{"env_info": "sys.platform: linux\nPython: 3.8.13 (default, Mar 28 2022, 11:38:47) [GCC 7.5.0]\nCUDA available: True\nGPU 0: NVIDIA A100-SXM4-80GB\nCUDA_HOME: /mnt/cache/share/cuda-11.1\nNVCC: Cuda compilation tools, release 11.1, V11.1.74\nGCC: gcc (GCC) 5.4.0\nPyTorch: 1.11.0+cu113\nPyTorch compiling details: PyTorch built with:\n  - GCC 7.3\n  - C++ Version: 201402\n  - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications\n  - Intel(R) MKL-DNN v2.5.2 (Git Hash a9302535553c73243c632ad3c4c80beec3d19a1e)\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 11.3\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_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\n  - CuDNN 8.2\n  - Magma 2.5.2\n  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2.0, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -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 -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -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 -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.11.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, \n\nTorchVision: 0.12.0+cu113\nOpenCV: 4.5.5\nMMCV: 1.5.0\nMMCV Compiler: GCC 7.3\nMMCV CUDA Compiler: not available\nMMClassification: 0.23.1+2cb879b", "seed": 2045970967, "mmcls_version": "0.23.1", "config": "dataset_type = 'VOC'\nimg_norm_cfg = dict(mean=[0, 0, 0], std=[255, 255, 255], to_rgb=True)\ntrain_pipeline = [\n    dict(type='LoadImageFromFile'),\n    dict(type='RandomResizedCrop', size=448, scale=(0.7, 1.0)),\n    dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),\n    dict(type='Normalize', mean=[0, 0, 0], std=[255, 255, 255], to_rgb=True),\n    dict(type='ImageToTensor', keys=['img']),\n    dict(type='ToTensor', keys=['gt_label']),\n    dict(type='Collect', keys=['img', 'gt_label'])\n]\ntest_pipeline = [\n    dict(type='LoadImageFromFile'),\n    dict(type='Resize', size=448),\n    dict(type='Normalize', mean=[0, 0, 0], std=[255, 255, 255], to_rgb=True),\n    dict(type='ImageToTensor', keys=['img']),\n    dict(type='Collect', keys=['img'])\n]\ndata = dict(\n    samples_per_gpu=16,\n    workers_per_gpu=2,\n    train=dict(\n        type='VOC',\n        data_prefix='data/VOCdevkit/VOC2007/',\n        ann_file='data/VOCdevkit/VOC2007/ImageSets/Main/trainval.txt',\n        pipeline=[\n            dict(type='LoadImageFromFile'),\n            dict(type='RandomResizedCrop', size=448, scale=(0.7, 1.0)),\n            dict(type='RandomFlip', flip_prob=0.5, direction='horizontal'),\n            dict(\n                type='Normalize',\n                mean=[0, 0, 0],\n                std=[255, 255, 255],\n                to_rgb=True),\n            dict(type='ImageToTensor', keys=['img']),\n            dict(type='ToTensor', keys=['gt_label']),\n            dict(type='Collect', keys=['img', 'gt_label'])\n        ],\n        difficult_as_postive=False),\n    val=dict(\n        type='VOC',\n        data_prefix='data/VOCdevkit/VOC2007/',\n        ann_file='data/VOCdevkit/VOC2007/ImageSets/Main/test.txt',\n        pipeline=[\n            dict(type='LoadImageFromFile'),\n            