2023-11-10 02:39:31,307 - mmseg - INFO - Multi-processing start method is `None` 2023-11-10 02:39:31,312 - mmseg - INFO - OpenCV num_threads is `128 2023-11-10 02:39:31,312 - mmseg - INFO - OMP num threads is 1 2023-11-10 02:39:31,384 - 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+ ------------------------------------------------------------ 2023-11-10 02:39:31,384 - mmseg - INFO - Distributed training: True 2023-11-10 02:39:31,657 - 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=2526, 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=200, warmup_ratio=1e-06, power=1.0, min_lr=0.0, by_epoch=False) runner = dict(type='IterBasedRunner', max_iters=10000) 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_10k_ade20k_bs16_lr4e-5_1of8' gpu_ids = range(0, 8) auto_resume = False 2023-11-10 02:39:36,133 - mmseg - INFO - Set random seed to 180439972, deterministic: False 2023-11-10 02:40:57,810 - mmseg - INFO - 2023-11-10 02:41:19,867 - 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 2023-11-10 02:41:19,876 - 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'}} ) 2023-11-10 02:41:20,424 - mmseg - INFO - Loaded 20210 images 2023-11-10 02:41:20,434 - mmseg - INFO - Randomly select 2526 images 2023-11-10 02:41:21,808 - mmseg - INFO - {'num_layers': 48, 'layer_decay_rate': 0.95} 2023-11-10 02:41:21,808 - mmseg - INFO - Build LayerDecayOptimizerConstructor 0.950000 - 50 2023-11-10 02:41:21,815 - 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 } } 2023-11-10 02:41:48,276 - mmseg - INFO - trainable parameters: 5906608150 2023-11-10 02:41:48,278 - mmseg - INFO - total parameters: 5906608150 2023-11-10 02:41:48,323 - mmseg - INFO - Loaded 2000 images 2023-11-10 02:41:48,323 - mmseg - INFO - Start running, host: wangwenhai@SH-IDC1-10-140-37-25, work_dir: /mnt/petrelfs/wangwenhai/workspace/ViTDetection/mmsegmentation/work_dirs/segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8 2023-11-10 02:41:48,324 - 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 -------------------- 2023-11-10 02:41:48,324 - mmseg - INFO - workflow: [('train', 1)], max: 10000 iters 2023-11-10 02:41:48,331 - mmseg - INFO - Checkpoints will be saved to /mnt/petrelfs/wangwenhai/workspace/ViTDetection/mmsegmentation/work_dirs/segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8 by HardDiskBackend. 2023-11-10 02:43:41,239 - mmseg - INFO - Iter [50/10000] lr: 7.899e-07, eta: 3:33:32, time: 1.288, data_time: 0.009, memory: 38534, decode.loss_ce: 4.1298, decode.acc_seg: 1.1571, loss: 4.1298 2023-11-10 02:44:42,054 - mmseg - INFO - Iter [100/10000] lr: 1.588e-06, eta: 3:26:34, time: 1.216, data_time: 0.007, memory: 38534, decode.loss_ce: 3.3589, decode.acc_seg: 26.3350, loss: 3.3589 2023-11-10 02:45:42,964 - mmseg - INFO - Iter [150/10000] lr: 2.378e-06, eta: 3:23:41, time: 1.218, data_time: 0.007, memory: 38534, decode.loss_ce: 1.8237, decode.acc_seg: 54.8012, loss: 1.8237 2023-11-10 02:46:46,082 - mmseg - INFO - Iter [200/10000] lr: 3.159e-06, eta: 3:23:31, time: 1.262, data_time: 0.050, memory: 38534, decode.loss_ce: 1.3015, decode.acc_seg: 65.6727, loss: 1.3015 2023-11-10 02:47:46,967 - mmseg - INFO - Iter [250/10000] lr: 3.159e-06, eta: 3:21:34, time: 1.218, data_time: 0.007, memory: 38534, decode.loss_ce: 1.0344, decode.acc_seg: 69.9806, loss: 1.0344 2023-11-10 02:48:47,833 - mmseg - INFO - Iter [300/10000] lr: 3.143e-06, eta: 3:19:54, time: 1.217, data_time: 0.007, memory: 38534, decode.loss_ce: 0.9132, decode.acc_seg: 73.4998, loss: 0.9132 2023-11-10 02:49:51,086 - mmseg - INFO - Iter [350/10000] lr: 3.127e-06, eta: 3:19:32, time: 1.265, data_time: 0.051, memory: 38534, decode.loss_ce: 0.8129, decode.acc_seg: 75.0050, loss: 0.8129 2023-11-10 02:50:52,013 - mmseg - INFO - Iter [400/10000] lr: 3.111e-06, eta: 3:18:03, time: 1.219, data_time: 0.007, memory: 38534, decode.loss_ce: 0.7998, decode.acc_seg: 74.3467, loss: 0.7998 2023-11-10 02:51:52,944 - mmseg - INFO - Iter [450/10000] lr: 3.094e-06, eta: 3:16:41, time: 1.219, data_time: 0.007, memory: 38534, decode.loss_ce: 0.7616, decode.acc_seg: 75.7469, loss: 0.7616 2023-11-10 02:52:56,314 - mmseg - INFO - Iter [500/10000] lr: 3.078e-06, eta: 3:16:09, time: 1.267, data_time: 0.053, memory: 38534, decode.loss_ce: 0.6794, decode.acc_seg: 77.4544, loss: 0.6794 2023-11-10 02:53:57,149 - mmseg - INFO - Iter [550/10000] lr: 3.062e-06, eta: 3:14:48, time: 1.217, data_time: 0.007, memory: 38534, decode.loss_ce: 0.6427, decode.acc_seg: 79.2950, loss: 0.6427 2023-11-10 02:54:58,025 - mmseg - INFO - Iter [600/10000] lr: 3.046e-06, eta: 3:13:31, time: 1.217, data_time: 0.007, memory: 38534, decode.loss_ce: 0.6445, decode.acc_seg: 79.1383, loss: 0.6445 2023-11-10 02:56:01,205 - mmseg - INFO - Iter [650/10000] lr: 3.030e-06, eta: 3:12:50, time: 1.264, data_time: 0.051, memory: 38534, decode.loss_ce: 0.5761, decode.acc_seg: 79.9854, loss: 0.5761 2023-11-10 02:57:02,037 - mmseg - INFO - Iter [700/10000] lr: 3.013e-06, eta: 3:11:34, time: 1.217, data_time: 0.007, memory: 38534, decode.loss_ce: 0.5813, decode.acc_seg: 80.4364, loss: 0.5813 2023-11-10 02:58:02,913 - mmseg - INFO - Iter [750/10000] lr: 2.997e-06, eta: 3:10:21, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.5717, decode.acc_seg: 80.7978, loss: 0.5717 2023-11-10 02:59:06,111 - mmseg - INFO - Iter [800/10000] lr: 2.981e-06, eta: 3:09:36, time: 1.264, data_time: 0.050, memory: 38534, decode.loss_ce: 0.5373, decode.acc_seg: 81.2860, loss: 0.5373 2023-11-10 03:00:07,034 - mmseg - INFO - Iter [850/10000] lr: 2.965e-06, eta: 3:08:24, time: 1.218, data_time: 0.007, memory: 38534, decode.loss_ce: 0.4866, decode.acc_seg: 83.2895, loss: 0.4866 2023-11-10 03:01:07,992 - mmseg - INFO - Iter [900/10000] lr: 2.949e-06, eta: 3:07:14, time: 1.219, data_time: 0.008, memory: 38534, decode.loss_ce: 0.5049, decode.acc_seg: 82.7966, loss: 0.5049 2023-11-10 03:02:11,242 - mmseg - INFO - Iter [950/10000] lr: 2.932e-06, eta: 3:06:27, time: 1.265, data_time: 0.051, memory: 38534, decode.loss_ce: 0.5199, decode.acc_seg: 81.9246, loss: 0.5199 2023-11-10 03:03:12,133 - mmseg - INFO - Saving checkpoint at 1000 iterations 2023-11-10 03:04:06,048 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 03:04:06,048 - mmseg - INFO - Iter [1000/10000] lr: 2.916e-06, eta: 3:13:22, time: 2.296, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4861, decode.acc_seg: 82.9843, loss: 0.4861 2023-11-10 03:05:48,865 - mmseg - INFO - per class results: 2023-11-10 03:05:48,870 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 76.5 | 87.42 | | building | 80.94 | 91.21 | | sky | 92.87 | 96.66 | | floor | 80.18 | 89.58 | | tree | 71.79 | 88.75 | | ceiling | 82.73 | 92.89 | | road | 81.79 | 86.0 | | bed | 88.21 | 95.43 | | windowpane | 60.73 | 77.77 | | grass | 65.42 | 84.79 | | cabinet | 62.58 | 81.36 | | sidewalk | 61.18 | 87.67 | | person | 78.92 | 91.86 | | earth | 35.79 | 52.16 | | door | 47.1 | 54.94 | | table | 59.43 | 78.58 | | mountain | 57.51 | 73.89 | | plant | 48.35 | 56.82 | | curtain | 72.72 | 83.27 | | chair | 55.85 | 69.63 | | car | 80.59 | 93.28 | | water | 44.36 | 57.37 | | painting | 62.31 | 85.83 | | sofa | 68.99 | 91.07 | | shelf | 35.96 | 52.28 | | house | 42.67 | 68.88 | | sea | 56.53 | 78.84 | | mirror | 67.49 | 79.07 | | rug | 66.12 | 71.99 | | field | 27.2 | 42.45 | | armchair | 40.59 | 48.9 | | seat | 58.17 | 83.72 | | fence | 43.54 | 62.85 | | desk | 38.36 | 51.88 | | rock | 49.03 | 61.09 | | wardrobe | 42.91 | 45.43 | | lamp | 59.07 | 71.45 | | bathtub | 77.29 | 87.3 | | railing | 36.57 | 49.46 | | cushion | 58.05 | 69.82 | | base | 16.75 | 22.96 | | box | 20.45 | 24.39 | | column | 41.72 | 45.48 | | signboard | 33.57 | 46.9 | | chest of drawers | 34.76 | 48.39 | | counter | 46.86 | 58.96 | | sand | 66.1 | 74.98 | | sink | 68.35 | 74.57 | | skyscraper | 46.85 | 59.21 | | fireplace | 73.49 | 91.92 | | refrigerator | 66.68 | 75.95 | | grandstand | 43.19 | 69.47 | | path | 11.87 | 14.86 | | stairs | 25.09 | 34.86 | | runway | 75.27 | 94.44 | | case | 55.7 | 86.62 | | pool table | 90.83 | 95.91 | | pillow | 57.3 | 67.51 | | screen door | 69.0 | 81.9 | | stairway | 31.3 | 58.65 | | river | 21.89 | 54.65 | | bridge | 37.86 | 41.78 | | bookcase | 28.01 | 57.97 | | blind | 28.47 | 29.43 | | coffee table | 61.4 | 82.4 | | toilet | 84.31 | 90.24 | | flower | 35.37 | 48.68 | | book | 42.48 | 56.16 | | hill | 2.1 | 2.16 | | bench | 38.12 | 42.79 | | countertop | 56.86 | 74.47 | | stove | 75.55 | 84.33 | | palm | 47.93 | 72.93 | | kitchen island | 39.08 | 55.26 | | computer | 70.72 | 89.8 | | swivel chair | 41.72 | 54.45 | | boat | 63.68 | 85.13 | | bar | 54.0 | 58.97 | | arcade machine | 61.28 | 63.84 | | hovel | 13.84 | 14.39 | | bus | 88.49 | 93.68 | | towel | 59.05 | 81.95 | | light | 39.71 | 46.95 | | truck | 38.33 | 46.96 | | tower | 12.63 | 17.93 | | chandelier | 59.88 | 75.88 | | awning | 23.62 | 26.71 | | streetlight | 16.76 | 27.92 | | booth | 36.53 | 45.71 | | television receiver | 66.07 | 85.01 | | airplane | 53.94 | 67.24 | | dirt track | 12.74 | 18.39 | | apparel | 37.21 | 51.93 | | pole | 11.81 | 13.19 | | land | 1.05 | 1.29 | | bannister | 4.11 | 4.75 | | escalator | 12.98 | 13.18 | | ottoman | 40.16 | 47.49 | | bottle | 25.92 | 34.96 | | buffet | 24.83 | 25.63 | | poster | 10.58 | 14.91 | | stage | 8.01 | 10.41 | | van | 31.64 | 37.17 | | ship | 7.82 | 7.86 | | fountain | 2.59 | 2.63 | | conveyer belt | 81.62 | 85.17 | | canopy | 43.73 | 53.56 | | washer | 50.4 | 51.69 | | plaything | 33.76 | 64.73 | | swimming pool | 42.86 | 90.61 | | stool | 41.09 | 64.4 | | barrel | 12.27 | 12.56 | | basket | 33.64 | 55.2 | | waterfall | 54.04 | 81.59 | | tent | 92.72 | 98.29 | | bag | 1.94 | 1.97 | | minibike | 59.43 | 70.98 | | cradle | 73.76 | 97.7 | | oven | 45.95 | 56.48 | | ball | 32.87 | 70.95 | | food | 31.25 | 35.09 | | step | 3.84 | 4.2 | | tank | 16.25 | 16.33 | | trade name | 17.42 | 19.04 | | microwave | 79.85 | 91.69 | | pot | 45.71 | 52.24 | | animal | 71.32 | 75.67 | | bicycle | 55.56 | 66.59 | | lake | 0.0 | 0.0 | | dishwasher | 59.2 | 63.38 | | screen | 49.81 | 93.17 | | blanket | 1.5 | 1.56 | | sculpture | 45.04 | 51.57 | | hood | 47.93 | 51.7 | | sconce | 31.2 | 38.01 | | vase | 31.98 | 39.69 | | traffic light | 20.92 | 28.26 | | tray | 1.75 | 1.91 | | ashcan | 42.52 | 56.41 | | fan | 47.07 | 55.61 | | pier | 33.98 | 34.6 | | crt screen | 3.26 | 6.34 | | plate | 49.59 | 66.18 | | monitor | 0.38 | 0.39 | | bulletin board | 35.69 | 36.59 | | shower | 0.0 | 0.0 | | radiator | 52.04 | 61.06 | | glass | 9.64 | 10.03 | | clock | 14.76 | 15.0 | | flag | 65.06 | 70.66 | +---------------------+-------+-------+ 2023-11-10 03:05:48,870 - mmseg - INFO - Summary: 2023-11-10 03:05:48,870 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 81.88 | 44.58 | 55.73 | +-------+-------+-------+ 2023-11-10 03:05:48,871 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 03:05:48,872 - mmseg - INFO - Iter(val) [250] aAcc: 0.8188, mIoU: 0.4458, mAcc: 0.5573, IoU.wall: 0.7650, IoU.building: 0.8094, IoU.sky: 0.9287, IoU.floor: 0.8018, IoU.tree: 0.7179, IoU.ceiling: 0.8273, IoU.road: 0.8179, IoU.bed : 0.8821, IoU.windowpane: 0.6073, IoU.grass: 0.6542, IoU.cabinet: 0.6258, IoU.sidewalk: 0.6118, IoU.person: 0.7892, IoU.earth: 0.3579, IoU.door: 0.4710, IoU.table: 0.5943, IoU.mountain: 0.5751, IoU.plant: 0.4835, IoU.curtain: 0.7272, IoU.chair: 0.5585, IoU.car: 0.8059, IoU.water: 0.4436, IoU.painting: 0.6231, IoU.sofa: 0.6899, IoU.shelf: 0.3596, IoU.house: 0.4267, IoU.sea: 0.5653, IoU.mirror: 0.6749, IoU.rug: 0.6612, IoU.field: 0.2720, IoU.armchair: 0.4059, IoU.seat: 0.5817, IoU.fence: 0.4354, IoU.desk: 0.3836, IoU.rock: 0.4903, IoU.wardrobe: 0.4291, IoU.lamp: 0.5907, IoU.bathtub: 0.7729, IoU.railing: 0.3657, IoU.cushion: 0.5805, IoU.base: 0.1675, IoU.box: 0.2045, IoU.column: 0.4172, IoU.signboard: 0.3357, IoU.chest of drawers: 0.3476, IoU.counter: 0.4686, IoU.sand: 0.6610, IoU.sink: 0.6835, IoU.skyscraper: 0.4685, IoU.fireplace: 0.7349, IoU.refrigerator: 0.6668, IoU.grandstand: 0.4319, IoU.path: 0.1187, IoU.stairs: 0.2509, IoU.runway: 0.7527, IoU.case: 0.5570, IoU.pool table: 0.9083, IoU.pillow: 0.5730, IoU.screen door: 0.6900, IoU.stairway: 0.3130, IoU.river: 0.2189, IoU.bridge: 0.3786, IoU.bookcase: 0.2801, IoU.blind: 0.2847, IoU.coffee table: 0.6140, IoU.toilet: 0.8431, IoU.flower: 0.3537, IoU.book: 0.4248, IoU.hill: 0.0210, IoU.bench: 0.3812, IoU.countertop: 0.5686, IoU.stove: 0.7555, IoU.palm: 0.4793, IoU.kitchen island: 0.3908, IoU.computer: 0.7072, IoU.swivel chair: 0.4172, IoU.boat: 0.6368, IoU.bar: 0.5400, IoU.arcade machine: 0.6128, IoU.hovel: 0.1384, IoU.bus: 0.8849, IoU.towel: 0.5905, IoU.light: 0.3971, IoU.truck: 0.3833, IoU.tower: 0.1263, IoU.chandelier: 0.5988, IoU.awning: 0.2362, IoU.streetlight: 0.1676, IoU.booth: 0.3653, IoU.television receiver: 0.6607, IoU.airplane: 0.5394, IoU.dirt track: 0.1274, IoU.apparel: 0.3721, IoU.pole: 0.1181, IoU.land: 0.0105, IoU.bannister: 0.0411, IoU.escalator: 0.1298, IoU.ottoman: 0.4016, IoU.bottle: 0.2592, IoU.buffet: 0.2483, IoU.poster: 0.1058, IoU.stage: 0.0801, IoU.van: 0.3164, IoU.ship: 0.0782, IoU.fountain: 0.0259, IoU.conveyer belt: 0.8162, IoU.canopy: 0.4373, IoU.washer: 0.5040, IoU.plaything: 0.3376, IoU.swimming pool: 0.4286, IoU.stool: 0.4109, IoU.barrel: 0.1227, IoU.basket: 0.3364, IoU.waterfall: 0.5404, IoU.tent: 0.9272, IoU.bag: 0.0194, IoU.minibike: 0.5943, IoU.cradle: 0.7376, IoU.oven: 0.4595, IoU.ball: 0.3287, IoU.food: 0.3125, IoU.step: 0.0384, IoU.tank: 0.1625, IoU.trade name: 0.1742, IoU.microwave: 0.7985, IoU.pot: 0.4571, IoU.animal: 0.7132, IoU.bicycle: 0.5556, IoU.lake: 0.0000, IoU.dishwasher: 0.5920, IoU.screen: 0.4981, IoU.blanket: 0.0150, IoU.sculpture: 0.4504, IoU.hood: 0.4793, IoU.sconce: 0.3120, IoU.vase: 0.3198, IoU.traffic light: 0.2092, IoU.tray: 0.0175, IoU.ashcan: 0.4252, IoU.fan: 0.4707, IoU.pier: 0.3398, IoU.crt screen: 0.0326, IoU.plate: 0.4959, IoU.monitor: 0.0038, IoU.bulletin board: 0.3569, IoU.shower: 0.0000, IoU.radiator: 0.5204, IoU.glass: 0.0964, IoU.clock: 0.1476, IoU.flag: 0.6506, Acc.wall: 0.8742, Acc.building: 0.9121, Acc.sky: 0.9666, Acc.floor: 0.8958, Acc.tree: 0.8875, Acc.ceiling: 0.9289, Acc.road: 0.8600, Acc.bed : 0.9543, Acc.windowpane: 0.7777, Acc.grass: 0.8479, Acc.cabinet: 0.8136, Acc.sidewalk: 0.8767, Acc.person: 0.9186, Acc.earth: 0.5216, Acc.door: 0.5494, Acc.table: 0.7858, Acc.mountain: 0.7389, Acc.plant: 0.5682, Acc.curtain: 0.8327, Acc.chair: 0.6963, Acc.car: 0.9328, Acc.water: 0.5737, Acc.painting: 0.8583, Acc.sofa: 0.9107, Acc.shelf: 0.5228, Acc.house: 0.6888, Acc.sea: 0.7884, Acc.mirror: 0.7907, Acc.rug: 0.7199, Acc.field: 0.4245, Acc.armchair: 0.4890, Acc.seat: 0.8372, Acc.fence: 0.6285, Acc.desk: 0.5188, Acc.rock: 0.6109, Acc.wardrobe: 0.4543, Acc.lamp: 0.7145, Acc.bathtub: 0.8730, Acc.railing: 0.4946, Acc.cushion: 0.6982, Acc.base: 0.2296, Acc.box: 0.2439, Acc.column: 0.4548, Acc.signboard: 0.4690, Acc.chest of drawers: 0.4839, Acc.counter: 0.5896, Acc.sand: 0.7498, Acc.sink: 0.7457, Acc.skyscraper: 0.5921, Acc.fireplace: 0.9192, Acc.refrigerator: 0.7595, Acc.grandstand: 0.6947, Acc.path: 0.1486, Acc.stairs: 0.3486, Acc.runway: 0.9444, Acc.case: 0.8662, Acc.pool table: 0.9591, Acc.pillow: 0.6751, Acc.screen door: 0.8190, Acc.stairway: 0.5865, Acc.river: 0.5465, Acc.bridge: 0.4178, Acc.bookcase: 0.5797, Acc.blind: 0.2943, Acc.coffee table: 0.8240, Acc.toilet: 0.9024, Acc.flower: 0.4868, Acc.book: 0.5616, Acc.hill: 0.0216, Acc.bench: 0.4279, Acc.countertop: 0.7447, Acc.stove: 0.8433, Acc.palm: 0.7293, Acc.kitchen island: 0.5526, Acc.computer: 0.8980, Acc.swivel chair: 0.5445, Acc.boat: 0.8513, Acc.bar: 0.5897, Acc.arcade machine: 0.6384, Acc.hovel: 0.1439, Acc.bus: 0.9368, Acc.towel: 0.8195, Acc.light: 0.4695, Acc.truck: 0.4696, Acc.tower: 0.1793, Acc.chandelier: 0.7588, Acc.awning: 0.2671, Acc.streetlight: 0.2792, Acc.booth: 0.4571, Acc.television receiver: 0.8501, Acc.airplane: 0.6724, Acc.dirt track: 0.1839, Acc.apparel: 0.5193, Acc.pole: 0.1319, Acc.land: 0.0129, Acc.bannister: 0.0475, Acc.escalator: 0.1318, Acc.ottoman: 0.4749, Acc.bottle: 0.3496, Acc.buffet: 0.2563, Acc.poster: 0.1491, Acc.stage: 0.1041, Acc.van: 0.3717, Acc.ship: 0.0786, Acc.fountain: 0.0263, Acc.conveyer belt: 0.8517, Acc.canopy: 0.5356, Acc.washer: 0.5169, Acc.plaything: 0.6473, Acc.swimming pool: 0.9061, Acc.stool: 0.6440, Acc.barrel: 0.1256, Acc.basket: 0.5520, Acc.waterfall: 0.8159, Acc.tent: 0.9829, Acc.bag: 0.0197, Acc.minibike: 0.7098, Acc.cradle: 0.9770, Acc.oven: 0.5648, Acc.ball: 0.7095, Acc.food: 0.3509, Acc.step: 0.0420, Acc.tank: 0.1633, Acc.trade name: 0.1904, Acc.microwave: 0.9169, Acc.pot: 0.5224, Acc.animal: 0.7567, Acc.bicycle: 0.6659, Acc.lake: 0.0000, Acc.dishwasher: 0.6338, Acc.screen: 0.9317, Acc.blanket: 0.0156, Acc.sculpture: 0.5157, Acc.hood: 0.5170, Acc.sconce: 0.3801, Acc.vase: 0.3969, Acc.traffic light: 0.2826, Acc.tray: 0.0191, Acc.ashcan: 0.5641, Acc.fan: 0.5561, Acc.pier: 0.3460, Acc.crt screen: 0.0634, Acc.plate: 0.6618, Acc.monitor: 0.0039, Acc.bulletin board: 0.3659, Acc.shower: 0.0000, Acc.radiator: 0.6106, Acc.glass: 0.1003, Acc.clock: 0.1500, Acc.flag: 0.7066 2023-11-10 03:06:49,905 - mmseg - INFO - Iter [1050/10000] lr: 2.900e-06, eta: 3:26:25, time: 3.277, data_time: 2.064, memory: 38534, decode.loss_ce: 0.4568, decode.acc_seg: 84.4807, loss: 0.4568 2023-11-10 03:07:50,829 - mmseg - INFO - Iter [1100/10000] lr: 2.884e-06, eta: 3:24:09, time: 1.218, data_time: 0.007, memory: 38534, decode.loss_ce: 0.4660, decode.acc_seg: 83.8041, loss: 0.4660 2023-11-10 03:08:54,021 - mmseg - INFO - Iter [1150/10000] lr: 2.868e-06, eta: 3:22:17, time: 1.264, data_time: 0.052, memory: 38534, decode.loss_ce: 0.4524, decode.acc_seg: 83.9482, loss: 0.4524 2023-11-10 03:09:54,972 - mmseg - INFO - Iter [1200/10000] lr: 2.851e-06, eta: 3:20:12, time: 1.219, data_time: 0.008, memory: 38534, decode.loss_ce: 0.4085, decode.acc_seg: 85.0495, loss: 0.4085 2023-11-10 03:10:55,867 - mmseg - INFO - Iter [1250/10000] lr: 2.835e-06, eta: 3:18:12, time: 1.218, data_time: 0.007, memory: 38534, decode.loss_ce: 0.4073, decode.acc_seg: 85.0661, loss: 0.4073 2023-11-10 03:11:59,034 - mmseg - INFO - Iter [1300/10000] lr: 2.819e-06, eta: 3:16:32, time: 1.263, data_time: 0.051, memory: 38534, decode.loss_ce: 0.4388, decode.acc_seg: 84.7232, loss: 0.4388 2023-11-10 03:12:59,929 - mmseg - INFO - Iter [1350/10000] lr: 2.803e-06, eta: 3:14:41, time: 1.218, data_time: 0.007, memory: 38534, decode.loss_ce: 0.4042, decode.acc_seg: 85.3311, loss: 0.4042 2023-11-10 03:14:00,851 - mmseg - INFO - Iter [1400/10000] lr: 2.787e-06, eta: 3:12:53, time: 1.218, data_time: 0.007, memory: 38534, decode.loss_ce: 0.4048, decode.acc_seg: 85.4285, loss: 0.4048 2023-11-10 03:15:04,269 - mmseg - INFO - Iter [1450/10000] lr: 