{"env_info": "sys.platform: linux\nPython: 3.7.16 (default, Jan 17 2023, 22:20:44) [GCC 11.2.0]\nCUDA available: True\nGPU 0,1,2,3,4,5,6,7: NVIDIA A100-SXM4-80GB\nCUDA_HOME: /mnt/petrelfs/laizeqiang/miniconda3/envs/torch\nNVCC: Cuda compilation tools, release 11.6, V11.6.124\nGCC: gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-44)\nPyTorch: 1.13.1\nPyTorch compiling details: PyTorch built with:\n  - GCC 9.3\n  - C++ Version: 201402\n  - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications\n  - Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)\n  - OpenMP 201511 (a.k.a. OpenMP 4.5)\n  - LAPACK is enabled (usually provided by MKL)\n  - NNPACK is enabled\n  - CPU capability usage: AVX2\n  - CUDA Runtime 11.6\n  - 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\n  - CuDNN 8.3.2  (built against CUDA 11.5)\n  - Magma 2.6.1\n  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.6, CUDNN_VERSION=8.3.2, 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=1.13.1, 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, \n\nTorchVision: 0.14.1\nOpenCV: 4.7.0\nMMCV: 1.7.1\nMMCV Compiler: GCC 9.3\nMMCV CUDA Compiler: 11.6\nMMSegmentation: 0.30.0+c844fc6", "seed": 835892801, "exp_name": "deeplabv3plus_r101-d8_aspp_head_unet_fc_small_single_step_cityscapes_pretrained_freeze_embed_80k_cityscapes20.py", "mmseg_version": "0.30.0+c844fc6", "config": "norm_cfg = dict(type='SyncBN', requires_grad=True)\nmodel = dict(\n    type='EncoderDecoderFreeze',\n    pretrained=\n    'pretrained/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143-068fcfe9.pth',\n    backbone=dict(\n        type='ResNetV1cCustomInitWeights',\n        depth=101,\n        num_stages=4,\n        out_indices=(0, 1, 2, 3),\n        dilations=(1, 1, 2, 4),\n        strides=(1, 2, 1, 1),\n        norm_cfg=dict(type='SyncBN', requires_grad=True),\n        norm_eval=False,\n        style='pytorch',\n        contract_dilation=True,\n        pretrained=\n        'pretrained/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143-068fcfe9.pth'\n    ),\n    decode_head=dict(\n        type='DepthwiseSeparableASPPHeadUnetFCHeadSingleStep',\n        pretrained=\n        'pretrained/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143-068fcfe9.pth',\n        dim=256,\n        out_dim=256,\n        unet_channels=528,\n        dim_mults=[1, 1, 1],\n        cat_embedding_dim=16,\n        ignore_index=0,\n        in_channels=2048,\n        in_index=3,\n        channels=512,\n        dilations=(1, 12, 24, 36),\n        c1_in_channels=256,\n        c1_channels=48,\n        dropout_ratio=0.1,\n        num_classes=20,\n        norm_cfg=dict(type='SyncBN', requires_grad=True),\n        align_corners=False,\n        loss_decode=dict(\n            type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0)),\n    auxiliary_head=None,\n    train_cfg=dict(),\n    test_cfg=dict(mode='whole'),\n    freeze_parameters=['backbone', 'decode_head'])\ndataset_type = 'Cityscapes20Dataset'\ndata_root = 'data/cityscapes/'\nimg_norm_cfg = dict(\n    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)\ncrop_size = (512, 1024)\ntrain_pipeline = [\n    dict(type='LoadImageFromFile'),\n    dict(type='LoadAnnotationsCityscapes20'),\n    dict(type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),\n    dict(type='RandomCrop', crop_size=(512, 1024), cat_max_ratio=0.75),\n    dict(type='RandomFlip', prob=0.5),\n    dict(type='PhotoMetricDistortion'),\n    dict(\n        type='Normalize',\n        mean=[123.675, 116.28, 103.53],\n        std=[58.395, 57.12, 57.375],\n        to_rgb=True),\n    dict(type='Pad', size=(512, 1024), pad_val=0, seg_pad_val=0),\n    dict(type='DefaultFormatBundle'),\n    dict(type='Collect', keys=['img', 'gt_semantic_seg'])\n]\ntest_pipeline = [\n    dict(type='LoadImageFromFile'),\n    dict(\n        type='MultiScaleFlipAug',\n        img_scale=(2048, 1024),\n        flip=False,\n        transforms=[\n            dict(type='Resize', keep_ratio=True),\n            dict(type='RandomFlip'),\n            dict(\n                type='Normalize',\n                mean=[123.675, 116.28, 103.53],\n                std=[58.395, 57.12, 57.375],\n                to_rgb=True),\n            dict(type='ImageToTensor', keys=['img']),\n            dict(type='Collect', keys=['img'])\n        ])\n]\ndata = dict(\n    samples_per_gpu=2,\n    workers_per_gpu=2,\n    train=dict(\n        