dict(type='Resize', size=448),\n            dict(\n                type='Normalize',\n                mean=[0, 0, 0],\n                std=[255, 255, 255],\n                to_rgb=True),\n            dict(type='ImageToTensor', keys=['img']),\n            dict(type='Collect', keys=['img'])\n        ]),\n    test=dict(\n        type='VOC',\n        data_prefix='data/VOCdevkit/VOC2007/',\n        ann_file='data/VOCdevkit/VOC2007/ImageSets/Main/test.txt',\n        pipeline=[\n            dict(type='LoadImageFromFile'),\n            dict(type='Resize', size=448),\n            dict(\n                type='Normalize',\n                mean=[0, 0, 0],\n                std=[255, 255, 255],\n                to_rgb=True),\n            dict(type='ImageToTensor', keys=['img']),\n            dict(type='Collect', keys=['img'])\n        ]))\nevaluation = dict(\n    interval=1, metric=['mAP', 'CP', 'OP', 'CR', 'OR', 'CF1', 'OF1'])\ncheckpoint_config = dict(interval=1)\nlog_config = dict(interval=100, hooks=[dict(type='TextLoggerHook')])\ndist_params = dict(backend='nccl')\nlog_level = 'INFO'\nload_from = None\nresume_from = None\nworkflow = [('train', 1)]\ncheckpoint = 'https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_8xb32_in1k_20210831-539c63f8.pth'\nmodel = dict(\n    type='ImageClassifier',\n    backbone=dict(\n        type='ResNet',\n        depth=101,\n        num_stages=4,\n        out_indices=(3, ),\n        style='pytorch',\n        init_cfg=dict(\n            type='Pretrained',\n            checkpoint=\n            'https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_8xb32_in1k_20210831-539c63f8.pth',\n            prefix='backbone')),\n    neck=None,\n    head=dict(\n        type='CSRAClsHead',\n        num_classes=20,\n        in_channels=2048,\n        num_heads=1,\n        lam=0.1,\n        loss=dict(type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)))\noptimizer = dict(\n    type='SGD',\n    lr=0.0002,\n    momentum=0.9,\n    weight_decay=0.0001,\n    paramwise_cfg=dict(custom_keys=dict(head=dict(lr_mult=10))))\noptimizer_config = dict(grad_clip=None)\nlr_config = dict(\n    policy='step',\n    step=6,\n    gamma=0.1,\n    warmup='linear',\n    warmup_iters=1,\n    warmup_ratio=1e-07,\n    warmup_by_epoch=True)\nrunner = dict(type='EpochBasedRunner', max_epochs=20)\nwork_dir = '/mnt/lustre/yuzhaohui/csra/final'\ngpu_ids = range(0, 1)\nseed = 2045970967\n", "CLASSES": ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]}
{"mode": "train", "epoch": 1, "iter": 100, "lr": 6e-05, "memory": 8517, "data_time": 0.31258, "loss": 5.24758, "time": 0.45161}
{"mode": "train", "epoch": 1, "iter": 200, "lr": 0.00013, "memory": 8517, "data_time": 0.31265, "loss": 2.19151, "time": 0.44261}
{"mode": "train", "epoch": 1, "iter": 300, "lr": 0.00019, "memory": 8517, "data_time": 0.26201, "loss": 1.5084, "time": 0.39427}
{"mode": "val", "epoch": 1, "iter": 310, "lr": 0.0002, "mAP": 91.93045, "CP": 89.29573, "CR": 77.76075, "CF1": 83.13, "OP": 90.5804, "OR": 81.44874, "OF1": 85.77221}
{"mode": "train", "epoch": 2, "iter": 100, "lr": 0.0002, "memory": 8517, "data_time": 0.39005, "loss": 1.19055, "time": 0.52513}