2.770e-06, eta: 3:11:22, time: 1.268, data_time: 0.057, memory: 38534, decode.loss_ce: 0.4065, decode.acc_seg: 85.6826, loss: 0.4065 2023-11-10 03:16:05,233 - mmseg - INFO - Iter [1500/10000] lr: 2.754e-06, eta: 3:09:40, time: 1.219, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3856, decode.acc_seg: 86.1506, loss: 0.3856 2023-11-10 03:17:06,279 - mmseg - INFO - Iter [1550/10000] lr: 2.738e-06, eta: 3:08:01, time: 1.221, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3644, decode.acc_seg: 86.5567, loss: 0.3644 2023-11-10 03:18:09,665 - mmseg - INFO - Iter [1600/10000] lr: 2.722e-06, eta: 3:06:37, time: 1.268, data_time: 0.054, memory: 38534, decode.loss_ce: 0.3792, decode.acc_seg: 86.5686, loss: 0.3792 2023-11-10 03:19:10,594 - mmseg - INFO - Iter [1650/10000] lr: 2.706e-06, eta: 3:05:01, time: 1.219, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3796, decode.acc_seg: 86.4155, loss: 0.3796 2023-11-10 03:20:11,520 - mmseg - INFO - Iter [1700/10000] lr: 2.689e-06, eta: 3:03:27, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3605, decode.acc_seg: 86.6520, loss: 0.3605 2023-11-10 03:21:14,732 - mmseg - INFO - Iter [1750/10000] lr: 2.673e-06, eta: 3:02:07, time: 1.264, data_time: 0.051, memory: 38534, decode.loss_ce: 0.3636, decode.acc_seg: 86.8912, loss: 0.3636 2023-11-10 03:22:15,646 - mmseg - INFO - Iter [1800/10000] lr: 2.657e-06, eta: 3:00:36, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3919, decode.acc_seg: 86.5974, loss: 0.3919 2023-11-10 03:23:16,575 - mmseg - INFO - Iter [1850/10000] lr: 2.641e-06, eta: 2:59:07, time: 1.219, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3608, decode.acc_seg: 86.7973, loss: 0.3608 2023-11-10 03:24:19,927 - mmseg - INFO - Iter [1900/10000] lr: 2.625e-06, eta: 2:57:50, time: 1.267, data_time: 0.055, memory: 38534, decode.loss_ce: 0.3574, decode.acc_seg: 86.7514, loss: 0.3574 2023-11-10 03:25:20,838 - mmseg - INFO - Iter [1950/10000] lr: 2.608e-06, eta: 2:56:24, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3416, decode.acc_seg: 87.6318, loss: 0.3416 2023-11-10 03:26:21,740 - mmseg - INFO - Saving checkpoint at 2000 iterations 2023-11-10 03:27:13,205 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 03:27:13,205 - mmseg - INFO - Iter [2000/10000] lr: 2.592e-06, eta: 2:58:25, time: 2.247, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3458, decode.acc_seg: 87.4546, loss: 0.3458 2023-11-10 03:28:07,256 - mmseg - INFO - per class results: 2023-11-10 03:28:07,261 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 76.55 | 87.77 | | building | 81.29 | 91.05 | | sky | 93.38 | 96.4 | | floor | 81.86 | 91.46 | | tree | 73.62 | 89.27 | | ceiling | 83.11 | 93.75 | | road | 81.92 | 85.15 | | bed | 89.39 | 95.58 | | windowpane | 61.44 | 82.36 | | grass | 67.71 | 82.58 | | cabinet | 62.94 | 72.84 | | sidewalk | 61.77 | 90.59 | | person | 80.02 | 91.49 | | earth | 31.71 | 41.1 | | door | 48.83 | 56.07 | | table | 62.93 | 75.36 | | mountain | 54.64 | 72.97 | | plant | 50.88 | 62.63 | | curtain | 70.82 | 85.56 | | chair | 54.98 | 65.83 | | car | 83.02 | 92.21 | | water | 45.15 | 59.56 | | painting | 67.94 | 87.81 | | sofa | 71.25 | 88.66 | | shelf | 38.27 | 58.8 | | house | 45.63 | 75.96 | | sea | 49.81 | 83.81 | | mirror | 70.54 | 78.57 | | rug | 65.72 | 70.73 | | field | 28.42 | 57.32 | | armchair | 45.37 | 65.75 | | seat | 65.77 | 81.47 | | fence | 44.72 | 56.2 | | desk | 43.46 | 58.16 | | rock | 41.7 | 51.14 | | wardrobe | 52.96 | 73.85 | | lamp | 61.02 | 72.1 | | bathtub | 82.75 | 90.32 | | railing | 38.48 | 50.6 | | cushion | 58.03 | 71.31 | | base | 15.42 | 18.94 | | box | 29.01 | 39.74 | | column | 47.29 | 63.42 | | signboard | 37.12 | 51.05 | | chest of drawers | 39.14 | 55.0 | | counter | 47.18 | 54.99 | | sand | 66.15 | 80.49 | | sink | 71.76 | 77.7 | | skyscraper | 45.8 | 58.54 | | fireplace | 72.25 | 92.48 | | refrigerator | 74.61 | 82.65 | | grandstand | 45.59 | 75.3 | | path | 20.85 | 26.72 | | stairs | 33.51 | 40.24 | | runway | 69.79 | 88.25 | | case | 58.81 | 85.22 | | pool table | 91.77 | 96.84 | | pillow | 60.42 | 76.76 | | screen door | 58.59 | 81.33 | | stairway | 35.72 | 48.01 | | river | 23.76 | 42.87 | | bridge | 36.67 | 40.25 | | bookcase | 29.65 | 48.25 | | blind | 23.58 | 25.43 | | coffee table | 62.2 | 82.1 | | toilet | 86.58 | 93.23 | | flower | 38.4 | 61.24 | | book | 45.21 | 61.52 | | hill | 6.65 | 9.56 | | bench | 45.54 | 51.21 | | countertop | 56.72 | 76.57 | | stove | 72.98 | 90.69 | | palm | 49.68 | 73.27 | | kitchen island | 35.96 | 48.85 | | computer | 74.11 | 86.32 | | swivel chair | 44.14 | 69.22 | | boat | 54.18 | 85.12 | | bar | 58.65 | 65.99 | | arcade machine | 79.7 | 84.58 | | hovel | 14.52 | 15.65 | | bus | 89.32 | 94.65 | | towel | 62.9 | 83.44 | | light | 38.89 | 44.06 | | truck | 45.91 | 61.13 | | tower | 6.75 | 10.35 | | chandelier | 63.36 | 79.87 | | awning | 29.3 | 35.89 | | streetlight | 20.09 | 27.8 | | booth | 57.45 | 63.83 | | television receiver | 72.53 | 77.76 | | airplane | 57.44 | 67.7 | | dirt track | 8.89 | 9.81 | | apparel | 36.94 | 47.75 | | pole | 15.19 | 18.23 | | land | 0.22 | 0.24 | | bannister | 4.82 | 6.44 | | escalator | 26.29 | 28.43 | | ottoman | 50.76 | 73.39 | | bottle | 31.24 | 38.05 | | buffet | 37.96 | 43.74 | | poster | 12.87 | 15.24 | | stage | 17.97 | 24.25 | | van | 37.81 | 44.95 | | ship | 0.7 | 0.7 | | fountain | 9.91 | 10.68 | | conveyer belt | 84.42 | 92.88 | | canopy | 42.14 | 45.23 | | washer | 70.56 | 73.66 | | plaything | 36.23 | 59.97 | | swimming pool | 75.14 | 85.18 | | stool | 47.18 | 66.88 | | barrel | 31.84 | 32.37 | | basket | 38.92 | 51.8 | | waterfall | 45.82 | 57.55 | | tent | 94.86 | 97.45 | | bag | 19.0 | 21.17 | | minibike | 67.69 | 80.14 | | cradle | 70.15 | 98.02 | | oven | 24.72 | 25.35 | | ball | 47.46 | 70.19 | | food | 20.2 | 21.57 | | step | 0.79 | 0.92 | | tank | 29.83 | 34.64 | | trade name | 21.82 | 24.27 | | microwave | 81.43 | 91.77 | | pot | 51.89 | 58.92 | | animal | 73.97 | 78.69 | | bicycle | 59.23 | 78.45 | | lake | 0.0 | 0.0 | | dishwasher | 64.8 | 70.63 | | screen | 50.05 | 92.67 | | blanket | 3.1 | 3.42 | | sculpture | 51.76 | 59.48 | | hood | 57.82 | 65.87 | | sconce | 41.35 | 54.44 | | vase | 34.87 | 51.59 | | traffic light | 25.25 | 36.19 | | tray | 4.13 | 4.86 | | ashcan | 48.04 | 60.4 | | fan | 52.67 | 67.1 | | pier | 38.18 | 40.41 | | crt screen | 4.56 | 10.9 | | plate | 52.8 | 79.93 | | monitor | 4.7 | 5.66 | | bulletin board | 50.87 | 53.91 | | shower | 0.0 | 0.0 | | radiator | 53.72 | 65.14 | | glass | 17.87 | 20.46 | | clock | 27.6 | 30.01 | | flag | 62.83 | 67.11 | +---------------------+-------+-------+ 2023-11-10 03:28:07,261 - mmseg - INFO - Summary: 2023-11-10 03:28:07,261 - mmseg - INFO - +-------+-------+------+ | aAcc | mIoU | mAcc | +-------+-------+------+ | 82.48 | 47.65 | 58.9 | +-------+-------+------+ 2023-11-10 03:28:07,262 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 03:28:07,263 - mmseg - INFO - Iter(val) [250] aAcc: 0.8248, mIoU: 0.4765, mAcc: 0.5890, IoU.wall: 0.7655, IoU.building: 0.8129, IoU.sky: 0.9338, IoU.floor: 0.8186, IoU.tree: 0.7362, IoU.ceiling: 0.8311, IoU.road: 0.8192, IoU.bed : 0.8939, IoU.windowpane: 0.6144, IoU.grass: 0.6771, IoU.cabinet: 0.6294, IoU.sidewalk: 0.6177, IoU.person: 0.8002, IoU.earth: 0.3171, IoU.door: 0.4883, IoU.table: 0.6293, IoU.mountain: 0.5464, IoU.plant: 0.5088, IoU.curtain: 0.7082, IoU.chair: 0.5498, IoU.car: 0.8302, IoU.water: 0.4515, IoU.painting: 0.6794, IoU.sofa: 0.7125, IoU.shelf: 0.3827, IoU.house: 0.4563, IoU.sea: 0.4981, IoU.mirror: 0.7054, IoU.rug: 0.6572, IoU.field: 0.2842, IoU.armchair: 0.4537, IoU.seat: 0.6577, IoU.fence: 0.4472, IoU.desk: 0.4346, IoU.rock: 0.4170, IoU.wardrobe: 0.5296, IoU.lamp: 0.6102, IoU.bathtub: 0.8275, IoU.railing: 0.3848, IoU.cushion: 0.5803, IoU.base: 0.1542, IoU.box: 0.2901, IoU.column: 0.4729, IoU.signboard: 0.3712, IoU.chest of drawers: 0.3914, IoU.counter: 0.4718, IoU.sand: 0.6615, IoU.sink: 0.7176, IoU.skyscraper: 0.4580, IoU.fireplace: 0.7225, IoU.refrigerator: 0.7461, IoU.grandstand: 0.4559, IoU.path: 0.2085, IoU.stairs: 0.3351, IoU.runway: 0.6979, IoU.case: 0.5881, IoU.pool table: 0.9177, IoU.pillow: 0.6042, IoU.screen door: 0.5859, IoU.stairway: 0.3572, IoU.river: 0.2376, IoU.bridge: 0.3667, IoU.bookcase: 0.2965, IoU.blind: 0.2358, IoU.coffee table: 0.6220, IoU.toilet: 0.8658, IoU.flower: 0.3840, IoU.book: 0.4521, IoU.hill: 0.0665, IoU.bench: 0.4554, IoU.countertop: 0.5672, IoU.stove: 0.7298, IoU.palm: 0.4968, IoU.kitchen island: 0.3596, IoU.computer: 0.7411, IoU.swivel chair: 0.4414, IoU.boat: 0.5418, IoU.bar: 0.5865, IoU.arcade machine: 0.7970, IoU.hovel: 0.1452, IoU.bus: 0.8932, IoU.towel: 0.6290, IoU.light: 0.3889, IoU.truck: 0.4591, IoU.tower: 0.0675, IoU.chandelier: 0.6336, IoU.awning: 0.2930, IoU.streetlight: 0.2009, IoU.booth: 0.5745, IoU.television receiver: 0.7253, IoU.airplane: 0.5744, IoU.dirt track: 0.0889, IoU.apparel: 0.3694, IoU.pole: 0.1519, IoU.land: 0.0022, IoU.bannister: 0.0482, IoU.escalator: 0.2629, IoU.ottoman: 0.5076, IoU.bottle: 0.3124, IoU.buffet: 0.3796, IoU.poster: 0.1287, IoU.stage: 0.1797, IoU.van: 0.3781, IoU.ship: 0.0070, IoU.fountain: 0.0991, IoU.conveyer belt: 0.8442, IoU.canopy: 0.4214, IoU.washer: 0.7056, IoU.plaything: 0.3623, IoU.swimming pool: 0.7514, IoU.stool: 0.4718, IoU.barrel: 0.3184, IoU.basket: 0.3892, IoU.waterfall: 0.4582, IoU.tent: 0.9486, IoU.bag: 0.1900, IoU.minibike: 0.6769, IoU.cradle: 0.7015, IoU.oven: 0.2472, IoU.ball: 0.4746, IoU.food: 0.2020, IoU.step: 0.0079, IoU.tank: 0.2983, IoU.trade name: 0.2182, IoU.microwave: 0.8143, IoU.pot: 0.5189, IoU.animal: 0.7397, IoU.bicycle: 0.5923, IoU.lake: 0.0000, IoU.dishwasher: 0.6480, IoU.screen: 0.5005, IoU.blanket: 0.0310, IoU.sculpture: 0.5176, IoU.hood: 0.5782, IoU.sconce: 0.4135, IoU.vase: 0.3487, IoU.traffic light: 0.2525, IoU.tray: 0.0413, IoU.ashcan: 0.4804, IoU.fan: 0.5267, IoU.pier: 0.3818, IoU.crt screen: 0.0456, IoU.plate: 0.5280, IoU.monitor: 0.0470, IoU.bulletin board: 0.5087, IoU.shower: 0.0000, IoU.radiator: 0.5372, IoU.glass: 0.1787, IoU.clock: 0.2760, IoU.flag: 0.6283, Acc.wall: 0.8777, Acc.building: 0.9105, Acc.sky: 0.9640, Acc.floor: 0.9146, Acc.tree: 0.8927, Acc.ceiling: 0.9375, Acc.road: 0.8515, Acc.bed : 0.9558, Acc.windowpane: 0.8236, Acc.grass: 0.8258, Acc.cabinet: 0.7284, Acc.sidewalk: 0.9059, Acc.person: 0.9149, Acc.earth: 0.4110, Acc.door: 0.5607, Acc.table: 0.7536, Acc.mountain: 0.7297, Acc.plant: 0.6263, Acc.curtain: 0.8556, Acc.chair: 0.6583, Acc.car: 0.9221, Acc.water: 0.5956, Acc.painting: 0.8781, Acc.sofa: 0.8866, Acc.shelf: 0.5880, Acc.house: 0.7596, Acc.sea: 0.8381, Acc.mirror: 0.7857, Acc.rug: 0.7073, Acc.field: 0.5732, Acc.armchair: 0.6575, Acc.seat: 0.8147, Acc.fence: 0.5620, Acc.desk: 0.5816, Acc.rock: 0.5114, Acc.wardrobe: 0.7385, Acc.lamp: 0.7210, Acc.bathtub: 0.9032, Acc.railing: 0.5060, Acc.cushion: 0.7131, Acc.base: 0.1894, Acc.box: 0.3974, Acc.column: 0.6342, Acc.signboard: 0.5105, Acc.chest of drawers: 0.5500, Acc.counter: 0.5499, Acc.sand: 0.8049, Acc.sink: 0.7770, Acc.skyscraper: 0.5854, Acc.fireplace: 0.9248, Acc.refrigerator: 0.8265, Acc.grandstand: 0.7530, Acc.path: 0.2672, Acc.stairs: 0.4024, Acc.runway: 0.8825, Acc.case: 0.8522, Acc.pool table: 0.9684, Acc.pillow: 0.7676, Acc.screen door: 0.8133, Acc.stairway: 0.4801, Acc.river: 0.4287, Acc.bridge: 0.4025, Acc.bookcase: 0.4825, Acc.blind: 0.2543, Acc.coffee table: 0.8210, Acc.toilet: 0.9323, Acc.flower: 0.6124, Acc.book: 0.6152, Acc.hill: 0.0956, Acc.bench: 0.5121, Acc.countertop: 0.7657, Acc.stove: 0.9069, Acc.palm: 0.7327, Acc.kitchen island: 0.4885, Acc.computer: 0.8632, Acc.swivel chair: 0.6922, Acc.boat: 0.8512, Acc.bar: 0.6599, Acc.arcade machine: 0.8458, Acc.hovel: 0.1565, Acc.bus: 0.9465, Acc.towel: 0.8344, Acc.light: 0.4406, Acc.truck: 0.6113, Acc.tower: 0.1035, Acc.chandelier: 0.7987, Acc.awning: 0.3589, Acc.streetlight: 0.2780, Acc.booth: 0.6383, Acc.television receiver: 0.7776, Acc.airplane: 0.6770, Acc.dirt track: 0.0981, Acc.apparel: 0.4775, Acc.pole: 0.1823, Acc.land: 0.0024, Acc.bannister: 0.0644, Acc.escalator: 0.2843, Acc.ottoman: 0.7339, Acc.bottle: 0.3805, Acc.buffet: 0.4374, Acc.poster: 0.1524, Acc.stage: 0.2425, Acc.van: 0.4495, Acc.ship: 0.0070, Acc.fountain: 0.1068, Acc.conveyer belt: 0.9288, Acc.canopy: 0.4523, Acc.washer: 0.7366, Acc.plaything: 0.5997, Acc.swimming pool: 0.8518, Acc.stool: 0.6688, Acc.barrel: 0.3237, Acc.basket: 0.5180, Acc.waterfall: 0.5755, Acc.tent: 0.9745, Acc.bag: 0.2117, Acc.minibike: 0.8014, Acc.cradle: 0.9802, Acc.oven: 0.2535, Acc.ball: 0.7019, Acc.food: 0.2157, Acc.step: 0.0092, Acc.tank: 0.3464, Acc.trade name: 0.2427, Acc.microwave: 0.9177, Acc.pot: 0.5892, Acc.animal: 0.7869, Acc.bicycle: 0.7845, Acc.lake: 0.0000, Acc.dishwasher: 0.7063, Acc.screen: 0.9267, Acc.blanket: 0.0342, Acc.sculpture: 0.5948, Acc.hood: 0.6587, Acc.sconce: 0.5444, Acc.vase: 0.5159, Acc.traffic light: 0.3619, Acc.tray: 0.0486, Acc.ashcan: 0.6040, Acc.fan: 0.6710, Acc.pier: 0.4041, Acc.crt screen: 0.1090, Acc.plate: 0.7993, Acc.monitor: 0.0566, Acc.bulletin board: 0.5391, Acc.shower: 0.0000, Acc.radiator: 0.6514, Acc.glass: 0.2046, Acc.clock: 0.3001, Acc.flag: 0.6711 2023-11-10 03:29:08,227 - mmseg - INFO - Iter [2050/10000] lr: 2.576e-06, eta: 3:00:24, time: 2.300, data_time: 1.089, memory: 38534, decode.loss_ce: 0.3341, decode.acc_seg: 87.6876, loss: 0.3341 2023-11-10 03:30:11,439 - mmseg - INFO - Iter [2100/10000] lr: 2.560e-06, eta: 2:58:58, time: 1.264, data_time: 0.051, memory: 38534, decode.loss_ce: 0.3068, decode.acc_seg: 88.6496, loss: 0.3068 2023-11-10 03:31:12,387 - mmseg - INFO - Iter [2150/10000] lr: 2.544e-06, eta: 2:57:24, time: 1.219, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3278, decode.acc_seg: 88.2126, loss: 0.3278 2023-11-10 03:32:13,298 - mmseg - INFO - Iter [2200/10000] lr: 2.527e-06, eta: 2:55:52, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3241, decode.acc_seg: 87.8559, loss: 0.3241 2023-11-10 03:33:16,552 - mmseg - INFO - Iter [2250/10000] lr: 2.511e-06, eta: 2:54:29, time: 1.265, data_time: 0.051, memory: 38534, decode.loss_ce: 0.3263, decode.acc_seg: 88.1024, loss: 0.3263 2023-11-10 03:34:17,470 - mmseg - INFO - Iter [2300/10000] lr: 2.495e-06, eta: 2:53:00, time: 1.218, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3074, decode.acc_seg: 88.6881, loss: 0.3074 2023-11-10 03:35:18,387 - mmseg - INFO - Iter [2350/10000] lr: 2.479e-06, eta: 2:51:31, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3155, decode.acc_seg: 88.1570, loss: 0.3155 2023-11-10 03:36:21,551 - mmseg - INFO - Iter [2400/10000] lr: 2.463e-06, eta: 2:50:11, time: 1.263, data_time: 0.049, memory: 38534, decode.loss_ce: 0.2977, decode.acc_seg: 88.7629, loss: 0.2977 2023-11-10 03:37:22,495 - mmseg - INFO - Iter [2450/10000] lr: 2.446e-06, eta: 2:48:45, time: 1.219, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3038, decode.acc_seg: 88.8188, loss: 0.3038 2023-11-10 03:38:23,392 - mmseg - INFO - Iter [2500/10000] lr: 2.430e-06, eta: 2:47:19, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.3137, decode.acc_seg: 88.2031, loss: 0.3137 2023-11-10 03:39:26,558 - mmseg - INFO - Iter [2550/10000] lr: 2.414e-06, eta: 2:46:01, time: 1.263, data_time: 0.051, memory: 38534, decode.loss_ce: 0.3030, decode.acc_seg: 88.8433, loss: 0.3030 2023-11-10 03:40:27,470 - mmseg - INFO - Iter [2600/10000] lr: 2.398e-06, eta: 2:44:37, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2967, decode.acc_seg: 89.0226, loss: 0.2967 2023-11-10 03:41:28,363 - mmseg - INFO - Iter [2650/10000] lr: 2.382e-06, eta: 2:43:14, time: 1.218, data_time: 0.007, memory: 38534, decode.loss_ce: 0.3039, decode.acc_seg: 88.9392, loss: 0.3039 2023-11-10 03:42:31,507 - mmseg - INFO - Iter [2700/10000] lr: 2.365e-06, eta: 2:41:58, time: 1.263, data_time: 0.051, memory: 38534, decode.loss_ce: 0.3118, decode.acc_seg: 89.0994, loss: 0.3118 2023-11-10 03:43:32,389 - mmseg - INFO - Iter [2750/10000] lr: 2.349e-06, eta: 2:40:37, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2799, decode.acc_seg: 89.3860, loss: 0.2799 2023-11-10 03:44:33,255 - mmseg - INFO - Iter [2800/10000] lr: 2.333e-06, eta: 2:39:16, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2907, decode.acc_seg: 89.1338, loss: 0.2907 2023-11-10 03:45:36,421 - mmseg - INFO - Iter [2850/10000] lr: 2.317e-06, eta: 2:38:01, time: 1.263, data_time: 0.050, memory: 38534, decode.loss_ce: 0.2794, decode.acc_seg: 89.4497, loss: 0.2794 2023-11-10 03:46:37,307 - mmseg - INFO - Iter [2900/10000] lr: 2.301e-06, eta: 2:36:42, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2773, decode.acc_seg: 89.5194, loss: 0.2773 2023-11-10 03:47:38,198 - mmseg - INFO - Iter [2950/10000] lr: 2.284e-06, eta: 2:35:23, time: 1.218, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2693, decode.acc_seg: 89.9780, loss: 0.2693 2023-11-10 03:48:39,062 - mmseg - INFO - Saving checkpoint at 3000 iterations 2023-11-10 03:49:33,339 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 03:49:33,339 - mmseg - INFO - Iter [3000/10000] lr: 2.268e-06, eta: 2:36:11, time: 2.303, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2651, decode.acc_seg: 89.8902, loss: 0.2651 2023-11-10 03:50:27,517 - mmseg - INFO - per class results: 2023-11-10 03:50:27,522 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 78.14 | 85.99 | | building | 82.04 | 92.25 | | sky | 93.64 | 96.83 | | floor | 81.79 | 91.68 | | tree | 74.48 | 84.82 | | ceiling | 83.71 | 93.7 | | road | 83.76 | 92.37 | | bed | 89.28 | 96.36 | | windowpane | 61.22 | 75.5 | | grass | 66.91 | 82.83 | | cabinet | 63.59 | 73.5 | | sidewalk | 63.97 | 75.31 | | person | 79.8 | 93.14 | | earth | 36.87 | 51.8 | | door | 54.86 | 72.7 | | table | 63.82 | 80.61 | | mountain | 57.62 | 76.97 | | plant | 53.01 | 63.41 | | curtain | 71.8 | 84.94 | | chair | 55.85 | 70.99 | | car | 83.3 | 93.19 | | water | 29.98 | 35.54 | | painting | 72.03 | 85.19 | | sofa | 74.2 | 85.2 | | shelf | 41.91 | 64.89 | | house | 48.78 | 76.02 | | sea | 56.79 | 86.19 | | mirror | 71.25 | 82.58 | | rug | 68.23 | 76.88 | | field | 21.21 | 43.45 | | armchair | 51.61 | 73.35 | | seat | 61.51 | 73.31 | | fence | 44.39 | 61.28 | | desk | 47.53 | 65.87 | | rock | 46.67 | 60.65 | | wardrobe | 52.07 | 70.15 | | lamp | 63.73 | 75.97 | | bathtub | 83.71 | 88.77 | | railing | 39.51 | 49.59 | | cushion | 60.73 | 70.98 | | base | 20.94 | 30.94 | | box | 30.08 | 41.36 | | column | 49.79 | 65.47 | | signboard | 36.36 | 58.85 | | chest of drawers | 41.65 | 59.92 | | counter | 50.18 | 68.67 | | sand | 64.47 | 78.67 | | sink | 72.92 | 79.59 | | skyscraper | 45.68 | 61.75 | | fireplace | 71.37 | 91.29 | | refrigerator | 75.96 | 89.15 | | grandstand | 47.09 | 82.14 | | path | 20.89 | 32.38 | | stairs | 26.21 | 33.69 | | runway | 72.78 | 94.53 | | case | 44.09 | 77.31 | | pool table | 92.12 | 97.62 | | pillow | 54.93 | 64.77 | | screen door | 60.35 | 85.56 | | stairway | 36.95 | 52.59 | | river | 18.96 | 79.06 | | bridge | 37.2 | 41.87 | | bookcase | 34.98 | 56.49 | | blind | 36.04 | 45.51 | | coffee table | 63.6 | 83.56 | | toilet | 87.14 | 92.22 | | flower | 37.21 | 60.67 | | book | 43.92 | 57.92 | | hill | 7.6 | 12.71 | | bench | 43.44 | 48.2 | | countertop | 57.85 | 72.41 | | stove | 78.42 | 90.65 | | palm | 49.16 | 78.1 | | kitchen island | 36.04 | 49.84 | | computer | 75.7 | 88.06 | | swivel chair | 45.69 | 66.03 | | boat | 54.08 | 87.4 | | bar | 68.61 | 78.4 | | arcade machine | 78.41 | 84.75 | | hovel | 25.98 | 28.72 | | bus | 88.72 | 94.77 | | towel | 66.24 | 84.95 | | light | 39.68 | 44.4 | | truck | 47.03 | 60.44 | | tower | 13.6 | 25.88 | | chandelier | 64.67 | 79.89 | | awning | 25.56 | 29.52 | | streetlight | 23.78 | 31.47 | | booth | 45.7 | 86.34 | | television receiver | 74.77 | 86.19 | | airplane | 64.63 | 74.8 | | dirt track | 6.29 | 6.95 | | apparel | 41.27 | 60.68 | | pole | 15.28 | 18.49 | | land | 5.74 | 6.68 | | bannister | 8.94 | 13.97 | | escalator | 47.55 | 58.3 | | ottoman | 50.94 | 66.07 | | bottle | 27.62 | 36.5 | | buffet | 42.62 | 56.73 | | poster | 30.86 | 41.04 | | stage | 21.2 | 28.9 | | van | 31.19 | 36.25 | | ship | 0.0 | 0.0 | | fountain | 3.85 | 3.91 | | conveyer belt | 74.95 | 97.68 | | canopy | 41.86 | 48.76 | | washer | 70.79 | 72.79 | | plaything | 36.18 | 53.99 | | swimming pool | 67.85 | 75.67 | | stool | 46.25 | 64.62 | | barrel | 21.97 | 22.03 | | basket | 37.36 | 52.12 | | waterfall | 60.94 | 77.94 | | tent | 93.82 | 97.78 | | bag | 19.87 | 23.12 | | minibike | 65.38 | 78.54 | | cradle | 73.8 | 97.87 | | oven | 43.38 | 50.43 | | ball | 41.41 | 71.88 | | food | 19.56 | 21.56 | | step | 5.4 | 6.45 | | tank | 27.65 | 33.31 | | trade name | 14.7 | 15.92 | | microwave | 80.65 | 93.78 | | pot | 49.74 | 55.49 | | animal | 72.04 | 74.62 | | bicycle | 58.85 | 77.32 | | lake | 0.0 | 0.0 | | dishwasher | 66.66 | 69.01 | | screen | 51.57 | 93.29 | | blanket | 7.54 | 8.28 | | sculpture | 59.8 | 70.47 | | hood | 58.42 | 73.96 | | sconce | 45.4 | 58.6 | | vase | 37.75 | 55.22 | | traffic light | 26.79 | 54.53 | | tray | 4.29 | 5.38 | | ashcan | 48.95 | 64.81 | | fan | 53.19 | 65.25 | | pier | 37.35 | 40.25 | | crt screen | 4.74 | 13.89 | | plate | 55.53 | 67.12 | | monitor | 2.7 | 2.92 | | bulletin board | 58.48 | 74.4 | | shower | 2.72 | 3.1 | | radiator | 53.31 | 69.94 | | glass | 14.52 | 15.29 | | clock | 37.25 | 40.58 | | flag | 64.49 | 70.41 | +---------------------+-------+-------+ 2023-11-10 03:50:27,523 - mmseg - INFO - Summary: 2023-11-10 03:50:27,523 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 82.91 | 48.76 | 61.45 | +-------+-------+-------+ 2023-11-10 03:50:27,523 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 03:50:27,524 - mmseg - INFO - Iter(val) [250] aAcc: 0.8291, mIoU: 0.4876, mAcc: 0.6145, IoU.wall: 0.7814, IoU.building: 0.8204, IoU.sky: 0.9364, IoU.floor: 0.8179, IoU.tree: 0.7448, IoU.ceiling: 0.8371, IoU.road: 0.8376, IoU.bed : 0.8928, IoU.windowpane: 0.6122, IoU.grass: 0.6691, IoU.cabinet: 0.6359, IoU.sidewalk: 0.6397, IoU.person: 0.7980, IoU.earth: 0.3687, IoU.door: 0.5486, IoU.table: 0.6382, IoU.mountain: 0.5762, IoU.plant: 0.5301, IoU.curtain: 0.7180, IoU.chair: 0.5585, IoU.car: 0.8330, IoU.water: 0.2998, IoU.painting: 0.7203, IoU.sofa: 0.7420, IoU.shelf: 0.4191, IoU.house: 0.4878, IoU.sea: 0.5679, IoU.mirror: 0.7125, IoU.rug: 0.6823, IoU.field: 0.2121, IoU.armchair: 0.5161, IoU.seat: 0.6151, IoU.fence: 0.4439, IoU.desk: 0.4753, IoU.rock: 0.4667, IoU.wardrobe: 0.5207, IoU.lamp: 0.6373, IoU.bathtub: 0.8371, IoU.railing: 0.3951, IoU.cushion: 0.6073, IoU.base: 0.2094, IoU.box: 0.3008, IoU.column: 0.4979, IoU.signboard: 0.3636, IoU.chest of drawers: 0.4165, IoU.counter: 0.5018, IoU.sand: 0.6447, IoU.sink: 0.7292, IoU.skyscraper: 0.4568, IoU.fireplace: 0.7137, IoU.refrigerator: 0.7596, IoU.grandstand: 0.4709, IoU.path: 0.2089, IoU.stairs: 0.2621, IoU.runway: 0.7278, IoU.case: 0.4409, IoU.pool table: 0.9212, IoU.pillow: 0.5493, IoU.screen door: 0.6035, IoU.stairway: 0.3695, IoU.river: 0.1896, IoU.bridge: 0.3720, IoU.bookcase: 0.3498, IoU.blind: 0.3604, IoU.coffee table: 0.6360, IoU.toilet: 0.8714, IoU.flower: 0.3721, IoU.book: 0.4392, IoU.hill: 0.0760, IoU.bench: 0.4344, IoU.countertop: 0.5785, IoU.stove: 0.7842, IoU.palm: 0.4916, IoU.kitchen island: 0.3604, IoU.computer: 0.7570, IoU.swivel chair: 0.4569, IoU.boat: 0.5408, IoU.bar: 0.6861, IoU.arcade machine: 0.7841, IoU.hovel: 0.2598, IoU.bus: 0.8872, IoU.towel: 0.6624, IoU.light: 0.3968, IoU.truck: 0.4703, IoU.tower: 0.1360, IoU.chandelier: 0.6467, IoU.awning: 0.2556, IoU.streetlight: 0.2378, IoU.booth: 0.4570, IoU.television receiver: 0.7477, IoU.airplane: 0.6463, IoU.dirt track: 0.0629, IoU.apparel: 0.4127, IoU.pole: 0.1528, IoU.land: 0.0574, IoU.bannister: 0.0894, IoU.escalator: 0.4755, IoU.ottoman: 0.5094, IoU.bottle: 0.2762, IoU.buffet: 0.4262, IoU.poster: 0.3086, IoU.stage: 0.2120, IoU.van: 0.3119, IoU.ship: 0.0000, IoU.fountain: 0.0385, IoU.conveyer belt: 0.7495, IoU.canopy: 0.4186, IoU.washer: 0.7079, IoU.plaything: 0.3618, IoU.swimming pool: 0.6785, IoU.stool: 0.4625, IoU.barrel: 0.2197, IoU.basket: 0.3736, IoU.waterfall: 0.6094, IoU.tent: 0.9382, IoU.bag: 0.1987, IoU.minibike: 0.6538, IoU.cradle: 0.7380, IoU.oven: 0.4338, IoU.ball: 0.4141, IoU.food: 0.1956, IoU.step: 0.0540, IoU.tank: 0.2765, IoU.trade name: 0.1470, IoU.microwave: 0.8065, IoU.pot: 0.4974, IoU.animal: 0.7204, IoU.bicycle: 0.5885, IoU.lake: 0.0000, IoU.dishwasher: 0.6666, IoU.screen: 0.5157, IoU.blanket: 0.0754, IoU.sculpture: 0.5980, IoU.hood: 0.5842, IoU.sconce: 0.4540, IoU.vase: 0.3775, IoU.traffic light: 0.2679, IoU.tray: 0.0429, IoU.ashcan: 0.4895, IoU.fan: 0.5319, IoU.pier: 0.3735, IoU.crt screen: 0.0474, IoU.plate: 0.5553, IoU.monitor: 0.0270, IoU.bulletin board: 0.5848, IoU.shower: 0.0272, IoU.radiator: 0.5331, IoU.glass: 0.1452, IoU.clock: 0.3725, IoU.flag: 0.6449, Acc.wall: 0.8599, Acc.building: 0.9225, Acc.sky: 0.9683, Acc.floor: 0.9168, Acc.tree: 0.8482, Acc.ceiling: 0.9370, Acc.road: 0.9237, Acc.bed : 0.9636, Acc.windowpane: 0.7550, Acc.grass: 0.8283, Acc.cabinet: 0.7350, Acc.sidewalk: 0.7531, Acc.person: 0.9314, Acc.earth: 0.5180, Acc.door: 0.7270, Acc.table: 0.8061, Acc.mountain: 0.7697, Acc.plant: 0.6341, Acc.curtain: 0.8494, Acc.chair: 0.7099, Acc.car: 0.9319, Acc.water: 0.3554, Acc.painting: 0.8519, Acc.sofa: 0.8520, Acc.shelf: 0.6489, Acc.house: 0.7602, Acc.sea: 0.8619, Acc.mirror: 0.8258, Acc.rug: 0.7688, Acc.field: 0.4345, Acc.armchair: 0.7335, Acc.seat: 0.7331, Acc.fence: 0.6128, Acc.desk: 0.6587, Acc.rock: 0.6065, Acc.wardrobe: 0.7015, Acc.lamp: 0.7597, Acc.bathtub: 0.8877, Acc.railing: 0.4959, Acc.cushion: 0.7098, Acc.base: 0.3094, Acc.box: 0.4136, Acc.column: 0.6547, Acc.signboard: 0.5885, Acc.chest of drawers: 0.5992, Acc.counter: 0.6867, Acc.sand: 0.7867, Acc.sink: 0.7959, Acc.skyscraper: 0.6175, Acc.fireplace: 0.9129, Acc.refrigerator: 0.8915, Acc.grandstand: 0.8214, Acc.path: 0.3238, Acc.stairs: 0.3369, Acc.runway: 0.9453, Acc.case: 0.7731, Acc.pool table: 0.9762, Acc.pillow: 0.6477, Acc.screen door: 0.8556, Acc.stairway: 0.5259, Acc.river: 0.7906, Acc.bridge: 0.4187, Acc.bookcase: 0.5649, Acc.blind: 0.4551, Acc.coffee table: 0.8356, Acc.toilet: 0.9222, Acc.flower: 0.6067, Acc.book: 0.5792, Acc.hill: 0.1271, Acc.bench: 0.4820, Acc.countertop: 0.7241, Acc.stove: 0.9065, Acc.palm: 0.7810, Acc.kitchen island: 0.4984, Acc.computer: 0.8806, Acc.swivel chair: 0.6603, Acc.boat: 0.8740, Acc.bar: 0.7840, Acc.arcade machine: 0.8475, Acc.hovel: 0.2872, Acc.bus: 0.9477, Acc.towel: 0.8495, Acc.light: 0.4440, Acc.truck: 0.6044, Acc.tower: 0.2588, Acc.chandelier: 0.7989, Acc.awning: 0.2952, Acc.streetlight: 0.3147, Acc.booth: 0.8634, Acc.television receiver: 0.8619, Acc.airplane: 0.7480, Acc.dirt track: 0.0695, Acc.apparel: 0.6068, Acc.pole: 0.1849, Acc.land: 0.0668, Acc.bannister: 0.1397, Acc.escalator: 0.5830, Acc.ottoman: 0.6607, Acc.bottle: 0.3650, Acc.buffet: 0.5673, Acc.poster: 0.4104, Acc.stage: 0.2890, Acc.van: 0.3625, Acc.ship: 0.0000, Acc.fountain: 0.0391, Acc.conveyer belt: 0.9768, Acc.canopy: 0.4876, Acc.washer: 0.7279, Acc.plaything: 0.5399, Acc.swimming pool: 0.7567, Acc.stool: 0.6462, Acc.barrel: 0.2203, Acc.basket: 0.5212, Acc.waterfall: 0.7794, Acc.tent: 0.9778, Acc.bag: 0.2312, Acc.minibike: 0.7854, Acc.cradle: 0.9787, Acc.oven: 0.5043, Acc.ball: 0.7188, Acc.food: 0.2156, Acc.step: 0.0645, Acc.tank: 0.3331, Acc.trade name: 0.1592, Acc.microwave: 0.9378, Acc.pot: 0.5549, Acc.animal: 0.7462, Acc.bicycle: 0.7732, Acc.lake: 0.0000, Acc.dishwasher: 0.6901, Acc.screen: 0.9329, Acc.blanket: 0.0828, Acc.sculpture: 0.7047, Acc.hood: 0.7396, Acc.sconce: 0.5860, Acc.vase: 0.5522, Acc.traffic light: 0.5453, Acc.tray: 0.0538, Acc.ashcan: 0.6481, Acc.fan: 0.6525, Acc.pier: 0.4025, Acc.crt screen: 0.1389, Acc.plate: 0.6712, Acc.monitor: 0.0292, Acc.bulletin board: 0.7440, Acc.shower: 0.0310, Acc.radiator: 0.6994, Acc.glass: 0.1529, Acc.clock: 0.4058, Acc.flag: 0.7041 2023-11-10 03:51:30,673 - mmseg - INFO - Iter [3050/10000] lr: 2.252e-06, eta: 2:36:59, time: 2.347, data_time: 1.135, memory: 38534, decode.loss_ce: 0.2643, decode.acc_seg: 89.9309, loss: 0.2643 2023-11-10 03:52:31,528 - mmseg - INFO - Iter [3100/10000] lr: 2.236e-06, eta: 2:35:36, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2820, decode.acc_seg: 89.4675, loss: 0.2820 2023-11-10 03:53:32,335 - mmseg - INFO - Iter [3150/10000] lr: 2.220e-06, eta: 2:34:13, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2623, decode.acc_seg: 89.7210, loss: 0.2623 2023-11-10 03:54:35,523 - mmseg - INFO - Iter [3200/10000] lr: 2.203e-06, eta: 2:32:57, time: 1.264, data_time: 0.052, memory: 38534, decode.loss_ce: 0.2744, decode.acc_seg: 89.7895, loss: 0.2744 2023-11-10 03:55:36,334 - mmseg - INFO - Iter [3250/10000] lr: 2.187e-06, eta: 2:31:35, time: 1.216, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2776, decode.acc_seg: 89.4964, loss: 0.2776 2023-11-10 03:56:37,167 - mmseg - INFO - Iter [3300/10000] lr: 2.171e-06, eta: 2:30:15, time: 1.217, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2579, decode.acc_seg: 90.3594, loss: 0.2579 2023-11-10 03:57:40,201 - mmseg - INFO - Iter [3350/10000] lr: 2.155e-06, eta: 2:28:59, time: 1.261, data_time: 0.051, memory: 38534, decode.loss_ce: 0.2549, decode.acc_seg: 90.2914, loss: 0.2549 2023-11-10 03:58:40,990 - mmseg - INFO - Iter [3400/10000] lr: 2.139e-06, eta: 2:27:39, time: 1.216, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2607, decode.acc_seg: 90.1341, loss: 0.2607 2023-11-10 03:59:41,816 - mmseg - INFO - Iter [3450/10000] lr: 2.122e-06, eta: 2:26:20, time: 1.217, data_time: 0.007, memory: 38534, decode.loss_ce: 0.2629, decode.acc_seg: 90.1103, loss: 0.2629 2023-11-10 04:00:44,964 - mmseg - INFO - Iter [3500/10000] lr: 2.106e-06, eta: 2:25:06, time: 1.263, data_time: 0.052, memory: 38534, decode.loss_ce: 0.2566, decode.acc_seg: 89.9631, loss: 0.2566 2023-11-10 04:01:45,838 - mmseg - INFO - Iter [3550/10000] lr: 2.090e-06, eta: 2:23:48, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2773, decode.acc_seg: 89.6446, loss: 0.2773 2023-11-10 04:02:46,730 - mmseg - INFO - Iter [3600/10000] lr: 2.074e-06, eta: 2:22:30, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2466, decode.acc_seg: 90.6993, loss: 0.2466 2023-11-10 04:03:49,875 - mmseg - INFO - Iter [3650/10000] lr: 2.058e-06, eta: 2:21:17, time: 1.263, data_time: 0.051, memory: 38534, decode.loss_ce: 0.2502, decode.acc_seg: 90.6427, loss: 0.2502 2023-11-10 04:04:50,744 - mmseg - INFO - Iter [3700/10000] lr: 2.041e-06, eta: 2:20:00, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2543, decode.acc_seg: 90.2860, loss: 0.2543 2023-11-10 04:05:51,579 - mmseg - INFO - Iter [3750/10000] lr: 2.025e-06, eta: 2:18:44, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2281, decode.acc_seg: 91.2784, loss: 0.2281 2023-11-10 04:06:54,743 - mmseg - INFO - Iter [3800/10000] lr: 2.009e-06, eta: 2:17:32, time: 1.263, data_time: 0.050, memory: 38534, decode.loss_ce: 0.2558, decode.acc_seg: 90.3270, loss: 0.2558 2023-11-10 04:07:55,600 - mmseg - INFO - Iter [3850/10000] lr: 1.993e-06, eta: 2:16:16, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2499, decode.acc_seg: 90.7045, loss: 0.2499 2023-11-10 04:08:56,445 - mmseg - INFO - Iter [3900/10000] lr: 1.977e-06, eta: 2:15:01, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2295, decode.acc_seg: 91.1044, loss: 0.2295 2023-11-10 04:09:57,279 - mmseg - INFO - Iter [3950/10000] lr: 1.960e-06, eta: 2:13:46, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2321, decode.acc_seg: 90.9839, loss: 0.2321 2023-11-10 04:11:00,476 - mmseg - INFO - Saving checkpoint at 4000 iterations 2023-11-10 04:11:53,360 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 04:11:53,360 - mmseg - INFO - Iter [4000/10000] lr: 1.944e-06, eta: 2:13:54, time: 2.322, data_time: 0.052, memory: 38534, decode.loss_ce: 0.2300, decode.acc_seg: 90.9411, loss: 0.2300 2023-11-10 04:12:47,309 - mmseg - INFO - per class results: 2023-11-10 04:12:47,315 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 78.36 | 87.11 | | building | 81.52 | 93.03 | | sky | 93.71 | 97.44 | | floor | 82.23 | 91.56 | | tree | 74.16 | 86.65 | | ceiling | 84.07 | 91.86 | | road | 83.37 | 90.57 | | bed | 90.16 | 95.98 | | windowpane | 62.82 | 79.09 | | grass | 67.1 | 82.6 | | cabinet | 63.12 | 72.41 | | sidewalk | 65.92 | 81.44 | | person | 80.54 | 92.15 | | earth | 32.14 | 45.11 | | door | 54.8 | 69.95 | | table | 63.09 | 80.62 | | mountain | 56.69 | 73.04 | | plant | 50.26 | 62.73 | | curtain | 75.18 | 82.43 | | chair | 56.72 | 67.74 | | car | 82.91 | 94.49 | | water | 48.69 | 65.43 | | painting | 70.35 | 89.92 | | sofa | 75.81 | 87.3 | | shelf | 43.34 | 67.62 | | house | 38.53 | 50.34 | | sea | 50.1 | 77.56 | | mirror | 72.39 | 83.99 | | rug | 67.32 | 75.43 | | field | 18.82 | 33.82 | | armchair | 55.62 | 74.04 | | seat | 61.2 | 77.22 | | fence | 46.91 | 63.28 | | desk | 46.64 | 65.94 | | rock | 45.84 | 60.03 | | wardrobe | 55.25 | 75.84 | | lamp | 63.86 | 80.68 | | bathtub | 82.97 | 92.52 | | railing | 39.79 | 56.94 | | cushion | 60.84 | 73.74 | | base | 19.29 | 34.7 | | box | 29.5 | 37.26 | | column | 48.01 | 62.14 | | signboard | 36.11 | 52.38 | | chest of drawers | 43.35 | 61.54 | | counter | 40.23 | 50.14 | | sand | 61.75 | 79.56 | | sink | 75.27 | 83.65 | | skyscraper | 44.37 | 53.76 | | fireplace | 70.76 | 89.87 | | refrigerator | 77.0 | 87.81 | | grandstand | 44.07 | 83.05 | | path | 17.78 | 23.87 | | stairs | 27.67 | 35.24 | | runway | 67.27 | 85.81 | | case | 44.69 | 70.64 | | pool table | 89.67 | 97.63 | | pillow | 60.41 | 72.61 | | screen door | 53.32 | 66.39 | | stairway | 39.97 | 56.93 | | river | 23.7 | 34.81 | | bridge | 39.56 | 44.0 | | bookcase | 31.02 | 42.53 | | blind | 38.21 | 41.87 | | coffee table | 61.05 | 86.53 | | toilet | 87.78 | 92.94 | | flower | 38.65 | 67.69 | | book | 46.8 | 75.12 | | hill | 4.25 | 6.32 | | bench | 50.22 | 58.24 | | countertop | 57.32 | 75.97 | | stove | 79.83 | 88.64 | | palm | 47.04 | 61.58 | | kitchen island | 43.32 | 70.62 | | computer | 76.58 | 87.85 | | swivel chair | 46.28 | 79.49 | | boat | 53.07 | 87.21 | | bar | 58.62 | 83.73 | | arcade machine | 73.31 | 77.17 | | hovel | 24.4 | 28.46 | | bus | 89.88 | 95.29 | | towel | 65.07 | 87.45 | | light | 46.76 | 60.34 | | truck | 38.17 | 46.31 | | tower | 6.95 | 11.32 | | chandelier | 63.49 | 85.05 | | awning | 30.03 | 38.39 | | streetlight | 22.68 | 30.34 | | booth | 33.26 | 50.33 | | television receiver | 75.7 | 84.05 | | airplane | 59.65 | 70.83 | | dirt track | 5.86 | 6.77 | | apparel | 44.75 | 70.18 | | pole | 17.41 | 21.16 | | land | 0.05 | 0.06 | | bannister | 9.17 | 14.92 | | escalator | 45.27 | 54.63 | | ottoman | 48.5 | 71.25 | | bottle | 25.42 | 33.42 | | buffet | 47.08 | 64.1 | | poster | 24.07 | 29.27 | | stage | 21.48 | 27.86 | | van | 28.11 | 32.26 | | ship | 6.01 | 6.15 | | fountain | 2.09 | 2.11 | | conveyer belt | 80.22 | 94.85 | | canopy | 58.95 | 67.01 | | washer | 71.36 | 73.9 | | plaything | 37.68 | 53.47 | | swimming pool | 52.19 | 89.01 | | stool | 44.2 | 70.64 | | barrel | 28.51 | 28.74 | | basket | 38.67 | 55.25 | | waterfall | 33.94 | 35.24 | | tent | 93.49 | 97.86 | | bag | 20.26 | 23.85 | | minibike | 63.78 | 75.07 | | cradle | 74.97 | 97.25 | | oven | 46.63 | 54.96 | | ball | 51.58 | 71.6 | | food | 24.74 | 26.54 | | step | 7.77 | 9.09 | | tank | 24.09 | 28.73 | | trade name | 16.04 | 17.71 | | microwave | 81.66 | 94.03 | | pot | 51.98 | 59.01 | | animal | 77.1 | 82.07 | | bicycle | 59.78 | 82.29 | | lake | 0.0 | 0.0 | | dishwasher | 67.73 | 77.68 | | screen | 57.18 | 90.23 | | blanket | 7.61 | 8.32 | | sculpture | 59.73 | 66.8 | | hood | 64.96 | 70.32 | | sconce | 46.37 | 59.74 | | vase | 37.65 | 55.32 | | traffic light | 27.16 | 56.25 | | tray | 7.47 | 9.71 | | ashcan | 50.03 | 64.36 | | fan | 59.23 | 76.81 | | pier | 36.38 | 42.28 | | crt screen | 4.89 | 12.98 | | plate | 56.19 | 69.76 | | monitor | 1.6 | 1.67 | | bulletin board | 57.24 | 71.24 | | shower | 1.23 | 4.46 | | radiator | 52.86 | 64.46 | | glass | 17.17 | 18.93 | | clock | 34.34 | 39.21 | | flag | 68.4 | 75.25 | +---------------------+-------+-------+ 2023-11-10 04:12:47,316 - mmseg - INFO - Summary: 2023-11-10 04:12:47,316 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 83.08 | 48.71 | 61.09 | +-------+-------+-------+ 2023-11-10 04:12:47,317 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 04:12:47,317 - mmseg - INFO - Iter(val) [250] aAcc: 0.8308, mIoU: 0.4871, mAcc: 0.6109, IoU.wall: 0.7836, IoU.building: 0.8152, IoU.sky: 0.9371, IoU.floor: 0.8223, IoU.tree: 0.7416, IoU.ceiling: 0.8407, IoU.road: 0.8337, IoU.bed : 0.9016, IoU.windowpane: 0.6282, IoU.grass: 0.6710, IoU.cabinet: 0.6312, IoU.sidewalk: 0.6592, IoU.person: 0.8054, IoU.earth: 0.3214, IoU.door: 0.5480, IoU.table: 0.6309, IoU.mountain: 0.5669, IoU.plant: 0.5026, IoU.curtain: 0.7518, IoU.chair: 0.5672, IoU.car: 0.8291, IoU.water: 0.4869, IoU.painting: 0.7035, IoU.sofa: 0.7581, IoU.shelf: 0.4334, IoU.house: 0.3853, IoU.sea: 0.5010, IoU.mirror: 0.7239, IoU.rug: 0.6732, IoU.field: 0.1882, IoU.armchair: 0.5562, IoU.seat: 0.6120, IoU.fence: 0.4691, IoU.desk: 0.4664, IoU.rock: 0.4584, IoU.wardrobe: 0.5525, IoU.lamp: 0.6386, IoU.bathtub: 0.8297, IoU.railing: 0.3979, IoU.cushion: 0.6084, IoU.base: 0.1929, IoU.box: 0.2950, IoU.column: 0.4801, IoU.signboard: 0.3611, IoU.chest of drawers: 0.4335, IoU.counter: 0.4023, IoU.sand: 0.6175, IoU.sink: 0.7527, IoU.skyscraper: 0.4437, IoU.fireplace: 0.7076, IoU.refrigerator: 0.7700, IoU.grandstand: 