84.84 | 91.4 | | bed | 91.35 | 96.81 | | windowpane | 65.98 | 80.97 | | grass | 71.48 | 89.18 | | cabinet | 64.07 | 75.06 | | sidewalk | 67.0 | 82.1 | | person | 82.45 | 91.99 | | earth | 37.7 | 49.51 | | door | 57.82 | 73.89 | | table | 67.4 | 79.19 | | mountain | 61.92 | 78.62 | | plant | 53.24 | 66.47 | | curtain | 78.4 | 88.07 | | chair | 60.06 | 73.33 | | car | 85.49 | 92.52 | | water | 58.07 | 72.93 | | painting | 73.75 | 88.08 | | sofa | 80.25 | 90.1 | | shelf | 42.59 | 60.9 | | house | 39.5 | 52.16 | | sea | 61.98 | 84.2 | | mirror | 73.3 | 81.7 | | rug | 59.38 | 66.1 | | field | 32.77 | 52.33 | | armchair | 56.62 | 73.93 | | seat | 65.1 | 89.41 | | fence | 45.24 | 62.01 | | desk | 54.88 | 79.06 | | rock | 43.06 | 56.44 | | wardrobe | 51.69 | 68.4 | | lamp | 67.11 | 79.34 | | bathtub | 85.26 | 88.46 | | railing | 41.36 | 56.35 | | cushion | 62.05 | 77.09 | | base | 32.43 | 42.85 | | box | 33.42 | 43.16 | | column | 50.91 | 62.88 | | signboard | 36.39 | 50.18 | | chest of drawers | 38.24 | 61.03 | | counter | 51.69 | 65.63 | | sand | 38.86 | 51.07 | | sink | 76.64 | 85.14 | | skyscraper | 49.51 | 58.05 | | fireplace | 69.24 | 87.21 | | refrigerator | 81.98 | 91.64 | | grandstand | 55.3 | 73.65 | | path | 17.77 | 23.14 | | stairs | 24.68 | 28.79 | | runway | 67.24 | 85.55 | | case | 58.14 | 67.34 | | pool table | 93.56 | 97.83 | | pillow | 59.05 | 68.03 | | screen door | 72.4 | 79.55 | | stairway | 41.68 | 60.48 | | river | 17.34 | 30.58 | | bridge | 78.91 | 89.78 | | bookcase | 34.18 | 51.82 | | blind | 43.5 | 47.36 | | coffee table | 64.8 | 84.16 | | toilet | 89.17 | 93.42 | | flower | 41.14 | 56.56 | | book | 48.62 | 70.97 | | hill | 8.26 | 12.46 | | bench | 50.53 | 58.11 | | countertop | 56.16 | 74.58 | | stove | 81.71 | 90.48 | | palm | 47.06 | 78.6 | | kitchen island | 57.1 | 72.0 | | computer | 76.4 | 88.99 | | swivel chair | 43.82 | 64.63 | | boat | 59.19 | 91.09 | | bar | 61.81 | 68.72 | | arcade machine | 77.08 | 79.16 | | hovel | 10.13 | 10.37 | | bus | 91.54 | 95.36 | | towel | 70.78 | 83.56 | | light | 49.44 | 59.65 | | truck | 47.44 | 58.93 | | tower | 11.83 | 21.81 | | chandelier | 65.44 | 80.89 | | awning | 35.34 | 42.93 | | streetlight | 25.16 | 31.1 | | booth | 34.36 | 34.44 | | television receiver | 72.59 | 88.01 | | airplane | 59.78 | 65.85 | | dirt track | 22.41 | 31.28 | | apparel | 57.58 | 83.03 | | pole | 29.88 | 37.93 | | land | 3.95 | 5.76 | | bannister | 19.64 | 26.79 | | escalator | 63.54 | 78.85 | | ottoman | 48.66 | 65.71 | | bottle | 23.71 | 31.56 | | buffet | 53.98 | 65.71 | | poster | 31.39 | 40.84 | | stage | 12.03 | 18.8 | | van | 48.27 | 65.28 | | ship | 7.02 | 7.32 | | fountain | 15.23 | 16.07 | | conveyer belt | 80.97 | 93.49 | | canopy | 49.03 | 60.5 | | washer | 82.46 | 85.5 | | plaything | 30.98 | 41.81 | | swimming pool | 54.68 | 80.85 | | stool | 49.61 | 64.62 | | barrel | 53.97 | 62.7 | | basket | 39.22 | 52.89 | | waterfall | 52.72 | 63.47 | | tent | 96.28 | 97.68 | | bag | 24.85 | 29.41 | | minibike | 71.31 | 84.48 | | cradle | 85.64 | 96.55 | | oven | 66.88 | 77.12 | | ball | 51.14 | 54.15 | | food | 65.2 | 73.14 | | step | 18.32 | 23.37 | | tank | 52.53 | 62.93 | | trade name | 29.49 | 35.53 | | microwave | 87.27 | 92.68 | | pot | 53.11 | 60.61 | | animal | 70.4 | 72.86 | | bicycle | 59.33 | 77.02 | | lake | 50.22 | 63.73 | | dishwasher | 75.06 | 81.82 | | screen | 59.44 | 88.69 | | blanket | 20.76 | 23.47 | | sculpture | 64.37 | 71.41 | | hood | 58.96 | 68.9 | | sconce | 52.71 | 64.92 | | vase | 43.01 | 61.16 | | traffic light | 33.58 | 53.67 | | tray | 13.16 | 20.0 | | ashcan | 52.18 | 61.86 | | fan | 61.76 | 74.99 | | pier | 39.78 | 42.91 | | crt screen | 5.92 | 14.92 | | plate | 58.21 | 73.92 | | monitor | 11.75 | 12.37 | | bulletin board | 56.13 | 68.96 | | shower | 6.66 | 7.75 | | radiator | 56.73 | 65.8 | | glass | 18.72 | 20.62 | | clock | 33.09 | 39.97 | | flag | 68.95 | 74.26 | +---------------------+-------+-------+ 2023-11-03 01:51:20,722 - mmseg - INFO - Summary: 2023-11-03 01:51:20,722 - mmseg - INFO - +-------+-------+------+ | aAcc | mIoU | mAcc | +-------+-------+------+ | 84.68 | 53.25 | 64.5 | +-------+-------+------+ 2023-11-03 01:51:20,723 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-03 01:51:20,724 - mmseg - INFO - Iter(val) [250] aAcc: 0.8468, mIoU: 0.5325, mAcc: 0.6450, IoU.wall: 0.8037, IoU.building: 0.8328, IoU.sky: 0.9400, IoU.floor: 0.8244, IoU.tree: 0.7433, IoU.ceiling: 0.8562, IoU.road: 0.8484, IoU.bed : 0.9135, IoU.windowpane: 0.6598, IoU.grass: 0.7148, IoU.cabinet: 0.6407, IoU.sidewalk: 0.6700, IoU.person: 0.8245, IoU.earth: 0.3770, IoU.door: 0.5782, IoU.table: 0.6740, IoU.mountain: 0.6192, IoU.plant: 0.5324, IoU.curtain: 0.7840, IoU.chair: 0.6006, IoU.car: 0.8549, IoU.water: 0.5807, IoU.painting: 0.7375, IoU.sofa: 0.8025, IoU.shelf: 0.4259, IoU.house: 0.3950, IoU.sea: 0.6198, IoU.mirror: 0.7330, IoU.rug: 0.5938, IoU.field: 0.3277, IoU.armchair: 0.5662, IoU.seat: 0.6510, IoU.fence: 0.4524, IoU.desk: 0.5488, IoU.rock: 0.4306, IoU.wardrobe: 0.5169, IoU.lamp: 0.6711, IoU.bathtub: 0.8526, IoU.railing: 0.4136, IoU.cushion: 0.6205, IoU.base: 0.3243, IoU.box: 0.3342, IoU.column: 0.5091, IoU.signboard: 0.3639, IoU.chest of drawers: 0.3824, IoU.counter: 0.5169, IoU.sand: 0.3886, IoU.sink: 0.7664, IoU.skyscraper: 0.4951, IoU.fireplace: 0.6924, IoU.refrigerator: 0.8198, IoU.grandstand: 0.5530, IoU.path: 0.1777, IoU.stairs: 0.2468, IoU.runway: 0.6724, IoU.case: 0.5814, IoU.pool table: 0.9356, IoU.pillow: 0.5905, IoU.screen door: 0.7240, IoU.stairway: 0.4168, IoU.river: 0.1734, IoU.bridge: 0.7891, IoU.bookcase: 0.3418, IoU.blind: 0.4350, IoU.coffee table: 0.6480, IoU.toilet: 0.8917, IoU.flower: 0.4114, IoU.book: 0.4862, IoU.hill: 0.0826, IoU.bench: 0.5053, IoU.countertop: 0.5616, IoU.stove: 0.8171, IoU.palm: 0.4706, IoU.kitchen island: 0.5710, IoU.computer: 0.7640, IoU.swivel chair: 0.4382, IoU.boat: 0.5919, IoU.bar: 0.6181, IoU.arcade machine: 0.7708, IoU.hovel: 0.1013, IoU.bus: 0.9154, IoU.towel: 0.7078, IoU.light: 0.4944, IoU.truck: 0.4744, IoU.tower: 0.1183, IoU.chandelier: 0.6544, IoU.awning: 0.3534, IoU.streetlight: 0.2516, IoU.booth: 0.3436, IoU.television receiver: 0.7259, IoU.airplane: 0.5978, IoU.dirt track: 0.2241, IoU.apparel: 0.5758, IoU.pole: 0.2988, IoU.land: 0.0395, IoU.bannister: 