{"mode": "train", "epoch": 2, "iter": 200, "lr": 0.0002, "memory": 8517, "data_time": 0.23136, "loss": 1.08206, "time": 0.36331}
{"mode": "train", "epoch": 2, "iter": 300, "lr": 0.0002, "memory": 8517, "data_time": 0.25311, "loss": 1.07799, "time": 0.37985}
{"mode": "val", "epoch": 2, "iter": 310, "lr": 0.0002, "mAP": 94.1239, "CP": 89.75043, "CR": 86.26344, "CF1": 87.9724, "OP": 91.58823, "OR": 87.4091, "OF1": 89.44988}
{"mode": "train", "epoch": 3, "iter": 100, "lr": 0.0002, "memory": 8517, "data_time": 0.32729, "loss": 0.90323, "time": 0.46169}
{"mode": "train", "epoch": 3, "iter": 200, "lr": 0.0002, "memory": 8517, "data_time": 0.35226, "loss": 0.81732, "time": 0.48443}
{"mode": "train", "epoch": 3, "iter": 300, "lr": 0.0002, "memory": 8517, "data_time": 0.27828, "loss": 0.84434, "time": 0.41165}
{"mode": "val", "epoch": 3, "iter": 310, "lr": 0.0002, "mAP": 94.5641, "CP": 92.49461, "CR": 84.39038, "CF1": 88.25684, "OP": 94.35834, "OR": 86.81021, "OF1": 90.42703}
{"mode": "train", "epoch": 4, "iter": 100, "lr": 0.0002, "memory": 8517, "data_time": 0.37227, "loss": 0.74014, "time": 0.51158}
{"mode": "train", "epoch": 4, "iter": 200, "lr": 0.0002, "memory": 8517, "data_time": 0.35571, "loss": 0.65545, "time": 0.48446}
{"mode": "train", "epoch": 4, "iter": 300, "lr": 0.0002, "memory": 8517, "data_time": 0.32175, "loss": 0.71177, "time": 0.45741}
{"mode": "val", "epoch": 4, "iter": 310, "lr": 0.0002, "mAP": 94.75914, "CP": 90.19714, "CR": 87.46538, "CF1": 88.81026, "OP": 92.27914, "OR": 88.62113, "OF1": 90.41315}
{"mode": "train", "epoch": 5, "iter": 100, "lr": 0.0002, "memory": 8517, "data_time": 0.33932, "loss": 0.61444, "time": 0.48119}
{"mode": "train", "epoch": 5, "iter": 200, "lr": 0.0002, "memory": 8517, "data_time": 0.33471, "loss": 0.60183, "time": 0.46476}
{"mode": "train", "epoch": 5, "iter": 300, "lr": 0.0002, "memory": 8517, "data_time": 0.278, "loss": 0.59533, "time": 0.4103}
{"mode": "val", "epoch": 5, "iter": 310, "lr": 0.0002, "mAP": 94.99195, "CP": 92.34858, "CR": 85.35512, "CF1": 88.71423, "OP": 93.64717, "OR": 87.6515, "OF1": 90.5502}
{"mode": "train", "epoch": 6, "iter": 100, "lr": 0.0002, "memory": 8517, "data_time": 0.39405, "loss": 0.48353, "time": 0.53238}
{"mode": "train", "epoch": 6, "iter": 200, "lr": 0.0002, "memory": 8517, "data_time": 0.34069, "loss": 0.5541, "time": 0.47057}
{"mode": "train", "epoch": 6, "iter": 300, "lr": 0.0002, "memory": 8517, "data_time": 0.33974, "loss": 0.4799, "time": 0.47542}
{"mode": "val", "epoch": 6, "iter": 310, "lr": 0.0002, "mAP": 94.93356, "CP": 91.74028, "CR": 86.64374, "CF1": 89.11921, "OP": 93.71696, "OR": 88.47854, "OF1": 91.02244}
{"mode": "train", "epoch": 7, "iter": 100, "lr": 2e-05, "memory": 8517, "data_time": 0.34158, "loss": 0.43681, "time": 0.47248}
{"mode": "train", "epoch": 7, "iter": 200, "lr": 2e-05, "memory": 8517, "data_time": 0.3048, "loss": 0.41401, "time": 0.43965}
{"mode": "train", "epoch": 7, "iter": 300, "lr": 2e-05, "memory": 8517, "data_time": 0.33433, "loss": 0.42557, "time": 0.47389}
{"mode": "val", "epoch": 7, "iter": 310, "lr": 2e-05, "mAP": 95.01679, "CP": 92.26773, "CR": 86.57511, "CF1": 89.33082, "OP": 94.16325, "OR": 88.33595, "OF1": 91.15656}