0.4407, IoU.path: 0.1778, IoU.stairs: 0.2767, IoU.runway: 0.6727, IoU.case: 0.4469, IoU.pool table: 0.8967, IoU.pillow: 0.6041, IoU.screen door: 0.5332, IoU.stairway: 0.3997, IoU.river: 0.2370, IoU.bridge: 0.3956, IoU.bookcase: 0.3102, IoU.blind: 0.3821, IoU.coffee table: 0.6105, IoU.toilet: 0.8778, IoU.flower: 0.3865, IoU.book: 0.4680, IoU.hill: 0.0425, IoU.bench: 0.5022, IoU.countertop: 0.5732, IoU.stove: 0.7983, IoU.palm: 0.4704, IoU.kitchen island: 0.4332, IoU.computer: 0.7658, IoU.swivel chair: 0.4628, IoU.boat: 0.5307, IoU.bar: 0.5862, IoU.arcade machine: 0.7331, IoU.hovel: 0.2440, IoU.bus: 0.8988, IoU.towel: 0.6507, IoU.light: 0.4676, IoU.truck: 0.3817, IoU.tower: 0.0695, IoU.chandelier: 0.6349, IoU.awning: 0.3003, IoU.streetlight: 0.2268, IoU.booth: 0.3326, IoU.television receiver: 0.7570, IoU.airplane: 0.5965, IoU.dirt track: 0.0586, IoU.apparel: 0.4475, IoU.pole: 0.1741, IoU.land: 0.0005, IoU.bannister: 0.0917, IoU.escalator: 0.4527, IoU.ottoman: 0.4850, IoU.bottle: 0.2542, IoU.buffet: 0.4708, IoU.poster: 0.2407, IoU.stage: 0.2148, IoU.van: 0.2811, IoU.ship: 0.0601, IoU.fountain: 0.0209, IoU.conveyer belt: 0.8022, IoU.canopy: 0.5895, IoU.washer: 0.7136, IoU.plaything: 0.3768, IoU.swimming pool: 0.5219, IoU.stool: 0.4420, IoU.barrel: 0.2851, IoU.basket: 0.3867, IoU.waterfall: 0.3394, IoU.tent: 0.9349, IoU.bag: 0.2026, IoU.minibike: 0.6378, IoU.cradle: 0.7497, IoU.oven: 0.4663, IoU.ball: 0.5158, IoU.food: 0.2474, IoU.step: 0.0777, IoU.tank: 0.2409, IoU.trade name: 0.1604, IoU.microwave: 0.8166, IoU.pot: 0.5198, IoU.animal: 0.7710, IoU.bicycle: 0.5978, IoU.lake: 0.0000, IoU.dishwasher: 0.6773, IoU.screen: 0.5718, IoU.blanket: 0.0761, IoU.sculpture: 0.5973, IoU.hood: 0.6496, IoU.sconce: 0.4637, IoU.vase: 0.3765, IoU.traffic light: 0.2716, IoU.tray: 0.0747, IoU.ashcan: 0.5003, IoU.fan: 0.5923, IoU.pier: 0.3638, IoU.crt screen: 0.0489, IoU.plate: 0.5619, IoU.monitor: 0.0160, IoU.bulletin board: 0.5724, IoU.shower: 0.0123, IoU.radiator: 0.5286, IoU.glass: 0.1717, IoU.clock: 0.3434, IoU.flag: 0.6840, Acc.wall: 0.8711, Acc.building: 0.9303, Acc.sky: 0.9744, Acc.floor: 0.9156, Acc.tree: 0.8665, Acc.ceiling: 0.9186, Acc.road: 0.9057, Acc.bed : 0.9598, Acc.windowpane: 0.7909, Acc.grass: 0.8260, Acc.cabinet: 0.7241, Acc.sidewalk: 0.8144, Acc.person: 0.9215, Acc.earth: 0.4511, Acc.door: 0.6995, Acc.table: 0.8062, Acc.mountain: 0.7304, Acc.plant: 0.6273, Acc.curtain: 0.8243, Acc.chair: 0.6774, Acc.car: 0.9449, Acc.water: 0.6543, Acc.painting: 0.8992, Acc.sofa: 0.8730, Acc.shelf: 0.6762, Acc.house: 0.5034, Acc.sea: 0.7756, Acc.mirror: 0.8399, Acc.rug: 0.7543, Acc.field: 0.3382, Acc.armchair: 0.7404, Acc.seat: 0.7722, Acc.fence: 0.6328, Acc.desk: 0.6594, Acc.rock: 0.6003, Acc.wardrobe: 0.7584, Acc.lamp: 0.8068, Acc.bathtub: 0.9252, Acc.railing: 0.5694, Acc.cushion: 0.7374, Acc.base: 0.3470, Acc.box: 0.3726, Acc.column: 0.6214, Acc.signboard: 0.5238, Acc.chest of drawers: 0.6154, Acc.counter: 0.5014, Acc.sand: 0.7956, Acc.sink: 0.8365, Acc.skyscraper: 0.5376, Acc.fireplace: 0.8987, Acc.refrigerator: 0.8781, Acc.grandstand: 0.8305, Acc.path: 0.2387, Acc.stairs: 0.3524, Acc.runway: 0.8581, Acc.case: 0.7064, Acc.pool table: 0.9763, Acc.pillow: 0.7261, Acc.screen door: 0.6639, Acc.stairway: 0.5693, Acc.river: 0.3481, Acc.bridge: 0.4400, Acc.bookcase: 0.4253, Acc.blind: 0.4187, Acc.coffee table: 0.8653, Acc.toilet: 0.9294, Acc.flower: 0.6769, Acc.book: 0.7512, Acc.hill: 0.0632, Acc.bench: 0.5824, Acc.countertop: 0.7597, Acc.stove: 0.8864, Acc.palm: 0.6158, Acc.kitchen island: 0.7062, Acc.computer: 0.8785, Acc.swivel chair: 0.7949, Acc.boat: 0.8721, Acc.bar: 0.8373, Acc.arcade machine: 0.7717, Acc.hovel: 0.2846, Acc.bus: 0.9529, Acc.towel: 0.8745, Acc.light: 0.6034, Acc.truck: 0.4631, Acc.tower: 0.1132, Acc.chandelier: 0.8505, Acc.awning: 0.3839, Acc.streetlight: 0.3034, Acc.booth: 0.5033, Acc.television receiver: 0.8405, Acc.airplane: 0.7083, Acc.dirt track: 0.0677, Acc.apparel: 0.7018, Acc.pole: 0.2116, Acc.land: 0.0006, Acc.bannister: 0.1492, Acc.escalator: 0.5463, Acc.ottoman: 0.7125, Acc.bottle: 0.3342, Acc.buffet: 0.6410, Acc.poster: 0.2927, Acc.stage: 0.2786, Acc.van: 0.3226, Acc.ship: 0.0615, Acc.fountain: 0.0211, Acc.conveyer belt: 0.9485, Acc.canopy: 0.6701, Acc.washer: 0.7390, Acc.plaything: 0.5347, Acc.swimming pool: 0.8901, Acc.stool: 0.7064, Acc.barrel: 0.2874, Acc.basket: 0.5525, Acc.waterfall: 0.3524, Acc.tent: 0.9786, Acc.bag: 0.2385, Acc.minibike: 0.7507, Acc.cradle: 0.9725, Acc.oven: 0.5496, Acc.ball: 0.7160, Acc.food: 0.2654, Acc.step: 0.0909, Acc.tank: 0.2873, Acc.trade name: 0.1771, Acc.microwave: 0.9403, Acc.pot: 0.5901, Acc.animal: 0.8207, Acc.bicycle: 0.8229, Acc.lake: 0.0000, Acc.dishwasher: 0.7768, Acc.screen: 0.9023, Acc.blanket: 0.0832, Acc.sculpture: 0.6680, Acc.hood: 0.7032, Acc.sconce: 0.5974, Acc.vase: 0.5532, Acc.traffic light: 0.5625, Acc.tray: 0.0971, Acc.ashcan: 0.6436, Acc.fan: 0.7681, Acc.pier: 0.4228, Acc.crt screen: 0.1298, Acc.plate: 0.6976, Acc.monitor: 0.0167, Acc.bulletin board: 0.7124, Acc.shower: 0.0446, Acc.radiator: 0.6446, Acc.glass: 0.1893, Acc.clock: 0.3921, Acc.flag: 0.7525 2023-11-10 04:13:48,278 - mmseg - INFO - Iter [4050/10000] lr: 1.928e-06, eta: 2:13:58, time: 2.298, data_time: 1.087, memory: 38534, decode.loss_ce: 0.2239, decode.acc_seg: 91.2183, loss: 0.2239 2023-11-10 04:14:49,150 - mmseg - INFO - Iter [4100/10000] lr: 1.912e-06, eta: 2:12:41, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2249, decode.acc_seg: 91.2906, loss: 0.2249 2023-11-10 04:15:52,235 - mmseg - INFO - Iter [4150/10000] lr: 1.896e-06, eta: 2:11:27, time: 1.262, data_time: 0.051, memory: 38534, decode.loss_ce: 0.2232, decode.acc_seg: 91.2452, loss: 0.2232 2023-11-10 04:16:53,175 - mmseg - INFO - Iter [4200/10000] lr: 1.879e-06, eta: 2:10:11, time: 1.219, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2216, decode.acc_seg: 91.3844, loss: 0.2216 2023-11-10 04:17:54,006 - mmseg - INFO - Iter [4250/10000] lr: 1.863e-06, eta: 2:08:54, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2597, decode.acc_seg: 90.1685, loss: 0.2597 2023-11-10 04:18:57,214 - mmseg - INFO - Iter [4300/10000] lr: 1.847e-06, eta: 2:07:42, time: 1.264, data_time: 0.052, memory: 38534, decode.loss_ce: 0.2303, decode.acc_seg: 91.0450, loss: 0.2303 2023-11-10 04:19:58,088 - mmseg - INFO - Iter [4350/10000] lr: 1.831e-06, eta: 2:06:26, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2272, decode.acc_seg: 91.4008, loss: 0.2272 2023-11-10 04:20:58,963 - mmseg - INFO - Iter [4400/10000] lr: 1.815e-06, eta: 2:05:11, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2296, decode.acc_seg: 91.0567, loss: 0.2296 2023-11-10 04:22:02,099 - mmseg - INFO - Iter [4450/10000] lr: 1.798e-06, eta: 2:03:59, time: 1.263, data_time: 0.051, memory: 38534, decode.loss_ce: 0.2451, decode.acc_seg: 90.9205, loss: 0.2451 2023-11-10 04:23:02,994 - mmseg - INFO - Iter [4500/10000] lr: 1.782e-06, eta: 2:02:45, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2193, decode.acc_seg: 91.2959, loss: 0.2193 2023-11-10 04:24:03,861 - mmseg - INFO - Iter [4550/10000] lr: 1.766e-06, eta: 2:01:30, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2128, decode.acc_seg: 91.6913, loss: 0.2128 2023-11-10 04:25:06,974 - mmseg - INFO - Iter [4600/10000] lr: 1.750e-06, eta: 2:00:19, time: 1.262, data_time: 0.053, memory: 38534, decode.loss_ce: 0.2135, decode.acc_seg: 91.8292, loss: 0.2135 2023-11-10 04:26:07,830 - mmseg - INFO - Iter [4650/10000] lr: 1.734e-06, eta: 1:59:05, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2260, decode.acc_seg: 91.1690, loss: 0.2260 2023-11-10 04:27:08,670 - mmseg - INFO - Iter [4700/10000] lr: 1.717e-06, eta: 1:57:52, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2315, decode.acc_seg: 90.9456, loss: 0.2315 2023-11-10 04:28:11,905 - mmseg - INFO - Iter [4750/10000] lr: 1.701e-06, eta: 1:56:41, time: 1.265, data_time: 0.054, memory: 38534, decode.loss_ce: 0.2232, decode.acc_seg: 91.3283, loss: 0.2232 2023-11-10 04:29:12,839 - mmseg - INFO - Iter [4800/10000] lr: 1.685e-06, eta: 1:55:28, time: 1.219, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2268, decode.acc_seg: 91.1962, loss: 0.2268 2023-11-10 04:30:13,733 - mmseg - INFO - Iter [4850/10000] lr: 1.669e-06, eta: 1:54:16, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2262, decode.acc_seg: 91.0765, loss: 0.2262 2023-11-10 04:31:17,008 - mmseg - INFO - Iter [4900/10000] lr: 1.653e-06, eta: 1:53:06, time: 1.265, data_time: 0.055, memory: 38534, decode.loss_ce: 0.2077, decode.acc_seg: 91.7645, loss: 0.2077 2023-11-10 04:32:17,868 - mmseg - INFO - Iter [4950/10000] lr: 1.636e-06, eta: 1:51:53, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2208, decode.acc_seg: 91.3724, loss: 0.2208 2023-11-10 04:33:18,732 - mmseg - INFO - Saving checkpoint at 5000 iterations 2023-11-10 04:34:10,069 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 04:34:10,070 - mmseg - INFO - Iter [5000/10000] lr: 1.620e-06, eta: 1:51:33, time: 2.244, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2074, decode.acc_seg: 91.9241, loss: 0.2074 2023-11-10 04:35:04,099 - mmseg - INFO - per class results: 2023-11-10 04:35:04,105 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 78.77 | 89.27 | | building | 81.84 | 93.34 | | sky | 93.96 | 97.19 | | floor | 82.7 | 92.75 | | tree | 74.31 | 87.06 | | ceiling | 83.96 | 91.54 | | road | 83.52 | 90.43 | | bed | 90.17 | 95.63 | | windowpane | 62.13 | 76.1 | | grass | 67.57 | 85.63 | | cabinet | 63.85 | 75.35 | | sidewalk | 67.08 | 83.7 | | person | 80.97 | 90.12 | | earth | 33.36 | 41.45 | | door | 57.78 | 73.91 | | table | 64.84 | 81.38 | | mountain | 60.71 | 79.82 | | plant | 52.31 | 65.02 | | curtain | 75.05 | 83.82 | | chair | 57.62 | 71.97 | | car | 83.3 | 93.57 | | water | 55.43 | 79.31 | | painting | 72.7 | 84.75 | | sofa | 73.59 | 88.18 | | shelf | 40.67 | 60.01 | | house | 42.98 | 59.33 | | sea | 56.57 | 73.65 | | mirror | 73.14 | 81.99 | | rug | 65.96 | 72.15 | | field | 21.04 | 37.18 | | armchair | 53.49 | 67.99 | | seat | 53.48 | 67.97 | | fence | 47.18 | 64.35 | | desk | 47.45 | 59.65 | | rock | 45.44 | 58.13 | | wardrobe | 54.61 | 72.42 | | lamp | 64.83 | 77.02 | | bathtub | 82.74 | 87.5 | | railing | 41.46 | 61.26 | | cushion | 61.49 | 75.49 | | base | 14.76 | 16.07 | | box | 30.37 | 38.65 | | column | 48.06 | 58.71 | | signboard | 36.56 | 47.05 | | chest of drawers | 41.33 | 60.48 | | counter | 44.26 | 61.53 | | sand | 66.95 | 78.73 | | sink | 73.66 | 80.43 | | skyscraper | 41.86 | 50.18 | | fireplace | 70.59 | 88.76 | | refrigerator | 77.28 | 86.44 | | grandstand | 46.17 | 84.79 | | path | 18.95 | 26.75 | | stairs | 30.35 | 38.37 | | runway | 65.26 | 83.21 | | case | 47.08 | 82.45 | | pool table | 90.81 | 97.55 | | pillow | 57.59 | 67.35 | | screen door | 50.18 | 62.9 | | stairway | 37.54 | 49.29 | | river | 21.24 | 31.24 | | bridge | 46.73 | 50.93 | | bookcase | 34.46 | 55.65 | | blind | 38.84 | 42.78 | | coffee table | 63.16 | 85.13 | | toilet | 88.82 | 92.86 | | flower | 40.73 | 60.08 | | book | 43.38 | 57.45 | | hill | 3.53 | 5.62 | | bench | 42.03 | 46.31 | | countertop | 58.7 | 76.86 | | stove | 81.03 | 86.96 | | palm | 45.59 | 58.51 | | kitchen island | 41.18 | 56.18 | | computer | 73.51 | 79.72 | | swivel chair | 47.55 | 76.3 | | boat | 56.6 | 75.5 | | bar | 63.17 | 69.48 | | arcade machine | 71.85 | 75.12 | | hovel | 21.58 | 22.64 | | bus | 91.38 | 94.64 | | towel | 66.42 | 85.55 | | light | 47.21 | 57.9 | | truck | 43.45 | 53.77 | | tower | 15.04 | 25.71 | | chandelier | 63.54 | 81.95 | | awning | 29.6 | 47.17 | | streetlight | 22.61 | 31.14 | | booth | 35.48 | 37.66 | | television receiver | 75.29 | 82.71 | | airplane | 67.45 | 80.83 | | dirt track | 0.68 | 0.7 | | apparel | 45.51 | 69.62 | | pole | 17.88 | 23.06 | | land | 4.49 | 7.73 | | bannister | 12.56 | 20.81 | | escalator | 51.75 | 62.92 | | ottoman | 48.35 | 65.18 | | bottle | 22.58 | 27.98 | | buffet | 28.54 | 31.12 | | poster | 33.2 | 38.58 | | stage | 13.41 | 16.2 | | van | 32.4 | 37.58 | | ship | 1.29 | 1.36 | | fountain | 2.2 | 2.21 | | conveyer belt | 79.66 | 95.47 | | canopy | 45.82 | 51.45 | | washer | 68.08 | 70.36 | | plaything | 32.73 | 38.14 | | swimming pool | 76.19 | 85.81 | | stool | 46.1 | 66.07 | | barrel | 30.38 | 30.53 | | basket | 37.21 | 53.59 | | waterfall | 45.69 | 53.92 | | tent | 95.07 | 97.98 | | bag | 19.41 | 22.18 | | minibike | 64.17 | 74.64 | | cradle | 73.63 | 97.72 | | oven | 52.6 | 62.57 | | ball | 44.82 | 73.28 | | food | 21.21 | 22.59 | | step | 5.25 | 6.03 | | tank | 20.87 | 24.99 | | trade name | 22.91 | 26.06 | | microwave | 82.96 | 92.19 | | pot | 49.54 | 54.82 | | animal | 76.95 | 80.33 | | bicycle | 58.4 | 78.61 | | lake | 0.0 | 0.0 | | dishwasher | 75.31 | 80.31 | | screen | 55.31 | 93.14 | | blanket | 9.16 | 9.85 | | sculpture | 62.29 | 70.46 | | hood | 58.42 | 64.5 | | sconce | 45.62 | 55.4 | | vase | 36.49 | 54.87 | | traffic light | 30.74 | 48.56 | | tray | 8.09 | 10.29 | | ashcan | 47.35 | 60.59 | | fan | 58.72 | 81.58 | | pier | 35.38 | 37.65 | | crt screen | 3.84 | 11.1 | | plate | 57.17 | 70.0 | | monitor | 8.82 | 11.97 | | bulletin board | 55.12 | 59.6 | | shower | 1.03 | 3.86 | | radiator | 51.61 | 57.66 | | glass | 18.12 | 20.62 | | clock | 31.39 | 36.6 | | flag | 67.22 | 71.37 | +---------------------+-------+-------+ 2023-11-10 04:35:04,105 - mmseg - INFO - Summary: 2023-11-10 04:35:04,105 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 83.55 | 49.08 | 59.91 | +-------+-------+-------+ 2023-11-10 04:35:04,106 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 04:35:04,106 - mmseg - INFO - Iter(val) [250] aAcc: 0.8355, mIoU: 0.4908, mAcc: 0.5991, IoU.wall: 0.7877, IoU.building: 0.8184, IoU.sky: 0.9396, IoU.floor: 0.8270, IoU.tree: 0.7431, IoU.ceiling: 0.8396, IoU.road: 0.8352, IoU.bed : 0.9017, IoU.windowpane: 0.6213, IoU.grass: 0.6757, IoU.cabinet: 0.6385, IoU.sidewalk: 0.6708, IoU.person: 0.8097, IoU.earth: 0.3336, IoU.door: 0.5778, IoU.table: 0.6484, IoU.mountain: 0.6071, IoU.plant: 0.5231, IoU.curtain: 0.7505, IoU.chair: 0.5762, IoU.car: 0.8330, IoU.water: 0.5543, IoU.painting: 0.7270, IoU.sofa: 0.7359, IoU.shelf: 0.4067, IoU.house: 0.4298, IoU.sea: 0.5657, IoU.mirror: 0.7314, IoU.rug: 0.6596, IoU.field: 0.2104, IoU.armchair: 0.5349, IoU.seat: 0.5348, IoU.fence: 0.4718, IoU.desk: 0.4745, IoU.rock: 0.4544, IoU.wardrobe: 0.5461, IoU.lamp: 0.6483, IoU.bathtub: 0.8274, IoU.railing: 0.4146, IoU.cushion: 0.6149, IoU.base: 0.1476, IoU.box: 0.3037, IoU.column: 0.4806, IoU.signboard: 0.3656, IoU.chest of drawers: 0.4133, IoU.counter: 0.4426, IoU.sand: 0.6695, IoU.sink: 0.7366, IoU.skyscraper: 0.4186, IoU.fireplace: 0.7059, IoU.refrigerator: 0.7728, IoU.grandstand: 0.4617, IoU.path: 0.1895, IoU.stairs: 0.3035, IoU.runway: 0.6526, IoU.case: 0.4708, IoU.pool table: 0.9081, IoU.pillow: 0.5759, IoU.screen door: 0.5018, IoU.stairway: 0.3754, IoU.river: 0.2124, IoU.bridge: 0.4673, IoU.bookcase: 0.3446, IoU.blind: 0.3884, IoU.coffee table: 0.6316, IoU.toilet: 0.8882, IoU.flower: 0.4073, IoU.book: 0.4338, IoU.hill: 0.0353, IoU.bench: 0.4203, IoU.countertop: 0.5870, IoU.stove: 0.8103, IoU.palm: 0.4559, IoU.kitchen island: 0.4118, IoU.computer: 0.7351, IoU.swivel chair: 0.4755, IoU.boat: 0.5660, IoU.bar: 0.6317, IoU.arcade machine: 0.7185, IoU.hovel: 0.2158, IoU.bus: 0.9138, IoU.towel: 0.6642, IoU.light: 0.4721, IoU.truck: 0.4345, IoU.tower: 0.1504, IoU.chandelier: 0.6354, IoU.awning: 0.2960, IoU.streetlight: 0.2261, IoU.booth: 0.3548, IoU.television receiver: 0.7529, IoU.airplane: 0.6745, IoU.dirt track: 0.0068, IoU.apparel: 0.4551, IoU.pole: 0.1788, IoU.land: 0.0449, IoU.bannister: 0.1256, IoU.escalator: 0.5175, IoU.ottoman: 0.4835, IoU.bottle: 0.2258, IoU.buffet: 0.2854, IoU.poster: 0.3320, IoU.stage: 0.1341, IoU.van: 0.3240, IoU.ship: 0.0129, IoU.fountain: 0.0220, IoU.conveyer belt: 0.7966, IoU.canopy: 0.4582, IoU.washer: 0.6808, IoU.plaything: 0.3273, IoU.swimming pool: 0.7619, IoU.stool: 0.4610, IoU.barrel: 0.3038, IoU.basket: 0.3721, IoU.waterfall: 0.4569, IoU.tent: 0.9507, IoU.bag: 0.1941, IoU.minibike: 0.6417, IoU.cradle: 0.7363, IoU.oven: 0.5260, IoU.ball: 0.4482, IoU.food: 0.2121, IoU.step: 0.0525, IoU.tank: 0.2087, IoU.trade name: 0.2291, IoU.microwave: 0.8296, IoU.pot: 0.4954, IoU.animal: 0.7695, IoU.bicycle: 0.5840, IoU.lake: 0.0000, IoU.dishwasher: 0.7531, IoU.screen: 0.5531, IoU.blanket: 0.0916, IoU.sculpture: 0.6229, IoU.hood: 0.5842, IoU.sconce: 0.4562, IoU.vase: 0.3649, IoU.traffic light: 0.3074, IoU.tray: 0.0809, IoU.ashcan: 0.4735, IoU.fan: 0.5872, IoU.pier: 0.3538, IoU.crt screen: 0.0384, IoU.plate: 0.5717, IoU.monitor: 0.0882, IoU.bulletin board: 0.5512, IoU.shower: 0.0103, IoU.radiator: 0.5161, IoU.glass: 0.1812, IoU.clock: 0.3139, IoU.flag: 0.6722, Acc.wall: 0.8927, Acc.building: 0.9334, Acc.sky: 0.9719, Acc.floor: 0.9275, Acc.tree: 0.8706, Acc.ceiling: 0.9154, Acc.road: 0.9043, Acc.bed : 0.9563, Acc.windowpane: 0.7610, Acc.grass: 0.8563, Acc.cabinet: 0.7535, Acc.sidewalk: 0.8370, Acc.person: 0.9012, Acc.earth: 0.4145, Acc.door: 0.7391, Acc.table: 0.8138, Acc.mountain: 0.7982, Acc.plant: 0.6502, Acc.curtain: 0.8382, Acc.chair: 0.7197, Acc.car: 0.9357, Acc.water: 0.7931, Acc.painting: 0.8475, Acc.sofa: 0.8818, Acc.shelf: 0.6001, Acc.house: 0.5933, Acc.sea: 0.7365, Acc.mirror: 0.8199, Acc.rug: 0.7215, Acc.field: 0.3718, Acc.armchair: 0.6799, Acc.seat: 0.6797, Acc.fence: 0.6435, Acc.desk: 0.5965, Acc.rock: 0.5813, Acc.wardrobe: 0.7242, Acc.lamp: 0.7702, Acc.bathtub: 0.8750, Acc.railing: 0.6126, Acc.cushion: 0.7549, Acc.base: 0.1607, Acc.box: 0.3865, Acc.column: 0.5871, Acc.signboard: 0.4705, Acc.chest of drawers: 0.6048, Acc.counter: 0.6153, Acc.sand: 0.7873, Acc.sink: 0.8043, Acc.skyscraper: 0.5018, Acc.fireplace: 0.8876, Acc.refrigerator: 0.8644, Acc.grandstand: 0.8479, Acc.path: 0.2675, Acc.stairs: 0.3837, Acc.runway: 0.8321, Acc.case: 0.8245, Acc.pool table: 0.9755, Acc.pillow: 0.6735, Acc.screen door: 0.6290, Acc.stairway: 0.4929, Acc.river: 0.3124, Acc.bridge: 0.5093, Acc.bookcase: 0.5565, Acc.blind: 0.4278, Acc.coffee table: 0.8513, Acc.toilet: 0.9286, Acc.flower: 0.6008, Acc.book: 0.5745, Acc.hill: 0.0562, Acc.bench: 0.4631, Acc.countertop: 0.7686, Acc.stove: 0.8696, Acc.palm: 0.5851, Acc.kitchen island: 0.5618, Acc.computer: 0.7972, Acc.swivel chair: 0.7630, Acc.boat: 0.7550, Acc.bar: 0.6948, Acc.arcade machine: 0.7512, Acc.hovel: 0.2264, Acc.bus: 0.9464, Acc.towel: 0.8555, Acc.light: 0.5790, Acc.truck: 0.5377, Acc.tower: 0.2571, Acc.chandelier: 0.8195, Acc.awning: 0.4717, Acc.streetlight: 0.3114, Acc.booth: 0.3766, Acc.television receiver: 0.8271, Acc.airplane: 0.8083, Acc.dirt track: 0.0070, Acc.apparel: 0.6962, Acc.pole: 0.2306, Acc.land: 0.0773, Acc.bannister: 0.2081, Acc.escalator: 0.6292, Acc.ottoman: 