0.1964, IoU.escalator: 0.6354, IoU.ottoman: 0.4866, IoU.bottle: 0.2371, IoU.buffet: 0.5398, IoU.poster: 0.3139, IoU.stage: 0.1203, IoU.van: 0.4827, IoU.ship: 0.0702, IoU.fountain: 0.1523, IoU.conveyer belt: 0.8097, IoU.canopy: 0.4903, IoU.washer: 0.8246, IoU.plaything: 0.3098, IoU.swimming pool: 0.5468, IoU.stool: 0.4961, IoU.barrel: 0.5397, IoU.basket: 0.3922, IoU.waterfall: 0.5272, IoU.tent: 0.9628, IoU.bag: 0.2485, IoU.minibike: 0.7131, IoU.cradle: 0.8564, IoU.oven: 0.6688, IoU.ball: 0.5114, IoU.food: 0.6520, IoU.step: 0.1832, IoU.tank: 0.5253, IoU.trade name: 0.2949, IoU.microwave: 0.8727, IoU.pot: 0.5311, IoU.animal: 0.7040, IoU.bicycle: 0.5933, IoU.lake: 0.5022, IoU.dishwasher: 0.7506, IoU.screen: 0.5944, IoU.blanket: 0.2076, IoU.sculpture: 0.6437, IoU.hood: 0.5896, IoU.sconce: 0.5271, IoU.vase: 0.4301, IoU.traffic light: 0.3358, IoU.tray: 0.1316, IoU.ashcan: 0.5218, IoU.fan: 0.6176, IoU.pier: 0.3978, IoU.crt screen: 0.0592, IoU.plate: 0.5821, IoU.monitor: 0.1175, IoU.bulletin board: 0.5613, IoU.shower: 0.0666, IoU.radiator: 0.5673, IoU.glass: 0.1872, IoU.clock: 0.3309, IoU.flag: 0.6895, Acc.wall: 0.8946, Acc.building: 0.9379, Acc.sky: 0.9701, Acc.floor: 0.9161, Acc.tree: 0.8691, Acc.ceiling: 0.9341, Acc.road: 0.9140, Acc.bed : 0.9681, Acc.windowpane: 0.8097, Acc.grass: 0.8918, Acc.cabinet: 0.7506, Acc.sidewalk: 0.8210, Acc.person: 0.9199, Acc.earth: 0.4951, Acc.door: 0.7389, Acc.table: 0.7919, Acc.mountain: 0.7862, Acc.plant: 0.6647, Acc.curtain: 0.8807, Acc.chair: 0.7333, Acc.car: 0.9252, Acc.water: 0.7293, Acc.painting: 0.8808, Acc.sofa: 0.9010, Acc.shelf: 0.6090, Acc.house: 0.5216, Acc.sea: 0.8420, Acc.mirror: 0.8170, Acc.rug: 0.6610, Acc.field: 0.5233, Acc.armchair: 0.7393, Acc.seat: 0.8941, Acc.fence: 0.6201, Acc.desk: 0.7906, Acc.rock: 0.5644, Acc.wardrobe: 0.6840, Acc.lamp: 0.7934, Acc.bathtub: 0.8846, Acc.railing: 0.5635, Acc.cushion: 0.7709, Acc.base: 0.4285, Acc.box: 0.4316, Acc.column: 0.6288, Acc.signboard: 0.5018, Acc.chest of drawers: 0.6103, Acc.counter: 0.6563, Acc.sand: 0.5107, Acc.sink: 0.8514, Acc.skyscraper: 0.5805, Acc.fireplace: 0.8721, Acc.refrigerator: 0.9164, Acc.grandstand: 0.7365, Acc.path: 0.2314, Acc.stairs: 0.2879, Acc.runway: 0.8555, Acc.case: 0.6734, Acc.pool table: 0.9783, Acc.pillow: 0.6803, Acc.screen door: 0.7955, Acc.stairway: 0.6048, Acc.river: 0.3058, Acc.bridge: 0.8978, Acc.bookcase: 0.5182, Acc.blind: 0.4736, Acc.coffee table: 0.8416, Acc.toilet: 0.9342, Acc.flower: 0.5656, Acc.book: 0.7097, Acc.hill: 0.1246, Acc.bench: 0.5811, Acc.countertop: 0.7458, Acc.stove: 0.9048, Acc.palm: 0.7860, Acc.kitchen island: 0.7200, Acc.computer: 0.8899, Acc.swivel chair: 0.6463, Acc.boat: 0.9109, Acc.bar: 0.6872, Acc.arcade machine: 0.7916, Acc.hovel: 0.1037, Acc.bus: 0.9536, Acc.towel: 0.8356, Acc.light: 0.5965, Acc.truck: 0.5893, Acc.tower: 0.2181, Acc.chandelier: 0.8089, Acc.awning: 0.4293, Acc.streetlight: 0.3110, Acc.booth: 0.3444, Acc.television receiver: 0.8801, Acc.airplane: 0.6585, Acc.dirt track: 0.3128, Acc.apparel: 0.8303, Acc.pole: 0.3793, Acc.land: 0.0576, Acc.bannister: 0.2679, Acc.escalator: 0.7885, Acc.ottoman: 0.6571, Acc.bottle: 0.3156, Acc.buffet: 