type='Cityscapes20Dataset',\n        data_root='data/cityscapes/',\n        img_dir='leftImg8bit/train',\n        ann_dir='gtFine/train',\n        pipeline=[\n            dict(type='LoadImageFromFile'),\n            dict(type='LoadAnnotationsCityscapes20'),\n            dict(\n                type='Resize', img_scale=(2048, 1024), ratio_range=(0.5, 2.0)),\n            dict(type='RandomCrop', crop_size=(512, 1024), cat_max_ratio=0.75),\n            dict(type='RandomFlip', prob=0.5),\n            dict(type='PhotoMetricDistortion'),\n            dict(\n                type='Normalize',\n                mean=[123.675, 116.28, 103.53],\n                std=[58.395, 57.12, 57.375],\n                to_rgb=True),\n            dict(type='Pad', size=(512, 1024), pad_val=0, seg_pad_val=0),\n            dict(type='DefaultFormatBundle'),\n            dict(type='Collect', keys=['img', 'gt_semantic_seg'])\n        ]),\n    val=dict(\n        type='Cityscapes20Dataset',\n        data_root='data/cityscapes/',\n        img_dir='leftImg8bit/val',\n        ann_dir='gtFine/val',\n        pipeline=[\n            dict(type='LoadImageFromFile'),\n            dict(\n                type='MultiScaleFlipAug',\n                img_scale=(2048, 1024),\n                flip=False,\n                transforms=[\n                    dict(type='Resize', keep_ratio=True),\n                    dict(type='RandomFlip'),\n                    dict(\n                        type='Normalize',\n                        mean=[123.675, 116.28, 103.53],\n                        std=[58.395, 57.12, 57.375],\n                        to_rgb=True),\n                    dict(type='ImageToTensor', keys=['img']),\n                    dict(type='Collect', keys=['img'])\n                ])\n        ]),\n    test=dict(\n        type='Cityscapes20Dataset',\n        data_root='data/cityscapes/',\n        img_dir='leftImg8bit/val',\n        ann_dir='gtFine/val',\n        pipeline=[\n            dict(type='LoadImageFromFile'),\n            dict(\n                type='MultiScaleFlipAug',\n                img_scale=(2048, 1024),\n                flip=False,\n                transforms=[\n                    dict(type='Resize', keep_ratio=True),\n                    dict(type='RandomFlip'),\n                    dict(\n                        type='Normalize',\n                        mean=[123.675, 116.28, 103.53],\n                        std=[58.395, 57.12, 57.375],\n                        to_rgb=True),\n                    dict(type='ImageToTensor', keys=['img']),\n                    dict(type='Collect', keys=['img'])\n                ])\n        ]))\nlog_config = dict(\n    interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)])\ndist_params = dict(backend='nccl')\nlog_level = 'INFO'\nload_from = None\nresume_from = None\nworkflow = [('train', 1)]\ncudnn_benchmark = True\noptimizer = dict(\n    type='AdamW', lr=0.00015, betas=[0.9, 0.96], weight_decay=0.045)\noptimizer_config = dict()\nlr_config = dict(\n    policy='step',\n    warmup='linear',\n    warmup_iters=1000,\n    warmup_ratio=1e-06,\n    step=10000,\n    gamma=0.5,\n    min_lr=1e-06,\n    by_epoch=False)\nrunner = dict(type='IterBasedRunner', max_iters=80000)\ncheckpoint_config = dict(by_epoch=False, interval=8000, max_keep_ckpts=1)\nevaluation = dict(\n    interval=8000, metric='mIoU', pre_eval=True, save_best='mIoU')\ncheckpoint = 'pretrained/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143-068fcfe9.pth'\nwork_dir = './work_dirs2/deeplabv3plus_r101-d8_aspp_head_unet_fc_small_single_step_cityscapes_pretrained_freeze_embed_80k_cityscapes20'\ngpu_ids = range(0, 8)\nauto_resume = True\ndevice = 'cuda'\nseed = 835892801\n", "CLASSES": ["background", "road", "sidewalk", "building", "wall", "fence", "pole", "traffic light", "traffic sign", "vegetation", "terrain", "sky", "person", "rider", "car", "truck", "bus", "train", "motorcycle", "bicycle"], "PALETTE": [[0, 0, 0], [128, 64, 128], [244, 35, 232], [70, 70, 70], [102, 102, 156], [190, 153, 153], [153, 153, 153], [250, 170, 30], [220, 220, 0], [107, 142, 35], [152, 251, 152], [70, 130, 180], [220, 20, 60], [255, 0, 0], [0, 0, 142], [0, 0, 70], [0, 60, 100], [0, 80, 100], [0, 0, 230], [119, 11, 32]], "hook_msgs": {}}
{"mode": "train", "epoch": 1, "iter": 50, "lr": 1e-05, "memory": 67605, "data_time": 0.01446, "decode.loss_ce": 1.8576, "decode.acc_seg": 63.82413, "loss": 1.8576, "time": 0.66091}