0.6518, Acc.bottle: 0.2798, Acc.buffet: 0.3112, Acc.poster: 0.3858, Acc.stage: 0.1620, Acc.van: 0.3758, Acc.ship: 0.0136, Acc.fountain: 0.0221, Acc.conveyer belt: 0.9547, Acc.canopy: 0.5145, Acc.washer: 0.7036, Acc.plaything: 0.3814, Acc.swimming pool: 0.8581, Acc.stool: 0.6607, Acc.barrel: 0.3053, Acc.basket: 0.5359, Acc.waterfall: 0.5392, Acc.tent: 0.9798, Acc.bag: 0.2218, Acc.minibike: 0.7464, Acc.cradle: 0.9772, Acc.oven: 0.6257, Acc.ball: 0.7328, Acc.food: 0.2259, Acc.step: 0.0603, Acc.tank: 0.2499, Acc.trade name: 0.2606, Acc.microwave: 0.9219, Acc.pot: 0.5482, Acc.animal: 0.8033, Acc.bicycle: 0.7861, Acc.lake: 0.0000, Acc.dishwasher: 0.8031, Acc.screen: 0.9314, Acc.blanket: 0.0985, Acc.sculpture: 0.7046, Acc.hood: 0.6450, Acc.sconce: 0.5540, Acc.vase: 0.5487, Acc.traffic light: 0.4856, Acc.tray: 0.1029, Acc.ashcan: 0.6059, Acc.fan: 0.8158, Acc.pier: 0.3765, Acc.crt screen: 0.1110, Acc.plate: 0.7000, Acc.monitor: 0.1197, Acc.bulletin board: 0.5960, Acc.shower: 0.0386, Acc.radiator: 0.5766, Acc.glass: 0.2062, Acc.clock: 0.3660, Acc.flag: 0.7137 2023-11-10 04:36:05,058 - mmseg - INFO - Iter [5050/10000] lr: 1.604e-06, eta: 1:51:13, time: 2.300, data_time: 1.089, memory: 38534, decode.loss_ce: 0.2075, decode.acc_seg: 91.8022, loss: 0.2075 2023-11-10 04:37:08,213 - mmseg - INFO - Iter [5100/10000] lr: 1.588e-06, eta: 1:50:01, time: 1.263, data_time: 0.051, memory: 38534, decode.loss_ce: 0.2055, decode.acc_seg: 91.6958, loss: 0.2055 2023-11-10 04:38:09,101 - mmseg - INFO - Iter [5150/10000] lr: 1.572e-06, eta: 1:48:48, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2073, decode.acc_seg: 91.9136, loss: 0.2073 2023-11-10 04:39:09,961 - mmseg - INFO - Iter [5200/10000] lr: 1.555e-06, eta: 1:47:35, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2166, decode.acc_seg: 91.4550, loss: 0.2166 2023-11-10 04:40:13,190 - mmseg - INFO - Iter [5250/10000] lr: 1.539e-06, eta: 1:46:24, time: 1.265, data_time: 0.052, memory: 38534, decode.loss_ce: 0.2059, decode.acc_seg: 91.9588, loss: 0.2059 2023-11-10 04:41:14,050 - mmseg - INFO - Iter [5300/10000] lr: 1.523e-06, eta: 1:45:11, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2012, decode.acc_seg: 92.0848, loss: 0.2012 2023-11-10 04:42:14,934 - mmseg - INFO - Iter [5350/10000] lr: 1.507e-06, eta: 1:43:58, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2008, decode.acc_seg: 91.9675, loss: 0.2008 2023-11-10 04:43:18,145 - mmseg - INFO - Iter [5400/10000] lr: 1.491e-06, eta: 1:42:48, time: 1.264, data_time: 0.052, memory: 38534, decode.loss_ce: 0.2127, decode.acc_seg: 91.7482, loss: 0.2127 2023-11-10 04:44:19,006 - mmseg - INFO - Iter [5450/10000] lr: 1.474e-06, eta: 1:41:36, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2060, decode.acc_seg: 91.8883, loss: 0.2060 2023-11-10 04:45:19,879 - mmseg - INFO - Iter [5500/10000] lr: 1.458e-06, eta: 1:40:24, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1992, decode.acc_seg: 92.1246, loss: 0.1992 2023-11-10 04:46:23,037 - mmseg - INFO - Iter [5550/10000] lr: 1.442e-06, eta: 1:39:14, time: 1.263, data_time: 0.052, memory: 38534, decode.loss_ce: 0.2059, decode.acc_seg: 92.0126, loss: 0.2059 2023-11-10 04:47:23,950 - mmseg - INFO - Iter [5600/10000] lr: 1.426e-06, eta: 1:38:02, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1970, decode.acc_seg: 92.2762, loss: 0.1970 2023-11-10 04:48:24,837 - mmseg - INFO - Iter [5650/10000] lr: 1.410e-06, eta: 1:36:51, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1916, decode.acc_seg: 92.2032, loss: 0.1916 2023-11-10 04:49:27,957 - mmseg - INFO - Iter [5700/10000] lr: 1.393e-06, eta: 1:35:41, time: 1.262, data_time: 0.052, memory: 38534, decode.loss_ce: 0.2055, decode.acc_seg: 91.8727, loss: 0.2055 2023-11-10 04:50:28,788 - mmseg - INFO - Iter [5750/10000] lr: 1.377e-06, eta: 1:34:30, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1964, decode.acc_seg: 92.0867, loss: 0.1964 2023-11-10 04:51:29,640 - mmseg - INFO - Iter [5800/10000] lr: 1.361e-06, eta: 1:33:19, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.2011, decode.acc_seg: 92.1605, loss: 0.2011 2023-11-10 04:52:32,800 - mmseg - INFO - Iter [5850/10000] lr: 1.345e-06, eta: 1:32:10, time: 1.263, data_time: 0.051, memory: 38534, decode.loss_ce: 0.1837, decode.acc_seg: 92.5808, loss: 0.1837 2023-11-10 04:53:33,582 - mmseg - INFO - Iter [5900/10000] lr: 1.329e-06, eta: 1:30:59, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1850, decode.acc_seg: 92.7479, loss: 0.1850 2023-11-10 04:54:34,405 - mmseg - INFO - Iter [5950/10000] lr: 1.312e-06, eta: 1:29:49, time: 1.216, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1880, decode.acc_seg: 92.4555, loss: 0.1880 2023-11-10 04:55:35,283 - mmseg - INFO - Saving checkpoint at 6000 iterations 2023-11-10 04:56:31,538 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 04:56:31,539 - mmseg - INFO - Iter [6000/10000] lr: 1.296e-06, eta: 1:29:16, time: 2.343, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1976, decode.acc_seg: 92.1874, loss: 0.1976 2023-11-10 04:57:25,744 - mmseg - INFO - per class results: 2023-11-10 04:57:25,749 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 79.12 | 88.59 | | building | 82.74 | 92.65 | | sky | 94.04 | 96.85 | | floor | 82.51 | 91.32 | | tree | 74.93 | 88.64 | | ceiling | 84.26 | 92.2 | | road | 83.91 | 89.07 | | bed | 90.48 | 96.19 | | windowpane | 62.75 | 78.41 | | grass | 66.49 | 84.09 | | cabinet | 63.26 | 74.77 | | sidewalk | 66.51 | 82.34 | | person | 80.69 | 93.6 | | earth | 34.94 | 47.5 | | door | 56.86 | 71.47 | | table | 64.72 | 79.71 | | mountain | 60.4 | 77.41 | | plant | 53.02 | 66.11 | | curtain | 75.32 | 85.17 | | chair | 58.1 | 73.1 | | car | 84.15 | 93.76 | | water | 50.83 | 71.46 | | painting | 74.77 | 86.45 | | sofa | 73.5 | 92.03 | | shelf | 43.02 | 66.63 | | house | 48.91 | 65.6 | | sea | 51.19 | 75.14 | | mirror | 72.45 | 81.37 | | rug | 68.98 | 79.17 | | field | 17.84 | 30.23 | | armchair | 48.9 | 58.15 | | seat | 58.71 | 76.56 | | fence | 46.12 | 55.77 | | desk | 47.91 | 60.66 | | rock | 47.43 | 58.57 | | wardrobe | 54.02 | 74.37 | | lamp | 64.69 | 76.39 | | bathtub | 80.41 | 87.31 | | railing | 41.73 | 60.26 | | cushion | 60.36 | 79.64 | | base | 19.32 | 23.09 | | box | 29.76 | 36.21 | | column | 50.92 | 64.4 | | signboard | 36.92 | 49.3 | | chest of drawers | 39.68 | 61.82 | | counter | 44.06 | 56.44 | | sand | 62.44 | 82.46 | | sink | 74.43 | 79.96 | | skyscraper | 42.79 | 52.68 | | fireplace | 71.04 | 90.52 | | refrigerator | 78.52 | 87.18 | | grandstand | 45.44 | 87.85 | | path | 20.21 | 29.48 | | stairs | 28.33 | 34.87 | | runway | 66.91 | 92.82 | | case | 48.34 | 88.27 | | pool table | 91.27 | 96.8 | | pillow | 58.65 | 68.57 | | screen door | 53.88 | 67.25 | | stairway | 36.73 | 50.29 | | river | 21.91 | 32.9 | | bridge | 38.3 | 42.67 | | bookcase | 37.8 | 54.45 | | blind | 40.23 | 46.95 | | coffee table | 61.72 | 87.35 | | toilet | 88.87 | 93.24 | | flower | 45.16 | 64.27 | | book | 45.0 | 62.72 | | hill | 5.57 | 8.15 | | bench | 44.12 | 49.89 | | countertop | 58.83 | 74.1 | | stove | 81.96 | 88.63 | | palm | 47.08 | 69.64 | | kitchen island | 30.73 | 41.85 | | computer | 76.97 | 87.73 | | swivel chair | 47.72 | 75.43 | | boat | 46.59 | 85.25 | | bar | 64.75 | 69.51 | | arcade machine | 58.1 | 60.06 | | hovel | 26.1 | 28.47 | | bus | 90.73 | 95.72 | | towel | 66.02 | 82.1 | | light | 47.08 | 57.75 | | truck | 43.89 | 60.08 | | tower | 13.67 | 24.21 | | chandelier | 63.74 | 84.39 | | awning | 26.86 | 35.88 | | streetlight | 23.71 | 33.37 | | booth | 52.1 | 74.76 | | television receiver | 76.26 | 83.65 | | airplane | 60.37 | 71.23 | | dirt track | 2.25 | 5.84 | | apparel | 42.31 | 59.88 | | pole | 15.68 | 19.4 | | land | 4.89 | 9.51 | | bannister | 12.95 | 21.7 | | escalator | 44.95 | 54.3 | | ottoman | 51.13 | 69.54 | | bottle | 25.31 | 32.05 | | buffet | 45.86 | 51.65 | | poster | 32.66 | 40.43 | | stage | 14.5 | 18.03 | | van | 31.65 | 36.33 | | ship | 2.55 | 2.55 | | fountain | 3.14 | 3.16 | | conveyer belt | 76.9 | 92.34 | | canopy | 50.89 | 57.48 | | washer | 68.35 | 70.48 | | plaything | 33.74 | 64.09 | | swimming pool | 75.43 | 85.59 | | stool | 43.42 | 59.41 | | barrel | 36.6 | 36.89 | | basket | 38.78 | 59.54 | | waterfall | 50.54 | 62.45 | | tent | 94.4 | 98.39 | | bag | 25.18 | 29.71 | | minibike | 56.09 | 63.01 | | cradle | 71.05 | 96.51 | | oven | 53.77 | 63.0 | | ball | 51.56 | 73.72 | | food | 25.48 | 28.57 | | step | 4.78 | 5.41 | | tank | 20.45 | 24.62 | | trade name | 25.7 | 30.17 | | microwave | 84.11 | 93.29 | | pot | 52.57 | 60.35 | | animal | 74.91 | 78.87 | | bicycle | 59.48 | 76.05 | | lake | 0.0 | 0.0 | | dishwasher | 71.49 | 74.12 | | screen | 58.07 | 91.62 | | blanket | 11.58 | 12.56 | | sculpture | 66.33 | 75.67 | | hood | 60.85 | 69.15 | | sconce | 49.61 | 62.74 | | vase | 39.09 | 54.68 | | traffic light | 31.02 | 51.91 | | tray | 8.68 | 10.04 | | ashcan | 48.72 | 62.94 | | fan | 57.23 | 75.78 | | pier | 37.83 | 40.76 | | crt screen | 3.56 | 10.1 | | plate | 57.14 | 76.16 | | monitor | 9.63 | 10.98 | | bulletin board | 57.95 | 71.94 | | shower | 1.11 | 3.64 | | radiator | 53.34 | 64.14 | | glass | 17.87 | 19.61 | | clock | 27.8 | 32.71 | | flag | 65.1 | 71.62 | +---------------------+-------+-------+ 2023-11-10 04:57:25,749 - mmseg - INFO - Summary: 2023-11-10 04:57:25,749 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 83.63 | 49.47 | 61.22 | +-------+-------+-------+ 2023-11-10 04:57:25,750 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 04:57:25,750 - mmseg - INFO - Iter(val) [250] aAcc: 0.8363, mIoU: 0.4947, mAcc: 0.6122, IoU.wall: 0.7912, IoU.building: 0.8274, IoU.sky: 0.9404, IoU.floor: 0.8251, IoU.tree: 0.7493, IoU.ceiling: 0.8426, IoU.road: 0.8391, IoU.bed : 0.9048, IoU.windowpane: 0.6275, IoU.grass: 0.6649, IoU.cabinet: 0.6326, IoU.sidewalk: 0.6651, IoU.person: 0.8069, IoU.earth: 0.3494, IoU.door: 0.5686, IoU.table: 0.6472, IoU.mountain: 0.6040, IoU.plant: 0.5302, IoU.curtain: 0.7532, IoU.chair: 0.5810, IoU.car: 0.8415, IoU.water: 0.5083, IoU.painting: 0.7477, IoU.sofa: 0.7350, IoU.shelf: 0.4302, IoU.house: 0.4891, IoU.sea: 0.5119, IoU.mirror: 0.7245, IoU.rug: 0.6898, IoU.field: 0.1784, IoU.armchair: 0.4890, IoU.seat: 0.5871, IoU.fence: 0.4612, IoU.desk: 0.4791, IoU.rock: 0.4743, IoU.wardrobe: 0.5402, IoU.lamp: 0.6469, IoU.bathtub: 0.8041, IoU.railing: 0.4173, IoU.cushion: 0.6036, IoU.base: 0.1932, IoU.box: 0.2976, IoU.column: 0.5092, IoU.signboard: 0.3692, IoU.chest of drawers: 0.3968, IoU.counter: 0.4406, IoU.sand: 0.6244, IoU.sink: 0.7443, IoU.skyscraper: 0.4279, IoU.fireplace: 0.7104, IoU.refrigerator: 0.7852, IoU.grandstand: 0.4544, IoU.path: 0.2021, IoU.stairs: 0.2833, IoU.runway: 0.6691, IoU.case: 0.4834, IoU.pool table: 0.9127, IoU.pillow: 0.5865, IoU.screen door: 0.5388, IoU.stairway: 0.3673, IoU.river: 0.2191, IoU.bridge: 0.3830, IoU.bookcase: 0.3780, IoU.blind: 0.4023, IoU.coffee table: 0.6172, IoU.toilet: 0.8887, IoU.flower: 0.4516, IoU.book: 0.4500, IoU.hill: 0.0557, IoU.bench: 0.4412, IoU.countertop: 0.5883, IoU.stove: 0.8196, IoU.palm: 0.4708, IoU.kitchen island: 0.3073, IoU.computer: 0.7697, IoU.swivel chair: 0.4772, IoU.boat: 0.4659, IoU.bar: 0.6475, IoU.arcade machine: 0.5810, IoU.hovel: 0.2610, IoU.bus: 0.9073, IoU.towel: 0.6602, IoU.light: 0.4708, IoU.truck: 0.4389, IoU.tower: 0.1367, IoU.chandelier: 0.6374, IoU.awning: 0.2686, IoU.streetlight: 0.2371, IoU.booth: 0.5210, IoU.television receiver: 0.7626, IoU.airplane: 0.6037, IoU.dirt track: 0.0225, IoU.apparel: 0.4231, IoU.pole: 0.1568, IoU.land: 0.0489, IoU.bannister: 0.1295, IoU.escalator: 0.4495, IoU.ottoman: 0.5113, IoU.bottle: 0.2531, IoU.buffet: 0.4586, IoU.poster: 0.3266, IoU.stage: 0.1450, IoU.van: 0.3165, IoU.ship: 0.0255, IoU.fountain: 0.0314, IoU.conveyer belt: 0.7690, IoU.canopy: 0.5089, IoU.washer: 0.6835, IoU.plaything: 0.3374, IoU.swimming pool: 0.7543, IoU.stool: 0.4342, IoU.barrel: 0.3660, IoU.basket: 0.3878, IoU.waterfall: 0.5054, IoU.tent: 0.9440, IoU.bag: 0.2518, IoU.minibike: 0.5609, IoU.cradle: 0.7105, IoU.oven: 0.5377, IoU.ball: 0.5156, IoU.food: 0.2548, IoU.step: 0.0478, IoU.tank: 0.2045, IoU.trade name: 0.2570, IoU.microwave: 0.8411, IoU.pot: 0.5257, IoU.animal: 0.7491, IoU.bicycle: 0.5948, IoU.lake: 0.0000, IoU.dishwasher: 0.7149, IoU.screen: 0.5807, IoU.blanket: 0.1158, IoU.sculpture: 0.6633, IoU.hood: 0.6085, IoU.sconce: 0.4961, IoU.vase: 0.3909, IoU.traffic light: 0.3102, IoU.tray: 0.0868, IoU.ashcan: 0.4872, IoU.fan: 0.5723, IoU.pier: 0.3783, IoU.crt screen: 0.0356, IoU.plate: 0.5714, IoU.monitor: 0.0963, IoU.bulletin board: 0.5795, IoU.shower: 0.0111, IoU.radiator: 0.5334, IoU.glass: 0.1787, IoU.clock: 0.2780, IoU.flag: 0.6510, Acc.wall: 0.8859, Acc.building: 0.9265, Acc.sky: 0.9685, Acc.floor: 0.9132, Acc.tree: 0.8864, Acc.ceiling: 0.9220, Acc.road: 0.8907, Acc.bed : 0.9619, Acc.windowpane: 0.7841, Acc.grass: 0.8409, Acc.cabinet: 0.7477, Acc.sidewalk: 0.8234, Acc.person: 0.9360, Acc.earth: 0.4750, Acc.door: 0.7147, Acc.table: 0.7971, Acc.mountain: 0.7741, Acc.plant: 0.6611, Acc.curtain: 0.8517, Acc.chair: 0.7310, Acc.car: 0.9376, Acc.water: 0.7146, Acc.painting: 0.8645, Acc.sofa: 0.9203, Acc.shelf: 0.6663, Acc.house: 0.6560, Acc.sea: 0.7514, Acc.mirror: 0.8137, Acc.rug: 0.7917, Acc.field: 0.3023, Acc.armchair: 0.5815, Acc.seat: 0.7656, Acc.fence: 0.5577, Acc.desk: 0.6066, Acc.rock: 0.5857, Acc.wardrobe: 0.7437, Acc.lamp: 0.7639, Acc.bathtub: 0.8731, Acc.railing: 0.6026, Acc.cushion: 0.7964, Acc.base: 0.2309, Acc.box: 0.3621, Acc.column: 0.6440, Acc.signboard: 0.4930, Acc.chest of drawers: 0.6182, Acc.counter: 0.5644, Acc.sand: 0.8246, Acc.sink: 0.7996, Acc.skyscraper: 0.5268, Acc.fireplace: 0.9052, Acc.refrigerator: 0.8718, Acc.grandstand: 0.8785, Acc.path: 0.2948, Acc.stairs: 0.3487, Acc.runway: 0.9282, Acc.case: 0.8827, Acc.pool table: 0.9680, Acc.pillow: 0.6857, Acc.screen door: 0.6725, Acc.stairway: 0.5029, Acc.river: 0.3290, Acc.bridge: 0.4267, Acc.bookcase: 0.5445, Acc.blind: 0.4695, Acc.coffee table: 0.8735, Acc.toilet: 0.9324, Acc.flower: 0.6427, Acc.book: 0.6272, Acc.hill: 0.0815, Acc.bench: 0.4989, Acc.countertop: 0.7410, Acc.stove: 0.8863, Acc.palm: 0.6964, Acc.kitchen island: 0.4185, Acc.computer: 0.8773, Acc.swivel chair: 0.7543, Acc.boat: 0.8525, Acc.bar: 0.6951, Acc.arcade machine: 0.6006, Acc.hovel: 0.2847, Acc.bus: 0.9572, Acc.towel: 0.8210, Acc.light: 0.5775, Acc.truck: 0.6008, Acc.tower: 0.2421, Acc.chandelier: 0.8439, Acc.awning: 0.3588, Acc.streetlight: 0.3337, Acc.booth: 0.7476, Acc.television receiver: 0.8365, Acc.airplane: 0.7123, Acc.dirt track: 0.0584, Acc.apparel: 0.5988, Acc.pole: 0.1940, Acc.land: 0.0951, Acc.bannister: 0.2170, Acc.escalator: 0.5430, Acc.ottoman: 0.6954, Acc.bottle: 0.3205, Acc.buffet: 0.5165, Acc.poster: 0.4043, Acc.stage: 0.1803, Acc.van: 0.3633, Acc.ship: 0.0255, Acc.fountain: 0.0316, Acc.conveyer belt: 0.9234, Acc.canopy: 0.5748, Acc.washer: 0.7048, Acc.plaything: 0.6409, Acc.swimming pool: 0.8559, Acc.stool: 0.5941, Acc.barrel: 0.3689, Acc.basket: 0.5954, Acc.waterfall: 0.6245, Acc.tent: 0.9839, Acc.bag: 0.2971, Acc.minibike: 0.6301, Acc.cradle: 0.9651, Acc.oven: 0.6300, Acc.ball: 0.7372, Acc.food: 0.2857, Acc.step: 0.0541, Acc.tank: 0.2462, Acc.trade name: 0.3017, Acc.microwave: 0.9329, Acc.pot: 0.6035, Acc.animal: 0.7887, Acc.bicycle: 0.7605, Acc.lake: 0.0000, Acc.dishwasher: 0.7412, Acc.screen: 0.9162, Acc.blanket: 0.1256, Acc.sculpture: 0.7567, Acc.hood: 0.6915, Acc.sconce: 0.6274, Acc.vase: 0.5468, Acc.traffic light: 0.5191, Acc.tray: 0.1004, Acc.ashcan: 0.6294, Acc.fan: 0.7578, Acc.pier: 0.4076, Acc.crt screen: 0.1010, Acc.plate: 0.7616, Acc.monitor: 0.1098, Acc.bulletin board: 0.7194, Acc.shower: 0.0364, Acc.radiator: 0.6414, Acc.glass: 0.1961, Acc.clock: 0.3271, Acc.flag: 0.7162 2023-11-10 04:58:29,049 - mmseg - INFO - Iter [6050/10000] lr: 1.280e-06, eta: 1:28:42, time: 2.350, data_time: 1.138, memory: 38534, decode.loss_ce: 0.1896, decode.acc_seg: 92.4768, loss: 0.1896 2023-11-10 04:59:29,959 - mmseg - INFO - Iter [6100/10000] lr: 1.264e-06, eta: 1:27:30, time: 1.218, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1911, decode.acc_seg: 92.3165, loss: 0.1911 2023-11-10 05:00:30,929 - mmseg - INFO - Iter [6150/10000] lr: 1.248e-06, eta: 1:26:19, time: 1.219, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1981, decode.acc_seg: 92.1581, loss: 0.1981 2023-11-10 05:01:34,135 - mmseg - INFO - Iter [6200/10000] lr: 1.231e-06, eta: 1:25:09, time: 1.264, data_time: 0.051, memory: 38534, decode.loss_ce: 0.1968, decode.acc_seg: 92.3495, loss: 0.1968 2023-11-10 05:02:35,031 - mmseg - INFO - Iter [6250/10000] lr: 1.215e-06, eta: 1:23:58, time: 1.218, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1922, decode.acc_seg: 92.2078, loss: 0.1922 2023-11-10 05:03:35,965 - mmseg - INFO - Iter [6300/10000] lr: 1.199e-06, eta: 1:22:47, time: 1.219, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1998, decode.acc_seg: 92.0529, loss: 0.1998 2023-11-10 05:04:39,063 - mmseg - INFO - Iter [6350/10000] lr: 1.183e-06, eta: 1:21:38, time: 1.262, data_time: 0.051, memory: 38534, decode.loss_ce: 0.1855, decode.acc_seg: 92.7780, loss: 0.1855 2023-11-10 05:05:39,964 - mmseg - INFO - Iter [6400/10000] lr: 1.167e-06, eta: 1:20:27, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1882, decode.acc_seg: 92.2979, loss: 0.1882 2023-11-10 05:06:40,842 - mmseg - INFO - Iter [6450/10000] lr: 1.150e-06, eta: 1:19:17, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1851, decode.acc_seg: 92.5705, loss: 0.1851 2023-11-10 05:07:43,989 - mmseg - INFO - Iter [6500/10000] lr: 1.134e-06, eta: 1:18:08, time: 1.263, data_time: 0.053, memory: 38534, decode.loss_ce: 0.1849, decode.acc_seg: 92.4365, loss: 0.1849 2023-11-10 05:08:44,882 - mmseg - INFO - Iter [6550/10000] lr: 1.118e-06, eta: 1:16:58, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1928, decode.acc_seg: 92.3320, loss: 0.1928 2023-11-10 05:09:45,745 - mmseg - INFO - Iter [6600/10000] lr: 1.102e-06, eta: 1:15:48, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1845, decode.acc_seg: 92.4494, loss: 0.1845 2023-11-10 05:10:48,920 - mmseg - INFO - Iter [6650/10000] lr: 1.086e-06, eta: 1:14:39, time: 1.263, data_time: 0.052, memory: 38534, decode.loss_ce: 0.1751, decode.acc_seg: 92.8424, loss: 0.1751 2023-11-10 05:11:49,879 - mmseg - INFO - Iter [6700/10000] lr: 1.069e-06, eta: 1:13:29, time: 1.219, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1755, decode.acc_seg: 92.7930, loss: 0.1755 2023-11-10 05:12:50,759 - mmseg - INFO - Iter [6750/10000] lr: 1.053e-06, eta: 1:12:19, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1807, decode.acc_seg: 92.8187, loss: 0.1807 2023-11-10 05:13:54,032 - mmseg - INFO - Iter [6800/10000] lr: 1.037e-06, eta: 1:11:11, time: 1.265, data_time: 