0.6571, Acc.poster: 0.4084, Acc.stage: 0.1880, Acc.van: 0.6528, Acc.ship: 0.0732, Acc.fountain: 0.1607, Acc.conveyer belt: 0.9349, Acc.canopy: 0.6050, Acc.washer: 0.8550, Acc.plaything: 0.4181, Acc.swimming pool: 0.8085, Acc.stool: 0.6462, Acc.barrel: 0.6270, Acc.basket: 0.5289, Acc.waterfall: 0.6347, Acc.tent: 0.9768, Acc.bag: 0.2941, Acc.minibike: 0.8448, Acc.cradle: 0.9655, Acc.oven: 0.7712, Acc.ball: 0.5415, Acc.food: 0.7314, Acc.step: 0.2337, Acc.tank: 0.6293, Acc.trade name: 0.3553, Acc.microwave: 0.9268, Acc.pot: 0.6061, Acc.animal: 0.7286, Acc.bicycle: 0.7702, Acc.lake: 0.6373, Acc.dishwasher: 0.8182, Acc.screen: 0.8869, Acc.blanket: 0.2347, Acc.sculpture: 0.7141, Acc.hood: 0.6890, Acc.sconce: 0.6492, Acc.vase: 0.6116, Acc.traffic light: 0.5367, Acc.tray: 0.2000, Acc.ashcan: 0.6186, Acc.fan: 0.7499, Acc.pier: 0.4291, Acc.crt screen: 0.1492, Acc.plate: 0.7392, Acc.monitor: 0.1237, Acc.bulletin board: 0.6896, Acc.shower: 0.0775, Acc.radiator: 0.6580, Acc.glass: 0.2062, Acc.clock: 0.3997, Acc.flag: 0.7426 2023-11-03 01:52:21,288 - mmseg - INFO - Iter [19050/20000] lr: 1.541e-07, eta: 0:21:12, time: 2.402, data_time: 1.199, memory: 38534, decode.loss_ce: 0.1495, decode.acc_seg: 93.6447, loss: 0.1495 2023-11-03 01:53:21,770 - mmseg - INFO - Iter [19100/20000] lr: 1.460e-07, eta: 0:20:05, time: 1.210, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1552, decode.acc_seg: 93.5893, loss: 0.1552 2023-11-03 01:54:22,229 - mmseg - INFO - Iter [19150/20000] lr: 1.379e-07, eta: 0:18:58, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1484, decode.acc_seg: 93.7877, loss: 0.1484 2023-11-03 01:55:22,685 - mmseg - INFO - Iter [19200/20000] lr: 1.298e-07, eta: 0:17:50, time: 1.209, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1475, decode.acc_seg: 93.7331, loss: 0.1475 2023-11-03 01:56:23,207 - mmseg - INFO - Iter [19250/20000] lr: 1.217e-07, eta: 0:16:43, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1439, decode.acc_seg: 93.9037, loss: 0.1439 2023-11-03 01:57:26,090 - mmseg - INFO - Iter [19300/20000] lr: 1.136e-07, eta: 0:15:36, time: 1.258, data_time: 0.054, memory: 38534, decode.loss_ce: 0.1476, decode.acc_seg: 93.8232, loss: 0.1476 2023-11-03 01:58:26,644 - mmseg - INFO - Iter [19350/20000] lr: 1.055e-07, eta: 0:14:29, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1506, decode.acc_seg: 93.7286, loss: 0.1506 2023-11-03 01:59:27,179 - mmseg - INFO - Iter [19400/20000] lr: 9.736e-08, eta: 0:13:22, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1419, decode.acc_seg: 93.8825, loss: 0.1419 2023-11-03 02:00:27,740 - mmseg - INFO - Iter [19450/20000] lr: 8.926e-08, eta: 0:12:15, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1589, decode.acc_seg: 93.2949, loss: 0.1589 2023-11-03 02:01:28,282 - mmseg - INFO - Iter [19500/20000] lr: 8.116e-08, eta: 0:11:08, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1468, decode.acc_seg: 93.6987, loss: 0.1468 2023-11-03 02:02:28,778 - mmseg - INFO - Iter [19550/20000] lr: 7.306e-08, eta: 0:10:01, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1516, decode.acc_seg: 93.5701, loss: 0.1516 2023-11-03 02:03:31,735 - mmseg - INFO - Iter [19600/20000] lr: 6.496e-08, eta: 0:08:54, time: 1.259, data_time: 0.056, memory: 38534, decode.loss_ce: 0.1419, decode.acc_seg: 93.9721, loss: 0.1419 2023-11-03 02:04:32,230 - mmseg - INFO - Iter [19650/20000] lr: 5.686e-08, eta: 0:07:47, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1413, decode.acc_seg: 93.8589, loss: 0.1413 2023-11-03 02:05:32,747 - mmseg - INFO - Iter [19700/20000] lr: 4.876e-08, eta: 0:06:40, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1477, decode.acc_seg: 93.7399, loss: 0.1477 2023-11-03 02:06:33,280 - mmseg - INFO - Iter [19750/20000] lr: 4.066e-08, eta: 0:05:33, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1481, decode.acc_seg: 93.8888, loss: 0.1481 2023-11-03 02:07:33,765 - mmseg - INFO - Iter [19800/20000] lr: 3.256e-08, eta: 0:04:27, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1493, decode.acc_seg: 93.6241, loss: 0.1493 2023-11-03 02:08:34,291 - mmseg - INFO - Iter [19850/20000] lr: 2.446e-08, eta: 0:03:20, time: 1.211, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1401, decode.acc_seg: 94.0039, loss: 0.1401 2023-11-03 02:09:34,813 - mmseg - INFO - Iter [19900/20000] lr: 1.636e-08, eta: 0:02:13, time: 1.210, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1446, decode.acc_seg: 93.7376, loss: 0.1446 2023-11-03 02:10:37,802 - mmseg - INFO - Iter [19950/20000] lr: 8.261e-09, eta: 0:01:06, time: 1.260, data_time: 0.053, memory: 38534, decode.loss_ce: 0.1550, decode.acc_seg: 93.4989, loss: 0.1550 2023-11-03 02:11:38,334 - mmseg - INFO - Saving checkpoint at 20000 iterations 2023-11-03 02:12:36,139 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-03 02:12:36,139 - mmseg - INFO - Iter [20000/20000] lr: 1.620e-10, eta: 0:00:00, time: 2.367, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1529, decode.acc_seg: 93.5194, loss: 0.1529 2023-11-03 02:13:35,455 - mmseg - INFO - per class results: 2023-11-03 02:13:35,460 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 80.38 | 89.47 | | building | 83.23 | 94.06 | | sky | 94.0 | 97.16 | | floor | 82.81 | 90.94 | | tree | 74.06 | 87.25 | | ceiling | 85.59 | 93.62 | | road | 84.72 | 91.64 | | bed | 91.46 | 96.64 | | windowpane | 65.99 | 81.35 | | grass | 71.27 | 89.61 | | cabinet | 64.22 | 75.02 | | sidewalk | 66.81 | 81.92 | | person | 82.47 | 91.75 | | earth | 37.74 | 49.15 | | door | 58.17 | 73.73 | | table | 67.33 | 78.61 | | mountain | 62.04 | 78.45 | | plant | 53.22 | 65.03 | | curtain | 78.5 | 88.38 | | chair | 60.01 | 73.5 | | car | 85.5 | 92.79 | | water | 57.95 | 72.51 | | painting | 74.01 | 87.42 | | sofa | 80.28 | 89.96 | | shelf | 42.88 | 60.22 | | house | 39.53 | 51.59 | | sea | 61.79 | 84.11 | | mirror | 73.63 | 82.54 | | rug | 64.31 | 73.38 | | field | 31.61 | 49.7 | | armchair | 56.48 | 75.06 | | seat | 65.08 | 89.52 | | fence | 44.75 | 62.86 | | desk | 54.57 | 78.76 | | rock | 43.66 | 57.23 | | wardrobe | 51.88 | 68.86 | | lamp | 67.08 | 79.31 | | bathtub | 85.29 | 88.41 | | railing | 41.55 | 57.15 | | cushion | 61.64 | 76.3 | | base | 32.6 | 43.49 | | box | 33.59 | 43.73 | | column | 50.79 | 62.77 | | signboard | 36.13 | 50.43 | | chest of drawers | 38.47 | 