0.051, memory: 38534, decode.loss_ce: 0.1851, decode.acc_seg: 92.3347, loss: 0.1851 2023-11-10 05:14:54,929 - mmseg - INFO - Iter [6850/10000] lr: 1.021e-06, eta: 1:10:02, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1777, decode.acc_seg: 92.7530, loss: 0.1777 2023-11-10 05:15:55,809 - mmseg - INFO - Iter [6900/10000] lr: 1.005e-06, eta: 1:08:52, time: 1.218, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1808, decode.acc_seg: 92.6564, loss: 0.1808 2023-11-10 05:16:56,707 - mmseg - INFO - Iter [6950/10000] lr: 9.885e-07, eta: 1:07:43, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1843, decode.acc_seg: 92.7764, loss: 0.1843 2023-11-10 05:17:59,859 - mmseg - INFO - Saving checkpoint at 7000 iterations 2023-11-10 05:18:52,279 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 05:18:52,279 - mmseg - INFO - Iter [7000/10000] lr: 9.723e-07, eta: 1:06:57, time: 2.311, data_time: 0.053, memory: 38534, decode.loss_ce: 0.1714, decode.acc_seg: 93.0453, loss: 0.1714 2023-11-10 05:19:46,597 - mmseg - INFO - per class results: 2023-11-10 05:19:46,602 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 79.01 | 87.58 | | building | 82.08 | 93.41 | | sky | 93.96 | 96.81 | | floor | 82.81 | 91.44 | | tree | 74.69 | 88.06 | | ceiling | 84.31 | 93.45 | | road | 84.12 | 89.2 | | bed | 90.73 | 96.13 | | windowpane | 62.76 | 80.4 | | grass | 67.99 | 85.86 | | cabinet | 63.84 | 73.3 | | sidewalk | 66.2 | 84.63 | | person | 80.34 | 93.41 | | earth | 32.94 | 42.67 | | door | 57.26 | 74.67 | | table | 65.23 | 80.99 | | mountain | 59.86 | 77.62 | | plant | 52.24 | 67.07 | | curtain | 74.48 | 83.82 | | chair | 58.2 | 76.49 | | car | 83.83 | 94.02 | | water | 54.77 | 73.92 | | painting | 75.11 | 87.23 | | sofa | 76.15 | 87.14 | | shelf | 43.69 | 67.25 | | house | 44.91 | 56.12 | | sea | 60.8 | 82.12 | | mirror | 73.45 | 82.79 | | rug | 67.28 | 75.63 | | field | 23.32 | 39.09 | | armchair | 55.1 | 69.02 | | seat | 58.41 | 74.57 | | fence | 46.74 | 62.48 | | desk | 47.64 | 62.18 | | rock | 46.07 | 57.0 | | wardrobe | 53.23 | 70.42 | | lamp | 66.13 | 80.04 | | bathtub | 85.11 | 90.61 | | railing | 40.22 | 53.95 | | cushion | 61.54 | 77.25 | | base | 22.28 | 28.45 | | box | 31.06 | 37.73 | | column | 48.35 | 58.15 | | signboard | 37.26 | 51.12 | | chest of drawers | 40.92 | 59.85 | | counter | 44.98 | 59.74 | | sand | 60.18 | 82.17 | | sink | 75.96 | 83.44 | | skyscraper | 43.75 | 52.2 | | fireplace | 73.15 | 91.25 | | refrigerator | 77.89 | 87.92 | | grandstand | 46.73 | 86.96 | | path | 22.11 | 31.77 | | stairs | 28.59 | 35.42 | | runway | 65.48 | 93.24 | | case | 49.21 | 84.83 | | pool table | 90.98 | 97.85 | | pillow | 59.65 | 72.54 | | screen door | 59.96 | 73.36 | | stairway | 37.28 | 48.42 | | river | 20.54 | 32.35 | | bridge | 40.0 | 44.23 | | bookcase | 35.5 | 48.61 | | blind | 40.45 | 45.78 | | coffee table | 61.85 | 82.83 | | toilet | 88.81 | 93.98 | | flower | 41.65 | 61.07 | | book | 45.38 | 62.56 | | hill | 4.85 | 6.89 | | bench | 47.13 | 53.64 | | countertop | 57.26 | 75.85 | | stove | 82.28 | 88.39 | | palm | 48.43 | 67.85 | | kitchen island | 44.4 | 62.31 | | computer | 77.1 | 89.17 | | swivel chair | 47.62 | 75.91 | | boat | 39.07 | 73.78 | | bar | 65.49 | 71.45 | | arcade machine | 62.22 | 64.51 | | hovel | 23.7 | 25.56 | | bus | 90.34 | 95.34 | | towel | 67.11 | 87.31 | | light | 47.02 | 56.59 | | truck | 45.97 | 63.02 | | tower | 18.9 | 32.96 | | chandelier | 64.65 | 78.6 | | awning | 26.95 | 36.53 | | streetlight | 24.51 | 33.35 | | booth | 58.04 | 68.41 | | television receiver | 73.89 | 84.71 | | airplane | 62.32 | 72.23 | | dirt track | 4.56 | 4.8 | | apparel | 45.32 | 70.25 | | pole | 20.7 | 28.83 | | land | 4.39 | 5.73 | | bannister | 11.25 | 18.21 | | escalator | 49.08 | 60.44 | | ottoman | 49.18 | 67.25 | | bottle | 23.96 | 31.45 | | buffet | 35.96 | 39.7 | | poster | 32.62 | 41.63 | | stage | 19.2 | 24.24 | | van | 30.39 | 34.8 | | ship | 0.79 | 0.86 | | fountain | 1.59 | 1.59 | | conveyer belt | 76.05 | 95.46 | | canopy | 53.95 | 57.99 | | washer | 67.99 | 69.78 | | plaything | 36.39 | 57.43 | | swimming pool | 72.93 | 86.58 | | stool | 43.03 | 62.58 | | barrel | 53.76 | 55.19 | | basket | 41.1 | 59.71 | | waterfall | 48.23 | 62.63 | | tent | 94.07 | 97.72 | | bag | 22.37 | 25.31 | | minibike | 56.54 | 65.18 | | cradle | 67.05 | 97.78 | | oven | 53.94 | 64.61 | | ball | 48.32 | 74.49 | | food | 24.58 | 26.46 | | step | 6.75 | 7.81 | | tank | 32.99 | 39.79 | | trade name | 17.51 | 19.66 | | microwave | 84.16 | 93.42 | | pot | 52.58 | 58.67 | | animal | 73.85 | 76.41 | | bicycle | 58.2 | 74.21 | | lake | 0.0 | 0.0 | | dishwasher | 72.77 | 79.93 | | screen | 55.1 | 93.04 | | blanket | 16.94 | 18.84 | | sculpture | 62.22 | 71.55 | | hood | 59.83 | 67.7 | | sconce | 49.44 | 64.07 | | vase | 40.24 | 56.72 | | traffic light | 30.98 | 57.5 | | tray | 8.32 | 9.97 | | ashcan | 50.47 | 63.56 | | fan | 59.54 | 77.04 | | pier | 37.23 | 40.32 | | crt screen | 3.65 | 9.93 | | plate | 57.29 | 75.8 | | monitor | 9.28 | 10.22 | | bulletin board | 51.15 | 56.98 | | shower | 3.12 | 10.56 | | radiator | 53.65 | 64.1 | | glass | 19.76 | 22.28 | | clock | 27.76 | 32.91 | | flag | 66.26 | 71.18 | +---------------------+-------+-------+ 2023-11-10 05:19:46,602 - mmseg - INFO - Summary: 2023-11-10 05:19:46,602 - mmseg - INFO - +-------+-------+-------+ | aAcc | mIoU | mAcc | +-------+-------+-------+ | 83.75 | 49.97 | 61.77 | +-------+-------+-------+ 2023-11-10 05:19:46,603 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 05:19:46,603 - mmseg - INFO - Iter(val) [250] aAcc: 0.8375, mIoU: 0.4997, mAcc: 0.6177, IoU.wall: 0.7901, IoU.building: 0.8208, IoU.sky: 0.9396, IoU.floor: 0.8281, IoU.tree: 0.7469, IoU.ceiling: 0.8431, IoU.road: 0.8412, IoU.bed : 0.9073, IoU.windowpane: 0.6276, IoU.grass: 0.6799, IoU.cabinet: 0.6384, IoU.sidewalk: 0.6620, IoU.person: 0.8034, IoU.earth: 0.3294, IoU.door: 0.5726, IoU.table: 0.6523, IoU.mountain: 0.5986, IoU.plant: 0.5224, IoU.curtain: 0.7448, IoU.chair: 0.5820, IoU.car: 0.8383, IoU.water: 0.5477, IoU.painting: 0.7511, IoU.sofa: 0.7615, IoU.shelf: 0.4369, IoU.house: 0.4491, IoU.sea: 0.6080, IoU.mirror: 0.7345, IoU.rug: 0.6728, IoU.field: 0.2332, IoU.armchair: 0.5510, IoU.seat: 0.5841, IoU.fence: 0.4674, IoU.desk: 0.4764, IoU.rock: 0.4607, IoU.wardrobe: 0.5323, IoU.lamp: 0.6613, IoU.bathtub: 0.8511, IoU.railing: 0.4022, IoU.cushion: 0.6154, IoU.base: 0.2228, IoU.box: 0.3106, IoU.column: 0.4835, IoU.signboard: 0.3726, IoU.chest of drawers: 0.4092, IoU.counter: 0.4498, IoU.sand: 0.6018, IoU.sink: 0.7596, IoU.skyscraper: 0.4375, IoU.fireplace: 0.7315, IoU.refrigerator: 0.7789, IoU.grandstand: 0.4673, IoU.path: 0.2211, IoU.stairs: 0.2859, IoU.runway: 0.6548, IoU.case: 0.4921, IoU.pool table: 0.9098, IoU.pillow: 0.5965, IoU.screen door: 0.5996, IoU.stairway: 0.3728, IoU.river: 0.2054, IoU.bridge: 0.4000, IoU.bookcase: 0.3550, IoU.blind: 0.4045, IoU.coffee table: 0.6185, IoU.toilet: 0.8881, IoU.flower: 0.4165, IoU.book: 0.4538, IoU.hill: 0.0485, IoU.bench: 0.4713, IoU.countertop: 0.5726, IoU.stove: 0.8228, IoU.palm: 0.4843, IoU.kitchen island: 0.4440, IoU.computer: 0.7710, IoU.swivel chair: 0.4762, IoU.boat: 0.3907, IoU.bar: 0.6549, IoU.arcade machine: 0.6222, IoU.hovel: 0.2370, IoU.bus: 0.9034, IoU.towel: 0.6711, IoU.light: 0.4702, IoU.truck: 0.4597, IoU.tower: 0.1890, IoU.chandelier: 0.6465, IoU.awning: 0.2695, IoU.streetlight: 0.2451, IoU.booth: 0.5804, IoU.television receiver: 0.7389, IoU.airplane: 0.6232, IoU.dirt track: 0.0456, IoU.apparel: 0.4532, IoU.pole: 0.2070, IoU.land: 0.0439, IoU.bannister: 0.1125, IoU.escalator: 0.4908, IoU.ottoman: 0.4918, IoU.bottle: 0.2396, IoU.buffet: 0.3596, IoU.poster: 0.3262, IoU.stage: 0.1920, IoU.van: 0.3039, IoU.ship: 0.0079, IoU.fountain: 0.0159, IoU.conveyer belt: 0.7605, IoU.canopy: 0.5395, IoU.washer: 0.6799, IoU.plaything: 0.3639, IoU.swimming pool: 0.7293, IoU.stool: 0.4303, IoU.barrel: 0.5376, IoU.basket: 0.4110, IoU.waterfall: 0.4823, IoU.tent: 0.9407, IoU.bag: 0.2237, IoU.minibike: 0.5654, IoU.cradle: 0.6705, IoU.oven: 0.5394, IoU.ball: 0.4832, IoU.food: 0.2458, IoU.step: 0.0675, IoU.tank: 0.3299, IoU.trade name: 0.1751, IoU.microwave: 0.8416, IoU.pot: 0.5258, IoU.animal: 0.7385, IoU.bicycle: 0.5820, IoU.lake: 0.0000, IoU.dishwasher: 0.7277, IoU.screen: 0.5510, IoU.blanket: 0.1694, IoU.sculpture: 0.6222, IoU.hood: 0.5983, IoU.sconce: 0.4944, IoU.vase: 0.4024, IoU.traffic light: 0.3098, IoU.tray: 0.0832, IoU.ashcan: 0.5047, IoU.fan: 0.5954, IoU.pier: 0.3723, IoU.crt screen: 0.0365, IoU.plate: 0.5729, IoU.monitor: 0.0928, IoU.bulletin board: 0.5115, IoU.shower: 0.0312, IoU.radiator: 0.5365, IoU.glass: 0.1976, IoU.clock: 0.2776, IoU.flag: 0.6626, Acc.wall: 0.8758, Acc.building: 0.9341, Acc.sky: 0.9681, Acc.floor: 0.9144, Acc.tree: 0.8806, Acc.ceiling: 0.9345, Acc.road: 0.8920, Acc.bed : 0.9613, Acc.windowpane: 0.8040, Acc.grass: 0.8586, Acc.cabinet: 0.7330, Acc.sidewalk: 0.8463, Acc.person: 0.9341, Acc.earth: 0.4267, Acc.door: 0.7467, Acc.table: 0.8099, Acc.mountain: 0.7762, Acc.plant: 0.6707, Acc.curtain: 0.8382, Acc.chair: 0.7649, Acc.car: 0.9402, Acc.water: 0.7392, Acc.painting: 0.8723, Acc.sofa: 0.8714, Acc.shelf: 0.6725, Acc.house: 0.5612, Acc.sea: 0.8212, Acc.mirror: 0.8279, Acc.rug: 0.7563, Acc.field: 0.3909, Acc.armchair: 0.6902, Acc.seat: 0.7457, Acc.fence: 0.6248, Acc.desk: 0.6218, Acc.rock: 0.5700, Acc.wardrobe: 0.7042, Acc.lamp: 0.8004, Acc.bathtub: 0.9061, Acc.railing: 0.5395, Acc.cushion: 0.7725, Acc.base: 0.2845, Acc.box: 0.3773, Acc.column: 0.5815, Acc.signboard: 0.5112, Acc.chest of drawers: 0.5985, Acc.counter: 0.5974, Acc.sand: 0.8217, Acc.sink: 0.8344, Acc.skyscraper: 0.5220, Acc.fireplace: 0.9125, Acc.refrigerator: 0.8792, Acc.grandstand: 0.8696, Acc.path: 0.3177, Acc.stairs: 0.3542, Acc.runway: 0.9324, Acc.case: 0.8483, Acc.pool table: 0.9785, Acc.pillow: 0.7254, Acc.screen door: 0.7336, Acc.stairway: 0.4842, Acc.river: 0.3235, Acc.bridge: 0.4423, Acc.bookcase: 0.4861, Acc.blind: 0.4578, Acc.coffee table: 0.8283, Acc.toilet: 0.9398, Acc.flower: 0.6107, Acc.book: 0.6256, Acc.hill: 0.0689, Acc.bench: 0.5364, Acc.countertop: 0.7585, Acc.stove: 0.8839, Acc.palm: 0.6785, Acc.kitchen island: 0.6231, Acc.computer: 0.8917, Acc.swivel chair: 0.7591, Acc.boat: 0.7378, Acc.bar: 0.7145, Acc.arcade machine: 0.6451, Acc.hovel: 0.2556, Acc.bus: 0.9534, Acc.towel: 0.8731, Acc.light: 0.5659, Acc.truck: 0.6302, Acc.tower: 0.3296, Acc.chandelier: 0.7860, Acc.awning: 0.3653, Acc.streetlight: 0.3335, Acc.booth: 0.6841, Acc.television receiver: 0.8471, Acc.airplane: 0.7223, Acc.dirt track: 0.0480, Acc.apparel: 0.7025, Acc.pole: 0.2883, Acc.land: 0.0573, Acc.bannister: 0.1821, Acc.escalator: 0.6044, Acc.ottoman: 0.6725, Acc.bottle: 0.3145, Acc.buffet: 0.3970, Acc.poster: 0.4163, Acc.stage: 0.2424, Acc.van: 0.3480, Acc.ship: 0.0086, Acc.fountain: 0.0159, Acc.conveyer belt: 0.9546, Acc.canopy: 0.5799, Acc.washer: 0.6978, Acc.plaything: 0.5743, Acc.swimming pool: 0.8658, Acc.stool: 0.6258, Acc.barrel: 0.5519, Acc.basket: 0.5971, Acc.waterfall: 0.6263, Acc.tent: 0.9772, Acc.bag: 0.2531, Acc.minibike: 0.6518, Acc.cradle: 0.9778, Acc.oven: 0.6461, Acc.ball: 0.7449, Acc.food: 0.2646, Acc.step: 0.0781, Acc.tank: 0.3979, Acc.trade name: 0.1966, Acc.microwave: 0.9342, Acc.pot: 0.5867, Acc.animal: 0.7641, Acc.bicycle: 0.7421, Acc.lake: 0.0000, Acc.dishwasher: 0.7993, Acc.screen: 0.9304, Acc.blanket: 0.1884, Acc.sculpture: 0.7155, Acc.hood: 0.6770, Acc.sconce: 0.6407, Acc.vase: 0.5672, Acc.traffic light: 0.5750, Acc.tray: 0.0997, Acc.ashcan: 0.6356, Acc.fan: 0.7704, Acc.pier: 0.4032, Acc.crt screen: 0.0993, Acc.plate: 0.7580, Acc.monitor: 0.1022, Acc.bulletin board: 0.5698, Acc.shower: 0.1056, Acc.radiator: 0.6410, Acc.glass: 0.2228, Acc.clock: 0.3291, Acc.flag: 0.7118 2023-11-10 05:20:47,500 - mmseg - INFO - Iter [7050/10000] lr: 9.561e-07, eta: 1:06:11, time: 2.304, data_time: 1.095, memory: 38534, decode.loss_ce: 0.1829, decode.acc_seg: 92.6099, loss: 0.1829 2023-11-10 05:21:48,339 - mmseg - INFO - Iter [7100/10000] lr: 9.399e-07, eta: 1:05:01, time: 1.217, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1804, decode.acc_seg: 92.6706, loss: 0.1804 2023-11-10 05:22:51,439 - mmseg - INFO - Iter [7150/10000] lr: 9.237e-07, eta: 1:03:52, time: 1.262, data_time: 0.051, memory: 38534, decode.loss_ce: 0.1773, decode.acc_seg: 92.6436, loss: 0.1773 2023-11-10 05:23:52,216 - mmseg - INFO - Iter [7200/10000] lr: 9.075e-07, eta: 1:02:42, time: 1.216, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1706, decode.acc_seg: 93.1792, loss: 0.1706 2023-11-10 05:24:53,047 - mmseg - INFO - Iter [7250/10000] lr: 8.913e-07, eta: 1:01:32, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1726, decode.acc_seg: 93.0093, loss: 0.1726 2023-11-10 05:25:56,150 - mmseg - INFO - Iter [7300/10000] lr: 8.751e-07, eta: 1:00:24, time: 1.262, data_time: 0.052, memory: 38534, decode.loss_ce: 0.1681, decode.acc_seg: 93.0318, loss: 0.1681 2023-11-10 05:26:56,900 - mmseg - INFO - Iter [7350/10000] lr: 8.589e-07, eta: 0:59:14, time: 1.215, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1727, decode.acc_seg: 92.9839, loss: 0.1727 2023-11-10 05:27:57,665 - mmseg - INFO - Iter [7400/10000] lr: 8.427e-07, eta: 0:58:05, time: 1.215, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1785, decode.acc_seg: 92.7248, loss: 0.1785 2023-11-10 05:29:00,785 - mmseg - INFO - Iter [7450/10000] lr: 8.265e-07, eta: 0:56:57, time: 1.262, data_time: 0.051, memory: 38534, decode.loss_ce: 0.1673, decode.acc_seg: 93.0903, loss: 0.1673 2023-11-10 05:30:01,606 - mmseg - INFO - Iter [7500/10000] lr: 8.103e-07, eta: 0:55:48, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1710, decode.acc_seg: 93.0893, loss: 0.1710 2023-11-10 05:31:02,374 - mmseg - INFO - Iter [7550/10000] lr: 7.941e-07, eta: 0:54:39, time: 1.215, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1695, decode.acc_seg: 93.0052, loss: 0.1695 2023-11-10 05:32:05,498 - mmseg - INFO - Iter [7600/10000] lr: 7.779e-07, eta: 0:53:31, time: 1.262, data_time: 0.052, memory: 38534, decode.loss_ce: 0.1654, decode.acc_seg: 93.2513, loss: 0.1654 2023-11-10 05:33:06,351 - mmseg - INFO - Iter [7650/10000] lr: 7.617e-07, eta: 0:52:22, time: 1.217, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1658, decode.acc_seg: 93.1469, loss: 0.1658 2023-11-10 05:34:07,155 - mmseg - INFO - Iter [7700/10000] lr: 7.455e-07, eta: 0:51:13, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1696, decode.acc_seg: 93.0860, loss: 0.1696 2023-11-10 05:35:10,379 - mmseg - INFO - Iter [7750/10000] lr: 7.293e-07, eta: 0:50:05, time: 1.264, data_time: 0.052, memory: 38534, decode.loss_ce: 0.1688, decode.acc_seg: 93.1093, loss: 0.1688 2023-11-10 05:36:11,158 - mmseg - INFO - Iter [7800/10000] lr: 7.131e-07, eta: 0:48:57, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1657, decode.acc_seg: 93.3749, loss: 0.1657 2023-11-10 05:37:11,955 - mmseg - INFO - Iter [7850/10000] lr: 6.969e-07, eta: 0:47:48, time: 1.216, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1643, decode.acc_seg: 93.2431, loss: 0.1643 2023-11-10 05:38:12,766 - mmseg - INFO - Iter [7900/10000] lr: 6.807e-07, eta: 0:46:40, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1700, decode.acc_seg: 93.0921, loss: 0.1700 2023-11-10 05:39:15,942 - mmseg - INFO - Iter [7950/10000] lr: 6.645e-07, eta: 0:45:33, time: 1.264, data_time: 0.054, memory: 38534, decode.loss_ce: 0.1718, decode.acc_seg: 92.9246, loss: 0.1718 2023-11-10 05:40:16,681 - mmseg - INFO - Saving checkpoint at 8000 iterations 2023-11-10 05:41:13,055 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 05:41:13,056 - mmseg - INFO - Iter [8000/10000] lr: 6.483e-07, eta: 0:44:39, time: 2.342, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1668, decode.acc_seg: 93.2303, loss: 0.1668 2023-11-10 05:42:06,853 - mmseg - INFO - per class results: 2023-11-10 05:42:06,858 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 78.88 | 87.24 | | building | 82.48 | 92.68 | | sky | 93.89 | 97.35 | | floor | 83.09 | 90.58 | | tree | 74.7 | 89.58 | | ceiling | 84.19 | 93.04 | | road | 83.67 | 88.97 | | bed | 90.28 | 96.69 | | windowpane | 62.3 | 80.65 | | grass | 67.09 | 84.25 | | cabinet | 64.48 | 74.01 | | sidewalk | 66.26 | 84.03 | | person | 81.15 | 92.35 | | earth | 33.36 | 43.94 | | door | 56.19 | 71.85 | | table | 65.86 | 79.83 | | mountain | 59.3 | 76.81 | | plant | 51.68 | 65.51 | | curtain | 74.15 | 85.02 | | chair | 58.11 | 75.15 | | car | 83.97 | 94.21 | | water | 49.55 | 68.42 | | painting | 74.13 | 87.08 | | sofa | 77.64 | 89.32 | | shelf | 42.31 | 66.15 | | house | 42.88 | 55.53 | | sea | 50.87 | 76.89 | | mirror | 72.91 | 82.33 | | rug | 67.73 | 76.52 | | field | 19.36 | 34.02 | | armchair | 56.71 | 71.96 | | seat | 59.11 | 75.34 | | fence | 47.64 | 65.91 | | desk | 49.43 | 65.45 | | rock | 44.77 | 59.62 | | wardrobe | 53.5 | 72.66 | | lamp | 65.89 | 80.06 | | bathtub | 85.4 | 90.01 | | railing | 40.48 | 53.89 | | cushion | 62.36 | 76.68 | | base | 18.28 | 23.39 | | box | 33.17 | 42.39 | | column | 50.21 | 64.6 | | signboard | 37.99 | 53.89 | | chest of drawers | 40.54 | 63.55 | | counter | 49.77 | 64.7 | | sand | 60.98 | 78.47 | | sink | 75.69 | 83.71 | | skyscraper | 41.68 | 48.21 | | fireplace | 72.98 | 92.18 | | refrigerator | 77.38 | 89.24 | | grandstand | 47.32 | 86.28 | | path | 17.9 | 25.24 | | stairs | 27.21 | 35.85 | | runway | 67.66 | 89.92 | | case | 53.54 | 86.01 | | pool table | 91.39 | 98.24 | | pillow | 56.87 | 66.25 | | screen door | 54.88 | 67.59 | | stairway | 36.37 | 49.55 | | river | 21.57 | 33.19 | | bridge | 44.48 | 48.98 | | bookcase | 35.83 | 50.79 | | blind | 36.33 | 41.15 | | coffee table | 62.25 | 84.61 | | toilet | 88.95 | 94.56 | | flower | 40.81 | 58.91 | | book | 46.72 | 70.34 | | hill | 4.73 | 6.45 | | bench | 48.38 | 54.98 | | countertop | 57.23 | 74.32 | | stove | 82.75 | 90.47 | | palm | 45.89 | 63.75 | | kitchen island | 40.72 | 61.79 | | computer | 77.39 | 89.17 | | swivel chair | 46.32 | 76.39 | | boat | 42.17 | 80.03 | | bar | 69.05 | 77.37 | | arcade machine | 70.83 | 73.09 | | hovel | 23.41 | 25.18 | | bus | 90.75 | 95.61 | | towel | 68.17 | 86.64 | | light | 48.79 | 61.33 | | truck | 44.07 | 60.53 | | tower | 17.49 | 31.5 | | chandelier | 65.13 | 84.2 | | awning | 29.84 | 42.77 | | streetlight | 23.76 | 30.28 | | booth | 48.94 | 60.83 | | television receiver | 75.02 | 86.31 | | airplane | 61.51 | 72.13 | | dirt track | 1.11 | 2.3 | | apparel | 48.21 | 73.39 | | pole | 22.13 | 31.57 | | land | 4.84 | 7.64 | | bannister | 12.46 | 22.05 | | escalator | 51.42 | 63.21 | | ottoman | 49.95 | 65.86 | | bottle | 26.02 | 35.05 | | buffet | 46.56 | 55.76 | | poster | 32.25 | 43.16 | | stage | 20.88 | 27.54 | | van | 31.27 | 34.96 | | ship | 