60.92 | | counter | 53.83 | 68.73 | | sand | 38.54 | 51.35 | | sink | 76.84 | 84.07 | | skyscraper | 49.35 | 57.6 | | fireplace | 69.36 | 88.16 | | refrigerator | 82.2 | 92.27 | | grandstand | 55.53 | 73.83 | | path | 17.49 | 21.84 | | stairs | 24.17 | 27.76 | | runway | 67.1 | 85.36 | | case | 59.82 | 71.12 | | pool table | 93.5 | 97.89 | | pillow | 60.29 | 70.78 | | screen door | 72.75 | 79.3 | | stairway | 41.2 | 60.41 | | river | 17.21 | 30.05 | | bridge | 79.68 | 88.28 | | bookcase | 34.5 | 51.7 | | blind | 43.63 | 47.84 | | coffee table | 64.43 | 84.74 | | toilet | 89.34 | 93.59 | | flower | 40.65 | 54.65 | | book | 48.64 | 69.9 | | hill | 8.34 | 12.13 | | bench | 50.33 | 57.64 | | countertop | 57.05 | 74.65 | | stove | 81.89 | 90.62 | | palm | 47.04 | 78.43 | | kitchen island | 56.96 | 72.09 | | computer | 76.14 | 88.78 | | swivel chair | 43.2 | 62.74 | | boat | 59.89 | 90.84 | | bar | 60.62 | 67.55 | | arcade machine | 76.7 | 78.76 | | hovel | 11.14 | 11.45 | | bus | 91.44 | 95.35 | | towel | 70.76 | 83.39 | | light | 47.7 | 55.77 | | truck | 47.92 | 58.27 | | tower | 9.75 | 17.1 | | chandelier | 65.32 | 80.25 | | awning | 35.37 | 42.95 | | streetlight | 24.93 | 30.79 | | booth | 34.76 | 34.87 | | television receiver | 72.91 | 87.72 | | airplane | 59.79 | 65.34 | | dirt track | 23.04 | 31.86 | | apparel | 58.63 | 81.91 | | pole | 29.1 | 36.47 | | land | 3.89 | 5.49 | | bannister | 20.94 | 29.03 | | escalator | 63.29 | 78.19 | | ottoman | 48.51 | 67.4 | | bottle | 23.6 | 31.62 | | buffet | 53.67 | 65.57 | | poster | 31.17 | 40.28 | | stage | 12.58 | 19.84 | | van | 48.7 | 66.7 | | ship | 6.65 | 6.86 | | fountain | 15.42 | 16.27 | | conveyer belt | 81.12 | 93.95 | | canopy | 48.33 | 59.51 | | washer | 82.67 | 85.49 | | plaything | 31.26 | 41.38 | | swimming pool | 55.44 | 82.52 | | stool | 50.09 | 65.6 | | barrel | 56.32 | 65.66 | | basket | 39.71 | 54.46 | | waterfall | 52.68 | 62.62 | | tent | 96.2 | 97.59 | | bag | 25.0 | 30.25 | | minibike | 71.32 | 84.73 | | cradle | 85.85 | 96.56 | | oven | 67.0 | 77.55 | | ball | 53.37 | 57.32 | | food | 65.27 | 72.99 | | step | 18.42 | 23.88 | | tank | 52.63 | 62.94 | | trade name | 28.23 | 33.4 | | microwave | 87.31 | 93.01 | | pot | 53.57 | 61.46 | | animal | 69.86 | 72.14 | | bicycle | 58.72 | 74.76 | | lake | 50.53 | 63.73 | | dishwasher | 74.91 | 82.03 | | screen | 60.23 | 91.05 | | blanket | 20.98 | 23.76 | | sculpture | 65.42 | 72.32 | | hood | 59.4 | 69.81 | | sconce | 52.73 | 64.72 | | vase | 42.86 | 60.85 | | traffic light | 33.42 | 53.21 | | tray | 12.33 | 17.86 | | ashcan | 52.0 | 63.13 | | fan | 61.14 | 72.88 | | pier | 39.72 | 42.75 | | crt screen | 5.83 | 13.84 | | plate | 57.95 | 74.82 | | monitor | 14.7 | 15.64 | | bulletin board | 56.76 | 70.73 | | shower | 6.5 | 7.42 | | radiator | 56.8 | 66.29 | | glass | 19.16 | 21.3 | | clock | 33.03 | 39.27 | | flag | 69.05 | 73.61 | +---------------------+-------+-------+ 2023-11-03 02:13:35,460 - mmseg - INFO - Summary: 2023-11-03 02:13:35,461 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 84.73 | 53.36 | 64.56 | +-------+-------+-------+ 2023-11-03 02:13:35,461 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_20k_ade20k_bs16_lr4e-5_1of4.py 2023-11-03 02:13:35,462 - mmseg - INFO - Iter(val) [250] aAcc: 0.8473, mIoU: 0.5336, mAcc: 0.6456, IoU.wall: 0.8038, IoU.building: 0.8323, IoU.sky: 0.9400, IoU.floor: 0.8281, IoU.tree: 0.7406, IoU.ceiling: 0.8559, IoU.road: 0.8472, IoU.bed : 0.9146, IoU.windowpane: 0.6599, IoU.grass: 0.7127, IoU.cabinet: 0.6422, IoU.sidewalk: 0.6681, IoU.person: 0.8247, IoU.earth: 0.3774, IoU.door: 0.5817, IoU.table: 0.6733, IoU.mountain: 0.6204, IoU.plant: 0.5322, IoU.curtain: 0.7850, IoU.chair: 0.6001, IoU.car: 0.8550, IoU.water: 0.5795, IoU.painting: 0.7401, IoU.sofa: 0.8028, IoU.shelf: 0.4288, IoU.house: 0.3953, IoU.sea: 0.6179, IoU.mirror: 0.7363, IoU.rug: 0.6431, IoU.field: 0.3161, IoU.armchair: 0.5648, IoU.seat: 0.6508, IoU.fence: 0.4475, IoU.desk: 0.5457, IoU.rock: 0.4366, IoU.wardrobe: 0.5188, IoU.lamp: 0.6708, IoU.bathtub: 0.8529, IoU.railing: 0.4155, IoU.cushion: 0.6164, IoU.base: 0.3260, IoU.box: 0.3359, IoU.column: 0.5079, IoU.signboard: 0.3613, IoU.chest of drawers: 0.3847, IoU.counter: 0.5383, IoU.sand: 0.3854, IoU.sink: 0.7684, IoU.skyscraper: 0.4935, IoU.fireplace: 0.6936, IoU.refrigerator: 0.8220, IoU.grandstand: 0.5553, IoU.path: 0.1749, IoU.stairs: 0.2417, IoU.runway: 0.6710, IoU.case: 0.5982, IoU.pool table: 0.9350, IoU.pillow: 0.6029, IoU.screen door: 0.7275, IoU.stairway: 0.4120, IoU.river: 0.1721, IoU.bridge: 0.7968, IoU.bookcase: 0.3450, IoU.blind: 0.4363, IoU.coffee table: 0.6443, IoU.toilet: 0.8934, IoU.flower: 0.4065, IoU.book: 0.4864, IoU.hill: 0.0834, IoU.bench: 0.5033, IoU.countertop: 0.5705, IoU.stove: 0.8189, IoU.palm: 0.4704, IoU.kitchen island: 0.5696, IoU.computer: 0.7614, IoU.swivel chair: 0.4320, IoU.boat: 0.5989, IoU.bar: 0.6062, IoU.arcade machine: 0.7670, IoU.hovel: 0.1114, IoU.bus: 0.9144, IoU.towel: 0.7076, IoU.light: 0.4770, IoU.truck: 0.4792, IoU.tower: 0.0975, IoU.chandelier: 0.6532, IoU.awning: 0.3537, IoU.streetlight: 0.2493, IoU.booth: 0.3476, IoU.television receiver: 0.7291, IoU.airplane: 0.5979, IoU.dirt track: 0.2304, IoU.apparel: 0.5863, IoU.pole: 0.2910, IoU.land: 0.0389, IoU.bannister: 0.2094, IoU.escalator: 0.6329, IoU.ottoman: 0.4851, IoU.bottle: 0.2360, IoU.buffet: 0.5367, IoU.poster: 0.3117, IoU.stage: 0.1258, IoU.van: 0.4870, IoU.ship: 0.0665, IoU.fountain: 0.1542, IoU.conveyer belt: 0.8112, IoU.canopy: 0.4833, IoU.washer: 0.8267, IoU.plaything: 0.3126, IoU.swimming pool: 0.5544, IoU.stool: 0.5009, IoU.barrel: 0.5632, IoU.basket: 0.3971, IoU.waterfall: 0.5268, IoU.tent: 0.9620, IoU.bag: 0.2500, IoU.minibike: 0.7132, IoU.cradle: 0.8585, IoU.oven: 0.6700, IoU.ball: 0.5337, IoU.food: 0.6527, IoU.step: 0.1842, IoU.tank: 0.5263, IoU.trade name: 0.2823, IoU.microwave: 0.8731, IoU.pot: 0.5357, IoU.animal: 0.6986, IoU.bicycle: 0.5872, IoU.lake: 0.5053, IoU.dishwasher: 0.7491, IoU.screen: 0.6023, IoU.blanket: 0.2098, IoU.sculpture: 0.6542, IoU.hood: 0.5940, IoU.sconce: 0.5273, IoU.vase: 0.4286, IoU.traffic light: 0.3342, IoU.tray: 0.1233, IoU.ashcan: 0.5200, IoU.fan: 0.6114, IoU.pier: 0.3972, IoU.crt screen: 0.0583, IoU.plate: 0.5795, IoU.monitor: 0.1470, IoU.bulletin board: 0.5676, IoU.shower: 