3.38 | 3.62 | | fountain | 2.02 | 2.02 | | conveyer belt | 78.99 | 92.93 | | canopy | 50.21 | 54.21 | | washer | 70.55 | 72.5 | | plaything | 38.48 | 53.91 | | swimming pool | 74.34 | 86.22 | | stool | 42.66 | 59.85 | | barrel | 48.4 | 50.32 | | basket | 39.19 | 59.01 | | waterfall | 46.57 | 57.74 | | tent | 94.11 | 97.65 | | bag | 25.27 | 31.7 | | minibike | 66.36 | 79.08 | | cradle | 68.47 | 97.98 | | oven | 53.13 | 63.93 | | ball | 52.11 | 74.3 | | food | 29.21 | 32.3 | | step | 6.89 | 8.73 | | tank | 26.18 | 31.2 | | trade name | 26.39 | 32.94 | | microwave | 84.38 | 94.0 | | pot | 53.62 | 61.82 | | animal | 76.58 | 79.68 | | bicycle | 58.91 | 79.96 | | lake | 0.0 | 0.0 | | dishwasher | 75.17 | 80.12 | | screen | 53.13 | 93.25 | | blanket | 15.54 | 17.0 | | sculpture | 62.75 | 70.78 | | hood | 60.73 | 70.76 | | sconce | 49.91 | 70.23 | | vase | 39.77 | 56.68 | | traffic light | 31.63 | 57.02 | | tray | 10.53 | 13.91 | | ashcan | 48.73 | 66.48 | | fan | 58.81 | 79.36 | | pier | 37.38 | 40.56 | | crt screen | 4.25 | 12.22 | | plate | 56.92 | 74.56 | | monitor | 10.7 | 12.38 | | bulletin board | 57.02 | 67.84 | | shower | 3.02 | 8.41 | | radiator | 54.09 | 63.13 | | glass | 20.08 | 22.45 | | clock | 28.73 | 34.78 | | flag | 67.67 | 75.18 | +---------------------+-------+-------+ 2023-11-10 05:42:06,858 - mmseg - INFO - Summary: 2023-11-10 05:42:06,858 - mmseg - INFO - +-------+-------+------+ | aAcc | mIoU | mAcc | +-------+-------+------+ | 83.59 | 50.26 | 62.5 | +-------+-------+------+ 2023-11-10 05:42:06,859 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 05:42:06,860 - mmseg - INFO - Iter(val) [250] aAcc: 0.8359, mIoU: 0.5026, mAcc: 0.6250, IoU.wall: 0.7888, IoU.building: 0.8248, IoU.sky: 0.9389, IoU.floor: 0.8309, IoU.tree: 0.7470, IoU.ceiling: 0.8419, IoU.road: 0.8367, IoU.bed : 0.9028, IoU.windowpane: 0.6230, IoU.grass: 0.6709, IoU.cabinet: 0.6448, IoU.sidewalk: 0.6626, IoU.person: 0.8115, IoU.earth: 0.3336, IoU.door: 0.5619, IoU.table: 0.6586, IoU.mountain: 0.5930, IoU.plant: 0.5168, IoU.curtain: 0.7415, IoU.chair: 0.5811, IoU.car: 0.8397, IoU.water: 0.4955, IoU.painting: 0.7413, IoU.sofa: 0.7764, IoU.shelf: 0.4231, IoU.house: 0.4288, IoU.sea: 0.5087, IoU.mirror: 0.7291, IoU.rug: 0.6773, IoU.field: 0.1936, IoU.armchair: 0.5671, IoU.seat: 0.5911, IoU.fence: 0.4764, IoU.desk: 0.4943, IoU.rock: 0.4477, IoU.wardrobe: 0.5350, IoU.lamp: 0.6589, IoU.bathtub: 0.8540, IoU.railing: 0.4048, IoU.cushion: 0.6236, IoU.base: 0.1828, IoU.box: 0.3317, IoU.column: 0.5021, IoU.signboard: 0.3799, IoU.chest of drawers: 0.4054, IoU.counter: 0.4977, IoU.sand: 0.6098, IoU.sink: 0.7569, IoU.skyscraper: 0.4168, IoU.fireplace: 0.7298, IoU.refrigerator: 0.7738, IoU.grandstand: 0.4732, IoU.path: 0.1790, IoU.stairs: 0.2721, IoU.runway: 0.6766, IoU.case: 0.5354, IoU.pool table: 0.9139, IoU.pillow: 0.5687, IoU.screen door: 0.5488, IoU.stairway: 0.3637, IoU.river: 0.2157, IoU.bridge: 0.4448, IoU.bookcase: 0.3583, IoU.blind: 0.3633, IoU.coffee table: 0.6225, IoU.toilet: 0.8895, IoU.flower: 0.4081, IoU.book: 0.4672, IoU.hill: 0.0473, IoU.bench: 0.4838, IoU.countertop: 0.5723, IoU.stove: 0.8275, IoU.palm: 0.4589, IoU.kitchen island: 0.4072, IoU.computer: 0.7739, IoU.swivel chair: 0.4632, IoU.boat: 0.4217, IoU.bar: 0.6905, IoU.arcade machine: 0.7083, IoU.hovel: 0.2341, IoU.bus: 0.9075, IoU.towel: 0.6817, IoU.light: 0.4879, IoU.truck: 0.4407, IoU.tower: 0.1749, IoU.chandelier: 0.6513, IoU.awning: 0.2984, IoU.streetlight: 0.2376, IoU.booth: 0.4894, IoU.television receiver: 0.7502, IoU.airplane: 0.6151, IoU.dirt track: 0.0111, IoU.apparel: 0.4821, IoU.pole: 0.2213, IoU.land: 0.0484, IoU.bannister: 0.1246, IoU.escalator: 0.5142, IoU.ottoman: 0.4995, IoU.bottle: 0.2602, IoU.buffet: 0.4656, IoU.poster: 0.3225, IoU.stage: 0.2088, IoU.van: 0.3127, IoU.ship: 0.0338, IoU.fountain: 0.0202, IoU.conveyer belt: 0.7899, IoU.canopy: 0.5021, IoU.washer: 0.7055, IoU.plaything: 0.3848, IoU.swimming pool: 0.7434, IoU.stool: 0.4266, IoU.barrel: 0.4840, IoU.basket: 0.3919, IoU.waterfall: 0.4657, IoU.tent: 0.9411, IoU.bag: 0.2527, IoU.minibike: 0.6636, IoU.cradle: 0.6847, IoU.oven: 0.5313, IoU.ball: 0.5211, IoU.food: 0.2921, IoU.step: 0.0689, IoU.tank: 0.2618, IoU.trade name: 0.2639, IoU.microwave: 0.8438, IoU.pot: 0.5362, IoU.animal: 0.7658, IoU.bicycle: 0.5891, IoU.lake: 0.0000, IoU.dishwasher: 0.7517, IoU.screen: 0.5313, IoU.blanket: 0.1554, IoU.sculpture: 0.6275, IoU.hood: 0.6073, IoU.sconce: 0.4991, IoU.vase: 0.3977, IoU.traffic light: 0.3163, IoU.tray: 0.1053, IoU.ashcan: 0.4873, IoU.fan: 0.5881, IoU.pier: 0.3738, IoU.crt screen: 0.0425, IoU.plate: 0.5692, IoU.monitor: 0.1070, IoU.bulletin board: 0.5702, IoU.shower: 0.0302, IoU.radiator: 0.5409, IoU.glass: 0.2008, IoU.clock: 0.2873, IoU.flag: 0.6767, Acc.wall: 0.8724, Acc.building: 0.9268, Acc.sky: 0.9735, Acc.floor: 0.9058, Acc.tree: 0.8958, Acc.ceiling: 0.9304, Acc.road: 0.8897, Acc.bed : 0.9669, Acc.windowpane: 0.8065, Acc.grass: 0.8425, Acc.cabinet: 0.7401, Acc.sidewalk: 0.8403, Acc.person: 0.9235, Acc.earth: 0.4394, Acc.door: 0.7185, Acc.table: 0.7983, Acc.mountain: 0.7681, Acc.plant: 0.6551, Acc.curtain: 0.8502, Acc.chair: 0.7515, Acc.car: 0.9421, Acc.water: 0.6842, Acc.painting: 0.8708, Acc.sofa: 0.8932, Acc.shelf: 0.6615, Acc.house: 0.5553, Acc.sea: 0.7689, Acc.mirror: 0.8233, Acc.rug: 0.7652, Acc.field: 0.3402, Acc.armchair: 0.7196, Acc.seat: 0.7534, Acc.fence: 0.6591, Acc.desk: 0.6545, Acc.rock: 0.5962, Acc.wardrobe: 0.7266, Acc.lamp: 0.8006, Acc.bathtub: 0.9001, Acc.railing: 0.5389, Acc.cushion: 0.7668, Acc.base: 0.2339, Acc.box: 0.4239, Acc.column: 0.6460, Acc.signboard: 0.5389, Acc.chest of drawers: 0.6355, Acc.counter: 0.6470, Acc.sand: 0.7847, Acc.sink: 0.8371, Acc.skyscraper: 0.4821, Acc.fireplace: 0.9218, Acc.refrigerator: 0.8924, Acc.grandstand: 0.8628, Acc.path: 0.2524, Acc.stairs: 0.3585, Acc.runway: 0.8992, Acc.case: 0.8601, Acc.pool table: 0.9824, Acc.pillow: 0.6625, Acc.screen door: 0.6759, Acc.stairway: 0.4955, Acc.river: 0.3319, Acc.bridge: 0.4898, Acc.bookcase: 0.5079, Acc.blind: 0.4115, Acc.coffee table: 0.8461, Acc.toilet: 0.9456, Acc.flower: 0.5891, Acc.book: 0.7034, Acc.hill: 0.0645, Acc.bench: 0.5498, Acc.countertop: 0.7432, Acc.stove: 0.9047, Acc.palm: 0.6375, Acc.kitchen island: 0.6179, Acc.computer: 0.8917, Acc.swivel chair: 0.7639, Acc.boat: 0.8003, Acc.bar: 0.7737, Acc.arcade machine: 0.7309, Acc.hovel: 0.2518, Acc.bus: 0.9561, Acc.towel: 0.8664, Acc.light: 0.6133, Acc.truck: 0.6053, Acc.tower: 0.3150, Acc.chandelier: 0.8420, Acc.awning: 0.4277, Acc.streetlight: 0.3028, Acc.booth: 0.6083, Acc.television receiver: 0.8631, Acc.airplane: 0.7213, Acc.dirt track: 0.0230, Acc.apparel: 0.7339, Acc.pole: 0.3157, Acc.land: 0.0764, Acc.bannister: 0.2205, Acc.escalator: 0.6321, Acc.ottoman: 0.6586, Acc.bottle: 0.3505, Acc.buffet: 0.5576, Acc.poster: 0.4316, Acc.stage: 0.2754, Acc.van: 0.3496, Acc.ship: 0.0362, Acc.fountain: 0.0202, Acc.conveyer belt: 0.9293, Acc.canopy: 0.5421, Acc.washer: 0.7250, Acc.plaything: 0.5391, Acc.swimming pool: 0.8622, Acc.stool: 0.5985, Acc.barrel: 0.5032, Acc.basket: 0.5901, Acc.waterfall: 0.5774, Acc.tent: 0.9765, Acc.bag: 0.3170, Acc.minibike: 0.7908, Acc.cradle: 0.9798, Acc.oven: 0.6393, Acc.ball: 0.7430, Acc.food: 0.3230, Acc.step: 0.0873, Acc.tank: 0.3120, Acc.trade name: 0.3294, Acc.microwave: 0.9400, Acc.pot: 0.6182, Acc.animal: 0.7968, Acc.bicycle: 0.7996, Acc.lake: 0.0000, Acc.dishwasher: 0.8012, Acc.screen: 0.9325, Acc.blanket: 0.1700, Acc.sculpture: 0.7078, Acc.hood: 0.7076, Acc.sconce: 0.7023, Acc.vase: 0.5668, Acc.traffic light: 0.5702, Acc.tray: 0.1391, Acc.ashcan: 0.6648, Acc.fan: 0.7936, Acc.pier: 0.4056, Acc.crt screen: 0.1222, Acc.plate: 0.7456, Acc.monitor: 0.1238, Acc.bulletin board: 0.6784, Acc.shower: 0.0841, Acc.radiator: 0.6313, Acc.glass: 0.2245, Acc.clock: 0.3478, Acc.flag: 0.7518 2023-11-10 05:43:07,740 - mmseg - INFO - Iter [8050/10000] lr: 6.321e-07, eta: 0:43:43, time: 2.294, data_time: 1.084, memory: 38534, decode.loss_ce: 0.1627, decode.acc_seg: 93.2584, loss: 0.1627 2023-11-10 05:44:10,910 - mmseg - INFO - Iter [8100/10000] lr: 6.159e-07, eta: 0:42:35, time: 1.263, data_time: 0.052, memory: 38534, decode.loss_ce: 0.1676, decode.acc_seg: 93.2043, loss: 0.1676 2023-11-10 05:45:11,663 - mmseg - INFO - Iter [8150/10000] lr: 5.997e-07, eta: 0:41:26, time: 1.215, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1578, decode.acc_seg: 93.4731, loss: 0.1578 2023-11-10 05:46:12,394 - mmseg - INFO - Iter [8200/10000] lr: 5.835e-07, eta: 0:40:18, time: 1.215, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1622, decode.acc_seg: 93.1318, loss: 0.1622 2023-11-10 05:47:15,516 - mmseg - INFO - Iter [8250/10000] lr: 5.673e-07, eta: 0:39:09, time: 1.262, data_time: 0.051, memory: 38534, decode.loss_ce: 0.1648, decode.acc_seg: 93.2585, loss: 0.1648 2023-11-10 05:48:16,339 - mmseg - INFO - Iter [8300/10000] lr: 5.511e-07, eta: 0:38:01, time: 1.216, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1697, decode.acc_seg: 93.0881, loss: 0.1697 2023-11-10 05:49:17,170 - mmseg - INFO - Iter [8350/10000] lr: 5.349e-07, eta: 0:36:53, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1659, decode.acc_seg: 93.3424, loss: 0.1659 2023-11-10 05:50:20,242 - mmseg - INFO - Iter [8400/10000] lr: 5.187e-07, eta: 0:35:45, time: 1.261, data_time: 0.053, memory: 38534, decode.loss_ce: 0.1655, decode.acc_seg: 93.1601, loss: 0.1655 2023-11-10 05:51:21,028 - mmseg - INFO - Iter [8450/10000] lr: 5.025e-07, eta: 0:34:37, time: 1.216, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1621, decode.acc_seg: 93.3258, loss: 0.1621 2023-11-10 05:52:21,928 - mmseg - INFO - Iter [8500/10000] lr: 4.863e-07, eta: 0:33:29, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1496, decode.acc_seg: 93.8246, loss: 0.1496 2023-11-10 05:53:24,971 - mmseg - INFO - Iter [8550/10000] lr: 4.701e-07, eta: 0:32:21, time: 1.261, data_time: 0.052, memory: 38534, decode.loss_ce: 0.1608, decode.acc_seg: 93.1813, loss: 0.1608 2023-11-10 05:54:25,761 - mmseg - INFO - Iter [8600/10000] lr: 4.539e-07, eta: 0:31:13, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1687, decode.acc_seg: 93.2854, loss: 0.1687 2023-11-10 05:55:26,631 - mmseg - INFO - Iter [8650/10000] lr: 4.377e-07, eta: 0:30:05, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1607, decode.acc_seg: 93.3599, loss: 0.1607 2023-11-10 05:56:29,792 - mmseg - INFO - Iter [8700/10000] lr: 4.215e-07, eta: 0:28:58, time: 1.263, data_time: 0.050, memory: 38534, decode.loss_ce: 0.1642, decode.acc_seg: 93.2475, loss: 0.1642 2023-11-10 05:57:30,609 - mmseg - INFO - Iter [8750/10000] lr: 4.053e-07, eta: 0:27:50, time: 1.216, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1569, decode.acc_seg: 93.4221, loss: 0.1569 2023-11-10 05:58:31,412 - mmseg - INFO - Iter [8800/10000] lr: 3.891e-07, eta: 0:26:42, time: 1.216, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1568, decode.acc_seg: 93.5466, loss: 0.1568 2023-11-10 05:59:34,498 - mmseg - INFO - Iter [8850/10000] lr: 3.729e-07, eta: 0:25:35, time: 1.262, data_time: 0.051, memory: 38534, decode.loss_ce: 0.1627, decode.acc_seg: 93.3044, loss: 0.1627 2023-11-10 06:00:35,344 - mmseg - INFO - Iter [8900/10000] lr: 3.567e-07, eta: 0:24:28, time: 1.217, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1607, decode.acc_seg: 93.2296, loss: 0.1607 2023-11-10 06:01:36,140 - mmseg - INFO - Iter [8950/10000] lr: 3.405e-07, eta: 0:23:20, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1644, decode.acc_seg: 93.1715, loss: 0.1644 2023-11-10 06:02:36,921 - mmseg - INFO - Saving checkpoint at 9000 iterations 2023-11-10 06:03:31,586 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 06:03:31,586 - mmseg - INFO - Iter [9000/10000] lr: 3.243e-07, eta: 0:22:19, time: 2.309, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1544, decode.acc_seg: 93.5526, loss: 0.1544 2023-11-10 06:04:25,445 - mmseg - INFO - per class results: 2023-11-10 06:04:25,450 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 78.86 | 87.93 | | building | 82.37 | 93.8 | | sky | 94.04 | 97.11 | | floor | 83.13 | 91.0 | | tree | 75.02 | 87.42 | | ceiling | 84.54 | 93.24 | | road | 84.39 | 89.2 | | bed | 90.13 | 96.75 | | windowpane | 62.34 | 79.56 | | grass | 68.17 | 86.86 | | cabinet | 63.86 | 73.8 | | sidewalk | 67.06 | 83.32 | | person | 80.52 | 93.64 | | earth | 33.2 | 42.72 | | door | 56.32 | 71.23 | | table | 66.33 | 81.06 | | mountain | 60.45 | 79.7 | | plant | 51.82 | 66.93 | | curtain | 74.4 | 84.88 | | chair | 57.96 | 74.21 | | car | 84.7 | 93.27 | | water | 49.61 | 69.81 | | painting | 74.31 | 87.57 | | sofa | 77.38 | 87.79 | | shelf | 42.13 | 65.89 | | house | 40.93 | 50.13 | | sea | 50.14 | 74.52 | | mirror | 72.82 | 82.03 | | rug | 67.99 | 76.4 | | field | 21.02 | 37.0 | | armchair | 56.2 | 72.9 | | seat | 59.46 | 75.42 | | fence | 47.1 | 62.18 | | desk | 49.32 | 66.24 | | rock | 44.75 | 56.89 | | wardrobe | 52.94 | 74.08 | | lamp | 66.07 | 79.96 | | bathtub | 83.32 | 89.07 | | railing | 41.8 | 57.3 | | cushion | 61.94 | 78.66 | | base | 17.42 | 20.8 | | box | 33.41 | 43.64 | | column | 50.56 | 66.14 | | signboard | 37.54 | 50.74 | | chest of drawers | 42.74 | 62.09 | | counter | 45.66 | 61.41 | | sand | 67.37 | 80.9 | | sink | 76.54 | 84.68 | | skyscraper | 42.69 | 49.97 | | fireplace | 72.86 | 90.16 | | refrigerator | 76.78 | 88.68 | | grandstand | 48.81 | 84.77 | | path | 19.25 | 27.87 | | stairs | 27.11 | 32.61 | | runway | 68.15 | 91.0 | | case | 51.82 | 84.15 | | pool table | 91.81 | 98.01 | | pillow | 54.11 | 61.65 | | screen door | 52.64 | 65.15 | | stairway | 35.03 | 47.78 | | river | 21.85 | 31.18 | | bridge | 39.42 | 43.49 | | bookcase | 36.68 | 52.13 | | blind | 37.96 | 43.6 | | coffee table | 62.09 | 83.94 | | toilet | 89.12 | 94.11 | | flower | 40.27 | 65.3 | | book | 45.86 | 67.25 | | hill | 4.27 | 6.03 | | bench | 49.06 | 55.61 | | countertop | 58.4 | 74.98 | | stove | 82.34 | 90.52 | | palm | 46.59 | 66.13 | | kitchen island | 31.7 | 42.97 | | computer | 77.61 | 88.85 | | swivel chair | 46.06 | 71.47 | | boat | 44.77 | 76.81 | | bar | 69.28 | 78.89 | | arcade machine | 63.42 | 64.83 | | hovel | 27.06 | 29.39 | | bus | 91.48 | 95.23 | | towel | 68.32 | 85.43 | | light | 44.82 | 52.35 | | truck | 37.35 | 49.06 | | tower | 10.62 | 18.02 | | chandelier | 65.13 | 82.5 | | awning | 29.42 | 39.55 | | streetlight | 23.69 | 30.66 | | booth | 54.16 | 66.48 | | television receiver | 76.05 | 84.96 | | airplane | 61.85 | 70.32 | | dirt track | 0.82 | 2.32 | | apparel | 48.83 | 73.04 | | pole | 21.9 | 29.4 | | land | 5.73 | 7.84 | | bannister | 11.92 | 19.07 | | escalator | 52.1 | 63.82 | | ottoman | 51.28 | 70.24 | | bottle | 23.63 | 29.86 | | buffet | 48.38 | 59.04 | | poster | 31.11 | 42.69 | | stage | 17.59 | 21.82 | | van | 34.19 | 40.55 | | ship | 3.46 | 3.83 | | fountain | 1.78 | 1.79 | | conveyer belt | 77.02 | 89.1 | | canopy | 54.21 | 58.49 | | washer | 70.27 | 72.63 | | plaything | 38.51 | 56.68 | | swimming pool | 70.59 | 85.62 | | stool | 46.6 | 62.8 | | barrel | 48.98 | 50.11 | | basket | 40.14 | 56.99 | | waterfall | 45.12 | 54.71 | | tent | 94.47 | 97.77 | | bag | 25.22 | 30.03 | | minibike | 65.98 | 77.92 | | cradle | 72.78 | 96.76 | | oven | 55.69 | 64.72 | | ball | 47.45 | 74.66 | | food | 26.94 | 29.18 | | step | 7.65 | 9.25 | | tank | 20.97 | 24.64 | | trade name | 20.61 | 23.89 | | microwave | 85.5 | 93.41 | | pot | 53.11 | 60.05 | | animal | 73.6 | 75.94 | | bicycle | 58.56 | 76.36 | | lake | 0.0 | 0.0 | | dishwasher | 75.63 | 80.72 | | screen | 54.77 | 92.67 | | blanket | 18.97 | 21.14 | | sculpture | 62.23 | 71.23 | | hood | 63.1 | 71.21 | | sconce | 50.13 | 67.23 | | vase | 39.43 | 58.1 | | traffic light | 32.52 | 55.69 | | tray | 9.64 | 11.86 | | ashcan | 50.3 | 65.32 | | fan | 59.51 | 76.12 | | pier | 37.25 | 40.8 | | crt screen | 3.66 | 10.45 | | plate | 57.26 | 73.75 | | monitor | 9.75 | 11.15 | | bulletin board | 52.63 | 60.85 | | shower | 2.98 | 9.91 | | radiator | 54.05 | 63.14 | | glass | 18.95 | 20.79 | | clock | 28.85 | 34.47 | | flag | 65.87 | 72.08 | +---------------------+-------+-------+ 2023-11-10 06:04:25,451 - mmseg - INFO - Summary: 2023-11-10 06:04:25,451 - mmseg - INFO - +------+-------+-------+ | aAcc | mIoU | mAcc | +------+-------+-------+ | 83.7 | 50.05 | 61.61 | +------+-------+-------+ 2023-11-10 06:04:25,452 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 06:04:25,452 - mmseg - INFO - Iter(val) [250] aAcc: 0.8370, mIoU: 0.5005, mAcc: 0.6161, IoU.wall: 0.7886, IoU.building: 0.8237, IoU.sky: 0.9404, IoU.floor: 0.8313, IoU.tree: 0.7502, IoU.ceiling: 0.8454, IoU.road: 0.8439, IoU.bed : 0.9013, IoU.windowpane: 0.6234, IoU.grass: 0.6817, IoU.cabinet: 0.6386, IoU.sidewalk: 0.6706, IoU.person: 0.8052, IoU.earth: 0.3320, IoU.door: 0.5632, IoU.table: 0.6633, IoU.mountain: 0.6045, IoU.plant: 0.5182, IoU.curtain: 0.7440, IoU.chair: 0.5796, IoU.car: 0.8470, IoU.water: 0.4961, IoU.painting: 0.7431, IoU.sofa: 0.7738, IoU.shelf: 0.4213, IoU.house: 0.4093, IoU.sea: 0.5014, IoU.mirror: 0.7282, IoU.rug: 0.6799, IoU.field: 0.2102, IoU.armchair: 0.5620, IoU.seat: 0.5946, IoU.fence: 0.4710, IoU.desk: 0.4932, IoU.rock: 0.4475, IoU.wardrobe: 0.5294, IoU.lamp: 0.6607, IoU.bathtub: 0.8332, IoU.railing: 0.4180, IoU.cushion: 0.6194, IoU.base: 0.1742, IoU.box: 0.3341, IoU.column: 0.5056, IoU.signboard: 0.3754, IoU.chest of drawers: 0.4274, IoU.counter: 0.4566, IoU.sand: 0.6737, IoU.sink: 0.7654, IoU.skyscraper: 0.4269, IoU.fireplace: 0.7286, IoU.refrigerator: 0.7678, IoU.grandstand: 0.4881, IoU.path: 0.1925, IoU.stairs: 0.2711, IoU.runway: 0.6815, IoU.case: 0.5182, IoU.pool table: 0.9181, IoU.pillow: 0.5411, IoU.screen door: 0.5264, IoU.stairway: 0.3503, IoU.river: 0.2185, IoU.bridge: 0.3942, IoU.bookcase: 0.3668, IoU.blind: 0.3796, IoU.coffee table: 0.6209, IoU.toilet: 0.8912, IoU.flower: 0.4027, IoU.book: 0.4586, IoU.hill: 0.0427, IoU.bench: 0.4906, IoU.countertop: 0.5840, IoU.stove: 0.8234, IoU.palm: 0.4659, IoU.kitchen island: 0.3170, IoU.computer: 0.7761, IoU.swivel chair: 0.4606, IoU.boat: 0.4477, IoU.bar: 0.6928, IoU.arcade machine: 0.6342, IoU.hovel: 0.2706, IoU.bus: 0.9148, IoU.towel: 0.6832, IoU.light: 0.4482, IoU.truck: 0.3735, IoU.tower: 0.1062, IoU.chandelier: 0.6513, IoU.awning: 0.2942, IoU.streetlight: 0.2369, IoU.booth: 0.5416, IoU.television receiver: 0.7605, IoU.airplane: 0.6185, IoU.dirt track: 0.0082, IoU.apparel: 0.4883, IoU.pole: 0.2190, IoU.land: 0.0573, IoU.bannister: 0.1192, IoU.escalator: 0.5210, IoU.ottoman: 0.5128, IoU.bottle: 0.2363, IoU.buffet: 0.4838, IoU.poster: 0.3111, IoU.stage: 0.1759, IoU.van: 0.3419, IoU.ship: 0.0346, IoU.fountain: 0.0178, IoU.conveyer belt: 0.7702, IoU.canopy: 0.5421, IoU.washer: 0.7027, IoU.plaything: 0.3851, IoU.swimming pool: 0.7059, IoU.stool: 0.4660, IoU.barrel: 0.4898, IoU.basket: 0.4014, IoU.waterfall: 0.4512, IoU.tent: 0.9447, IoU.bag: 0.2522, IoU.minibike: 0.6598, IoU.cradle: 0.7278, IoU.oven: 0.5569, IoU.ball: 0.4745, IoU.food: 0.2694, IoU.step: 0.0765, IoU.tank: 0.2097, IoU.trade name: 0.2061, IoU.microwave: 0.8550, IoU.pot: 0.5311, IoU.animal: 0.7360, IoU.bicycle: 0.5856, IoU.lake: 0.0000, IoU.dishwasher: 0.7563, IoU.screen: 0.5477, IoU.blanket: 0.1897, IoU.sculpture: 0.6223, IoU.hood: 0.6310, IoU.sconce: 0.5013, IoU.vase: 0.3943, IoU.traffic light: 0.3252, IoU.tray: 0.0964, IoU.ashcan: 0.5030, IoU.fan: 0.5951, IoU.pier: 0.3725, IoU.crt screen: 0.0366, IoU.plate: 0.5726, IoU.monitor: 0.0975, IoU.bulletin board: 0.5263, IoU.shower: 0.0298, IoU.radiator: 0.5405, IoU.glass: 0.1895, IoU.clock: 0.2885, IoU.flag: 0.6587, Acc.wall: 0.8793, Acc.building: 0.9380, Acc.sky: 0.9711, Acc.floor: 0.9100, Acc.tree: 0.8742, Acc.ceiling: 0.9324, Acc.road: 0.8920, Acc.bed : 0.9675, Acc.windowpane: 0.7956, Acc.grass: 0.8686, Acc.cabinet: 0.7380, Acc.sidewalk: 0.8332, Acc.person: 0.9364, Acc.earth: 0.4272, Acc.door: 0.7123, Acc.table: 0.8106, Acc.mountain: 0.7970, Acc.plant: 0.6693, Acc.curtain: 0.8488, Acc.chair: 0.7421, Acc.car: 0.9327, Acc.water: 0.6981, Acc.painting: 0.8757, Acc.sofa: 0.8779, Acc.shelf: 0.6589, Acc.house: 0.5013, Acc.sea: 0.7452, Acc.mirror: 0.8203, Acc.rug: 0.7640, Acc.field: 0.3700, Acc.armchair: 0.7290, Acc.seat: 0.7542, Acc.fence: 0.6218, Acc.desk: 0.6624, Acc.rock: 0.5689, Acc.wardrobe: 0.7408, Acc.lamp: 0.7996, Acc.bathtub: 0.8907, Acc.railing: 0.5730, Acc.cushion: 0.7866, Acc.base: 0.2080, Acc.box: 0.4364, Acc.column: 0.6614, Acc.signboard: 0.5074, Acc.chest of drawers: 0.6209, Acc.counter: 0.6141, Acc.sand: 0.8090, Acc.sink: 0.8468, Acc.skyscraper: 0.4997, Acc.fireplace: 0.9016, Acc.refrigerator: 0.8868, Acc.grandstand: 0.8477, Acc.path: 0.2787, Acc.stairs: 0.3261, Acc.runway: 0.9100, Acc.case: 0.8415, Acc.pool table: 0.9801, Acc.pillow: 0.6165, Acc.screen door: 0.6515, Acc.stairway: 0.4778, Acc.river: 0.3118, Acc.bridge: 0.4349, Acc.bookcase: 0.5213, Acc.blind: 0.4360, Acc.coffee table: 0.8394, Acc.toilet: 0.9411, Acc.flower: 0.6530, Acc.book: 0.6725, Acc.hill: 0.0603, Acc.bench: 0.5561, Acc.countertop: 0.7498, Acc.stove: 0.9052, Acc.palm: 0.6613, Acc.kitchen island: 0.4297, Acc.computer: 0.8885, Acc.swivel chair: 0.7147, Acc.boat: 0.7681, Acc.bar: 0.7889, Acc.arcade machine: 0.6483, Acc.hovel: 0.2939, Acc.bus: 0.9523, Acc.towel: 0.8543, Acc.light: 0.5235, Acc.truck: 0.4906, Acc.tower: 0.1802, Acc.chandelier: 0.8250, Acc.awning: 0.3955, Acc.streetlight: 0.3066, Acc.booth: 0.6648, Acc.television receiver: 0.8496, Acc.airplane: 0.7032, Acc.dirt track: 0.0232, Acc.apparel: 0.7304, Acc.pole: 0.2940, Acc.land: 0.0784, Acc.bannister: 0.1907, Acc.escalator: 0.6382, Acc.ottoman: 0.7024, Acc.bottle: 0.2986, Acc.buffet: 0.5904, Acc.poster: 0.4269, Acc.stage: 0.2182, Acc.van: 0.4055, Acc.ship: 0.0383, Acc.fountain: 0.0179, Acc.conveyer belt: 0.8910, Acc.canopy: 0.5849, Acc.washer: 0.7263, Acc.plaything: 0.5668, Acc.swimming pool: 0.8562, Acc.stool: 0.6280, Acc.barrel: 0.5011, Acc.basket: 0.5699, Acc.waterfall: 0.5471, Acc.tent: 0.9777, Acc.bag: 0.3003, Acc.minibike: 0.7792, Acc.cradle: 0.9676, Acc.oven: 0.6472, Acc.ball: 0.7466, Acc.food: 0.2918, Acc.step: 0.0925, Acc.tank: 0.2464, Acc.trade name: 0.2389, Acc.microwave: 0.9341, Acc.pot: 0.6005, Acc.animal: 0.7594, Acc.bicycle: 0.7636, Acc.lake: 0.0000, Acc.dishwasher: 0.8072, Acc.screen: 0.9267, Acc.blanket: 0.2114, Acc.sculpture: 0.7123, Acc.hood: 0.7121, Acc.sconce: 0.6723, Acc.vase: 0.5810, Acc.traffic light: 0.5569, Acc.tray: 0.1186, Acc.ashcan: 0.6532, Acc.fan: 0.7612, Acc.pier: 0.4080, Acc.crt screen: 0.1045, Acc.plate: 0.7375, Acc.monitor: 0.1115, Acc.bulletin board: 0.6085, Acc.shower: 0.0991, Acc.radiator: 0.6314, Acc.glass: 0.2079, Acc.clock: 0.3447, Acc.flag: 0.7208 2023-11-10 06:05:28,620 - mmseg - INFO - Iter [9050/10000] lr: 3.081e-07, eta: 0:21:17, time: 2.341, data_time: 1.129, memory: 38534, decode.loss_ce: 0.1631, decode.acc_seg: 93.3816, loss: 0.1631 2023-11-10 06:06:29,444 - mmseg - INFO - Iter [9100/10000] lr: 2.919e-07, eta: 0:20:09, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1592, decode.acc_seg: 93.2095, loss: 0.1592 2023-11-10 06:07:30,241 - mmseg - INFO - Iter [9150/10000] lr: 2.757e-07, eta: 0:19:01, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1594, decode.acc_seg: 93.3748, loss: 0.1594 2023-11-10 06:08:33,319 - mmseg - INFO - Iter [9200/10000] lr: 2.595e-07, eta: 0:17:54, time: 1.262, data_time: 0.051, memory: 38534, decode.loss_ce: 0.1576, decode.acc_seg: 93.5702, loss: 0.1576 2023-11-10 06:09:34,170 - mmseg - INFO - Iter [9250/10000] lr: 2.433e-07, eta: 0:16:46, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1500, decode.acc_seg: 93.7145, loss: 0.1500 2023-11-10 06:10:35,028 - mmseg - INFO - Iter [9300/10000] lr: 2.271e-07, eta: 0:15:39, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1560, decode.acc_seg: 93.5220, loss: 0.1560 2023-11-10 06:11:38,145 - mmseg - INFO - Iter [9350/10000] lr: 2.109e-07, eta: 0:14:31, time: 1.262, data_time: 0.052, memory: 38534, decode.loss_ce: 0.1486, decode.acc_seg: 93.7933, loss: 0.1486 2023-11-10 06:12:38,937 - mmseg - INFO - Iter [9400/10000] lr: 1.947e-07, eta: 0:13:24, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1592, decode.acc_seg: 93.4439, loss: 0.1592 2023-11-10 06:13:39,848 - mmseg - INFO - Iter [9450/10000] lr: 1.785e-07, eta: 0:12:16, time: 1.218, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1594, decode.acc_seg: 93.4331, loss: 0.1594 2023-11-10 06:14:43,027 - mmseg - INFO - Iter [9500/10000] lr: 1.623e-07, eta: 0:11:09, time: 1.264, data_time: 0.052, memory: 38534, decode.loss_ce: 0.1536, decode.acc_seg: 93.6338, loss: 0.1536 2023-11-10 06:15:43,823 - mmseg - INFO - Iter [9550/10000] lr: 1.461e-07, eta: 0:10:02, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1523, decode.acc_seg: 93.5966, loss: 0.1523 2023-11-10 06:16:44,624 - mmseg - INFO - Iter [9600/10000] lr: 1.299e-07, eta: 0:08:55, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1512, decode.acc_seg: 93.7215, loss: 0.1512 2023-11-10 06:17:47,788 - mmseg - INFO - Iter [9650/10000] lr: 1.137e-07, eta: 0:07:48, time: 1.263, data_time: 0.053, memory: 38534, decode.loss_ce: 0.1578, decode.acc_seg: 93.5147, loss: 0.1578 2023-11-10 06:18:48,621 - mmseg - INFO - Iter [9700/10000] lr: 9.752e-08, eta: 0:06:41, time: 1.217, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1581, decode.acc_seg: 93.5729, loss: 0.1581 2023-11-10 06:19:49,423 - mmseg - INFO - Iter [9750/10000] lr: 8.132e-08, eta: 0:05:34, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1520, decode.acc_seg: 93.6601, loss: 0.1520 2023-11-10 06:20:52,521 - mmseg - INFO - Iter [9800/10000] lr: 6.512e-08, eta: 0:04:27, time: 1.262, data_time: 0.053, memory: 38534, decode.loss_ce: 0.1552, decode.acc_seg: 93.6070, loss: 0.1552 2023-11-10 06:21:53,313 - mmseg - INFO - Iter [9850/10000] lr: 4.892e-08, eta: 0:03:20, time: 1.216, data_time: 0.007, memory: 38534, decode.loss_ce: 0.1540, decode.acc_seg: 93.6025, loss: 0.1540 2023-11-10 06:22:54,124 - mmseg - INFO - Iter [9900/10000] lr: 3.272e-08, eta: 0:02:13, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1500, decode.acc_seg: 93.7612, loss: 0.1500 2023-11-10 06:23:54,933 - mmseg - INFO - Iter [9950/10000] lr: 1.652e-08, eta: 0:01:06, time: 1.216, data_time: 0.008, memory: 38534, decode.loss_ce: 0.1495, decode.acc_seg: 93.6658, loss: 0.1495 2023-11-10 06:24:58,126 - mmseg - INFO - Saving checkpoint at 10000 iterations 2023-11-10 06:25:53,542 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 06:25:53,542 - mmseg - INFO - Iter [10000/10000] lr: 3.240e-10, eta: 0:00:00, time: 2.372, data_time: 0.051, memory: 38534, decode.loss_ce: 0.1571, decode.acc_seg: 93.5536, loss: 0.1571 2023-11-10 06:26:47,635 - mmseg - INFO - per class results: 2023-11-10 06:26:47,640 - mmseg - INFO - +---------------------+-------+-------+ | Class | IoU | Acc | +---------------------+-------+-------+ | wall | 78.97 | 87.89 | | building | 82.51 | 93.19 | | sky | 94.05 | 97.14 | | floor | 83.07 | 91.6 | | tree | 75.05 | 87.99 | | ceiling | 84.58 | 93.24 | | road | 84.07 | 88.37 | | bed | 90.22 | 96.66 | | windowpane | 62.64 | 80.5 | | grass | 68.55 | 87.86 | | cabinet | 63.77 | 73.99 | | sidewalk | 66.92 | 85.05 | | person | 80.91 | 93.3 | | earth | 34.67 | 46.18 | | door | 56.57 | 72.76 | | table | 66.1 | 81.1 | | mountain | 60.24 | 78.67 | | plant | 52.07 | 65.6 | | curtain | 74.41 | 85.54 | | chair | 57.75 | 72.68 | | car | 84.64 | 93.69 | | water | 48.74 | 67.93 | | painting | 74.41 | 87.78 | | sofa | 77.69 | 88.82 | | shelf | 41.93 | 63.85 | | house | 44.14 | 57.06 | | sea | 49.61 | 75.3 | | mirror | 72.98 | 82.31 | | rug | 67.3 | 75.35 | | field | 20.42 | 32.36 | | armchair | 56.55 | 72.99 | | seat | 58.62 | 75.01 | | fence | 47.43 | 62.68 | | desk | 49.01 | 66.34 | | rock | 45.06 | 56.97 | | wardrobe | 52.78 | 72.96 | | lamp | 66.28 | 80.28 | | bathtub | 82.25 | 88.72 | | railing | 41.76 | 56.48 | | cushion | 62.06 | 77.19 | | base | 18.25 | 22.32 | | box | 32.85 | 41.34 | | column | 49.74 | 62.22 | | signboard | 37.67 | 51.35 | | chest of drawers | 41.72 | 61.33 | | counter | 42.3 | 55.59 | | sand | 67.15 | 78.95 | | sink | 76.31 | 84.23 | | skyscraper | 42.11 | 49.01 | | fireplace | 72.89 | 90.54 | | refrigerator | 77.53 | 88.74 | | grandstand | 48.48 | 86.59 | | path | 20.18 | 28.6 | | stairs | 26.58 | 33.01 | | runway | 67.7 | 89.06 | | case | 51.21 | 83.33 | | pool table | 92.04 | 97.85 | | pillow | 55.66 | 64.26 | | screen door | 54.62 | 67.85 | | stairway | 35.91 | 50.04 | | river | 21.78 | 32.74 | | bridge | 38.89 | 42.9 | | bookcase | 34.85 | 49.64 | | blind | 37.73 | 42.96 | | coffee table | 62.16 | 84.71 | | toilet | 89.0 | 94.14 | | flower | 40.59 | 62.6 | | book | 46.1 | 67.67 | | hill | 4.6 | 6.92 | | bench | 47.11 | 53.13 | | countertop | 58.09 | 75.03 | | stove | 82.83 | 90.36 | | palm | 47.72 | 70.37 | | kitchen island | 37.03 | 50.56 | | computer | 77.86 | 88.47 | | swivel chair | 45.5 | 71.63 | | boat | 49.01 | 75.9 | | bar | 66.2 | 80.11 | | arcade machine | 62.96 | 64.57 | | hovel | 24.87 | 26.75 | | bus | 90.92 | 95.54 | | towel | 67.86 | 86.02 | | light | 46.35 | 55.66 | | truck | 39.06 | 51.27 | | tower | 11.49 | 19.66 | | chandelier | 65.18 | 82.23 | | awning | 29.31 | 39.09 | | streetlight | 24.36 | 32.62 | | booth | 54.82 | 68.22 | | television receiver | 76.25 | 86.12 | | airplane | 62.02 | 69.99 | | dirt track | 0.78 | 2.6 | | apparel | 47.57 | 72.8 | | pole | 20.09 | 27.04 | | land | 5.28 | 8.23 | | bannister | 12.39 | 19.75 | | escalator | 49.06 | 59.85 | | ottoman | 50.33 | 66.53 | | bottle | 25.15 | 33.88 | | buffet | 45.73 | 52.43 | | poster | 31.11 | 42.85 | | stage | 17.69 | 22.2 | | van | 34.03 | 39.95 | | ship | 3.7 | 4.13 | | fountain | 1.78 | 1.79 | | conveyer belt | 77.88 | 90.95 | | canopy | 45.45 | 48.08 | | washer | 70.38 | 72.81 | | plaything | 39.78 | 54.85 | | swimming pool | 74.9 | 85.28 | | stool | 43.8 | 61.6 | | barrel | 49.23 | 50.34 | | basket | 40.03 | 56.91 | | waterfall | 45.16 | 55.67 | | tent | 94.21 | 97.71 | | bag | 26.48 | 32.51 | | minibike | 65.82 | 77.54 | | cradle | 71.35 | 97.29 | | oven | 55.79 | 65.51 | | ball | 47.03 | 74.62 | | food | 26.38 | 28.58 | | step | 7.18 | 8.83 | | tank | 20.62 | 24.32 | | trade name | 21.53 | 25.1 | | microwave | 85.21 | 93.56 | | pot | 52.89 | 59.82 | | animal | 72.47 | 74.47 | | bicycle | 58.95 | 75.57 | | lake | 0.0 | 0.0 | | dishwasher | 75.77 | 80.83 | | screen | 55.78 | 91.44 | | blanket | 18.36 | 20.34 | | sculpture | 61.36 | 69.87 | | hood | 63.1 | 70.8 | | sconce | 50.42 | 64.93 | | vase | 39.32 | 56.57 | | traffic light | 32.12 | 56.5 | | tray | 9.72 | 12.34 | | ashcan | 49.93 | 66.26 | | fan | 58.56 | 74.06 | | pier | 37.41 | 40.81 | | crt screen | 3.86 | 11.13 | | plate | 56.92 | 74.45 | | monitor | 10.02 | 11.43 | | bulletin board | 52.93 | 63.81 | | shower | 3.4 | 8.81 | | radiator | 54.24 | 63.45 | | glass | 19.35 | 21.36 | | clock | 28.85 | 33.96 | | flag | 66.51 | 72.94 | +---------------------+-------+-------+ 2023-11-10 06:26:47,641 - mmseg - INFO - Summary: 2023-11-10 06:26:47,641 - mmseg - INFO - +-------+------+-------+ | aAcc | mIoU | mAcc | +-------+------+-------+ | 83.73 | 50.0 | 61.53 | +-------+------+-------+ 2023-11-10 06:26:47,641 - mmseg - INFO - Exp name: segmenter_linear_intern_vit_6b_504_10k_ade20k_bs16_lr4e-5_1of8.py 2023-11-10 06:26:47,642 - mmseg - INFO - Iter(val) [250] aAcc: 0.8373, mIoU: 0.5000, mAcc: 0.6153, IoU.wall: 0.7897, IoU.building: 0.8251, IoU.sky: 0.9405, IoU.floor: 0.8307, IoU.tree: 0.7505, IoU.ceiling: 0.8458, IoU.road: 0.8407, IoU.bed : 0.9022, IoU.windowpane: 0.6264, IoU.grass: 0.6855, IoU.cabinet: 0.6377, IoU.sidewalk: 0.6692, IoU.person: 0.8091, IoU.earth: 0.3467, IoU.door: 0.5657, IoU.table: 0.6610, IoU.mountain: 0.6024, IoU.plant: 0.5207, IoU.curtain: 0.7441, IoU.chair: 0.5775, IoU.car: 0.8464, IoU.water: 0.4874, IoU.painting: 0.7441, IoU.sofa: 0.7769, IoU.shelf: 0.4193, IoU.house: 0.4414, IoU.sea: 0.4961, IoU.mirror: 0.7298, IoU.rug: 0.6730, IoU.field: 0.2042, IoU.armchair: 0.5655, IoU.seat: 0.5862, IoU.fence: 0.4743, IoU.desk: 0.4901, IoU.rock: 0.4506, IoU.wardrobe: 0.5278, IoU.lamp: 0.6628, IoU.bathtub: 0.8225, IoU.railing: 0.4176, IoU.cushion: 0.6206, IoU.base: 0.1825, IoU.box: 0.3285, IoU.column: 0.4974, IoU.signboard: 0.3767, IoU.chest of drawers: 0.4172, IoU.counter: 0.4230, IoU.sand: 0.6715, IoU.sink: 0.7631, IoU.skyscraper: 0.4211, IoU.fireplace: 0.7289, IoU.refrigerator: 0.7753, IoU.grandstand: 0.4848, IoU.path: 0.2018, IoU.stairs: 0.2658, IoU.runway: 0.6770, IoU.case: 0.5121, IoU.pool table: 0.9204, IoU.pillow: 0.5566, IoU.screen door: 0.5462, IoU.stairway: 0.3591, IoU.river: 0.2178, IoU.bridge: 0.3889, IoU.bookcase: 0.3485, IoU.blind: 0.3773, IoU.coffee table: 0.6216, IoU.toilet: 0.8900, IoU.flower: 0.4059, IoU.book: 0.4610, IoU.hill: 0.0460, IoU.bench: 0.4711, IoU.countertop: 0.5809, IoU.stove: 0.8283, IoU.palm: 0.4772, IoU.kitchen island: 0.3703, IoU.computer: 0.7786, IoU.swivel chair: 0.4550, IoU.boat: 0.4901, IoU.bar: 0.6620, IoU.arcade machine: 0.6296, IoU.hovel: 0.2487, IoU.bus: 0.9092, IoU.towel: 0.6786, IoU.light: 0.4635, IoU.truck: 0.3906, IoU.tower: 0.1149, IoU.chandelier: 0.6518, IoU.awning: 0.2931, IoU.streetlight: 0.2436, IoU.booth: 0.5482, IoU.television receiver: 0.7625, IoU.airplane: 0.6202, IoU.dirt track: 0.0078, IoU.apparel: 0.4757, IoU.pole: 0.2009, IoU.land: 0.0528, IoU.bannister: 0.1239, IoU.escalator: 0.4906, IoU.ottoman: 0.5033, IoU.bottle: 0.2515, IoU.buffet: 0.4573, IoU.poster: 0.3111, IoU.stage: 0.1769, IoU.van: 0.3403, IoU.ship: 0.0370, IoU.fountain: 0.0178, IoU.conveyer belt: 0.7788, IoU.canopy: 0.4545, IoU.washer: 0.7038, IoU.plaything: 0.3978, IoU.swimming pool: 0.7490, IoU.stool: 0.4380, IoU.barrel: 0.4923, IoU.basket: 0.4003, IoU.waterfall: 0.4516, IoU.tent: 0.9421, IoU.bag: 0.2648, IoU.minibike: 0.6582, IoU.cradle: 0.7135, IoU.oven: 0.5579, IoU.ball: 0.4703, IoU.food: 0.2638, IoU.step: 0.0718, IoU.tank: 0.2062, IoU.trade name: 0.2153, IoU.microwave: 0.8521, IoU.pot: 0.5289, IoU.animal: 0.7247, IoU.bicycle: 0.5895, IoU.lake: 0.0000, IoU.dishwasher: 0.7577, IoU.screen: 0.5578, IoU.blanket: 0.1836, IoU.sculpture: 0.6136, IoU.hood: 0.6310, IoU.sconce: 0.5042, IoU.vase: 0.3932, IoU.traffic light: 0.3212, IoU.tray: 0.0972, IoU.ashcan: 0.4993, IoU.fan: 0.5856, IoU.pier: 0.3741, IoU.crt screen: 0.0386, IoU.plate: 0.5692, IoU.monitor: 0.1002, IoU.bulletin board: 0.5293, IoU.shower: 0.0340, IoU.radiator: 0.5424, IoU.glass: 0.1935, IoU.clock: 0.2885, IoU.flag: 0.6651, Acc.wall: 0.8789, Acc.building: 0.9319, Acc.sky: 0.9714, Acc.floor: 0.9160, Acc.tree: 0.8799, Acc.ceiling: 0.9324, Acc.road: 0.8837, Acc.bed : 0.9666, Acc.windowpane: 0.8050, Acc.grass: 0.8786, Acc.cabinet: 0.7399, Acc.sidewalk: 0.8505, Acc.person: 0.9330, Acc.earth: 0.4618, Acc.door: 0.7276, Acc.table: 0.8110, Acc.mountain: 0.7867, Acc.plant: 0.6560, Acc.curtain: 0.8554, Acc.chair: 0.7268, Acc.car: 0.9369, Acc.water: 0.6793, Acc.painting: 0.8778, Acc.sofa: 0.8882, Acc.shelf: 0.6385, Acc.house: 0.5706, Acc.sea: 0.7530, Acc.mirror: 0.8231, Acc.rug: 0.7535, Acc.field: 0.3236, Acc.armchair: 0.7299, Acc.seat: 0.7501, Acc.fence: 0.6268, Acc.desk: 0.6634, Acc.rock: 0.5697, Acc.wardrobe: 0.7296, Acc.lamp: 0.8028, Acc.bathtub: 0.8872, Acc.railing: 0.5648, Acc.cushion: 0.7719, Acc.base: 0.2232, Acc.box: 0.4134, Acc.column: 0.6222, Acc.signboard: 0.5135, Acc.chest of drawers: 0.6133, Acc.counter: 0.5559, Acc.sand: 0.7895, Acc.sink: 0.8423, Acc.skyscraper: 0.4901, Acc.fireplace: 0.9054, Acc.refrigerator: 0.8874, Acc.grandstand: 0.8659, Acc.path: 0.2860, Acc.stairs: 0.3301, Acc.runway: 0.8906, Acc.case: 0.8333, Acc.pool table: 0.9785, Acc.pillow: 0.6426, Acc.screen door: 0.6785, Acc.stairway: 0.5004, Acc.river: 0.3274, Acc.bridge: 0.4290, Acc.bookcase: 0.4964, Acc.blind: 0.4296, Acc.coffee table: 0.8471, Acc.toilet: 0.9414, Acc.flower: 0.6260, Acc.book: 0.6767, Acc.hill: 0.0692, Acc.bench: 0.5313, Acc.countertop: 0.7503, Acc.stove: 0.9036, Acc.palm: 0.7037, Acc.kitchen island: 0.5056, Acc.computer: 0.8847, Acc.swivel chair: 0.7163, Acc.boat: 0.7590, Acc.bar: 0.8011, Acc.arcade machine: 0.6457, Acc.hovel: 0.2675, Acc.bus: 0.9554, Acc.towel: 0.8602, Acc.light: 0.5566, Acc.truck: 0.5127, Acc.tower: 0.1966, Acc.chandelier: 0.8223, Acc.awning: 0.3909, Acc.streetlight: 0.3262, Acc.booth: 0.6822, Acc.television receiver: 0.8612, Acc.airplane: 0.6999, Acc.dirt track: 0.0260, Acc.apparel: 0.7280, Acc.pole: 0.2704, Acc.land: 0.0823, Acc.bannister: 0.1975, Acc.escalator: 0.5985, Acc.ottoman: 0.6653, Acc.bottle: 0.3388, Acc.buffet: 0.5243, Acc.poster: 0.4285, Acc.stage: 0.2220, Acc.van: 0.3995, Acc.ship: 0.0413, Acc.fountain: 0.0179, Acc.conveyer belt: 0.9095, Acc.canopy: 0.4808, Acc.washer: 0.7281, Acc.plaything: 0.5485, Acc.swimming pool: 0.8528, Acc.stool: 0.6160, Acc.barrel: 0.5034, Acc.basket: 0.5691, Acc.waterfall: 0.5567, Acc.tent: 0.9771, Acc.bag: 0.3251, Acc.minibike: 0.7754, Acc.cradle: 0.9729, Acc.oven: 0.6551, Acc.ball: 0.7462, Acc.food: 0.2858, Acc.step: 0.0883, Acc.tank: 0.2432, Acc.trade name: 0.2510, Acc.microwave: 0.9356, Acc.pot: 0.5982, Acc.animal: 0.7447, Acc.bicycle: 0.7557, Acc.lake: 0.0000, Acc.dishwasher: 0.8083, Acc.screen: 0.9144, Acc.blanket: 0.2034, Acc.sculpture: 0.6987, Acc.hood: 0.7080, Acc.sconce: 0.6493, Acc.vase: 0.5657, Acc.traffic light: 0.5650, Acc.tray: 0.1234, Acc.ashcan: 0.6626, Acc.fan: 0.7406, Acc.pier: 0.4081, Acc.crt screen: 0.1113, Acc.plate: 0.7445, Acc.monitor: 0.1143, Acc.bulletin board: 0.6381, Acc.shower: 0.0881, Acc.radiator: 0.6345, Acc.glass: 0.2136, Acc.clock: 0.3396, Acc.flag: 0.7294