0.0650, IoU.radiator: 0.5680, IoU.glass: 0.1916, IoU.clock: 0.3303, IoU.flag: 0.6905, Acc.wall: 0.8947, Acc.building: 0.9406, Acc.sky: 0.9716, Acc.floor: 0.9094, Acc.tree: 0.8725, Acc.ceiling: 0.9362, Acc.road: 0.9164, Acc.bed : 0.9664, Acc.windowpane: 0.8135, Acc.grass: 0.8961, Acc.cabinet: 0.7502, Acc.sidewalk: 0.8192, Acc.person: 0.9175, Acc.earth: 0.4915, Acc.door: 0.7373, Acc.table: 0.7861, Acc.mountain: 0.7845, Acc.plant: 0.6503, Acc.curtain: 0.8838, Acc.chair: 0.7350, Acc.car: 0.9279, Acc.water: 0.7251, Acc.painting: 0.8742, Acc.sofa: 0.8996, Acc.shelf: 0.6022, Acc.house: 0.5159, Acc.sea: 0.8411, Acc.mirror: 0.8254, Acc.rug: 0.7338, Acc.field: 0.4970, Acc.armchair: 0.7506, Acc.seat: 0.8952, Acc.fence: 0.6286, Acc.desk: 0.7876, Acc.rock: 0.5723, Acc.wardrobe: 0.6886, Acc.lamp: 0.7931, Acc.bathtub: 0.8841, Acc.railing: 0.5715, Acc.cushion: 0.7630, Acc.base: 0.4349, Acc.box: 0.4373, Acc.column: 0.6277, Acc.signboard: 0.5043, Acc.chest of drawers: 0.6092, Acc.counter: 0.6873, Acc.sand: 0.5135, Acc.sink: 0.8407, Acc.skyscraper: 0.5760, Acc.fireplace: 0.8816, Acc.refrigerator: 0.9227, Acc.grandstand: 0.7383, Acc.path: 0.2184, Acc.stairs: 0.2776, Acc.runway: 0.8536, Acc.case: 0.7112, Acc.pool table: 0.9789, Acc.pillow: 0.7078, Acc.screen door: 0.7930, Acc.stairway: 0.6041, Acc.river: 0.3005, Acc.bridge: 0.8828, Acc.bookcase: 0.5170, Acc.blind: 0.4784, Acc.coffee table: 0.8474, Acc.toilet: 0.9359, Acc.flower: 0.5465, Acc.book: 0.6990, Acc.hill: 0.1213, Acc.bench: 0.5764, Acc.countertop: 0.7465, Acc.stove: 0.9062, Acc.palm: 0.7843, Acc.kitchen island: 0.7209, Acc.computer: 0.8878, Acc.swivel chair: 0.6274, Acc.boat: 0.9084, Acc.bar: 0.6755, Acc.arcade machine: 0.7876, Acc.hovel: 0.1145, Acc.bus: 0.9535, Acc.towel: 0.8339, Acc.light: 0.5577, Acc.truck: 0.5827, Acc.tower: 0.1710, Acc.chandelier: 0.8025, Acc.awning: 0.4295, Acc.streetlight: 0.3079, Acc.booth: 0.3487, Acc.television receiver: 0.8772, Acc.airplane: 0.6534, Acc.dirt track: 0.3186, Acc.apparel: 0.8191, Acc.pole: 0.3647, Acc.land: 0.0549, Acc.bannister: 0.2903, Acc.escalator: 0.7819, Acc.ottoman: 0.6740, Acc.bottle: 0.3162, Acc.buffet: 0.6557, Acc.poster: 0.4028, Acc.stage: 0.1984, Acc.van: 0.6670, Acc.ship: 0.0686, Acc.fountain: 0.1627, Acc.conveyer belt: 0.9395, Acc.canopy: 0.5951, Acc.washer: 0.8549, Acc.plaything: 0.4138, Acc.swimming pool: 0.8252, Acc.stool: 0.6560, Acc.barrel: 0.6566, Acc.basket: 0.5446, Acc.waterfall: 0.6262, Acc.tent: 0.9759, Acc.bag: 0.3025, Acc.minibike: 0.8473, Acc.cradle: 0.9656, Acc.oven: 0.7755, Acc.ball: 0.5732, Acc.food: 0.7299, Acc.step: 0.2388, Acc.tank: 0.6294, Acc.trade name: 0.3340, Acc.microwave: 0.9301, Acc.pot: 0.6146, Acc.animal: 0.7214, Acc.bicycle: 0.7476, Acc.lake: 0.6373, Acc.dishwasher: 0.8203, Acc.screen: 0.9105, Acc.blanket: 0.2376, Acc.sculpture: 0.7232, Acc.hood: 0.6981, Acc.sconce: 0.6472, Acc.vase: 0.6085, Acc.traffic light: 0.5321, Acc.tray: 0.1786, Acc.ashcan: 0.6313, Acc.fan: 0.7288, Acc.pier: 0.4275, Acc.crt screen: 0.1384, Acc.plate: 0.7482, Acc.monitor: 0.1564, Acc.bulletin board: 0.7073, Acc.shower: 0.0742, Acc.radiator: 0.6629, Acc.glass: 0.2130, Acc.clock: 0.3927, Acc.flag: 0.7361