{"mode": "train", "epoch": 8, "iter": 100, "lr": 2e-05, "memory": 8517, "data_time": 0.33196, "loss": 0.41396, "time": 0.46949}
{"mode": "train", "epoch": 8, "iter": 200, "lr": 2e-05, "memory": 8517, "data_time": 0.34813, "loss": 0.37473, "time": 0.48306}
{"mode": "train", "epoch": 8, "iter": 300, "lr": 2e-05, "memory": 8517, "data_time": 0.36315, "loss": 0.37477, "time": 0.49846}
{"mode": "val", "epoch": 8, "iter": 310, "lr": 2e-05, "mAP": 95.01164, "CP": 91.67507, "CR": 86.57629, "CF1": 89.05275, "OP": 93.57466, "OR": 88.46428, "OF1": 90.94774}
{"mode": "train", "epoch": 9, "iter": 100, "lr": 2e-05, "memory": 8517, "data_time": 0.30173, "loss": 0.35031, "time": 0.449}
{"mode": "train", "epoch": 9, "iter": 200, "lr": 2e-05, "memory": 8517, "data_time": 0.35342, "loss": 0.40111, "time": 0.49034}
{"mode": "train", "epoch": 9, "iter": 300, "lr": 2e-05, "memory": 8517, "data_time": 0.32019, "loss": 0.40577, "time": 0.45651}
{"mode": "val", "epoch": 9, "iter": 310, "lr": 2e-05, "mAP": 95.01925, "CP": 91.6896, "CR": 86.93354, "CF1": 89.24825, "OP": 93.45318, "OR": 88.94909, "OF1": 91.14553}
{"mode": "train", "epoch": 10, "iter": 100, "lr": 2e-05, "memory": 8517, "data_time": 0.2426, "loss": 0.37213, "time": 0.38375}
{"mode": "train", "epoch": 10, "iter": 200, "lr": 2e-05, "memory": 8517, "data_time": 0.28528, "loss": 0.39921, "time": 0.41642}
{"mode": "train", "epoch": 10, "iter": 300, "lr": 2e-05, "memory": 8517, "data_time": 0.29487, "loss": 0.36386, "time": 0.43384}
{"mode": "val", "epoch": 10, "iter": 310, "lr": 2e-05, "mAP": 95.01866, "CP": 92.27575, "CR": 86.40133, "CF1": 89.24198, "OP": 94.26305, "OR": 88.09354, "OF1": 91.07393}
{"mode": "train", "epoch": 11, "iter": 100, "lr": 2e-05, "memory": 8517, "data_time": 0.2029, "loss": 0.37012, "time": 0.33666}
{"mode": "train", "epoch": 11, "iter": 200, "lr": 2e-05, "memory": 8517, "data_time": 0.24196, "loss": 0.41127, "time": 0.37748}
{"mode": "train", "epoch": 11, "iter": 300, "lr": 2e-05, "memory": 8517, "data_time": 0.30439, "loss": 0.36373, "time": 0.43539}
{"mode": "val", "epoch": 11, "iter": 310, "lr": 2e-05, "mAP": 95.05301, "CP": 91.47371, "CR": 87.12137, "CF1": 89.24451, "OP": 93.59784, "OR": 88.8065, "OF1": 91.13924}
{"mode": "train", "epoch": 12, "iter": 100, "lr": 2e-05, "memory": 8517, "data_time": 0.30013, "loss": 0.37325, "time": 0.44298}
{"mode": "train", "epoch": 12, "iter": 200, "lr": 2e-05, "memory": 8517, "data_time": 0.28779, "loss": 0.36495, "time": 0.41335}
{"mode": "train", "epoch": 12, "iter": 300, "lr": 2e-05, "memory": 8517, "data_time": 0.30029, "loss": 0.38392, "time": 0.43184}
{"mode": "val", "epoch": 12, "iter": 310, "lr": 2e-05, "mAP": 94.98622, "CP": 91.92645, "CR": 86.46927, "CF1": 89.11439, "OP": 93.8408, "OR": 88.4215, "OF1": 91.05058}
{"mode": "train", "epoch": 13, "iter": 100, "lr": 0.0, "memory": 8517, "data_time": 0.29639, "loss": 0.36666, "time": 0.43361}
{"mode": "train", "epoch": 13, "iter": 200, "lr": 0.0, "memory": 8517, "data_time": 0.36886, "loss": 0.35019, "time": 0.49956}
{"mode": "train", "epoch": 13, "iter": 300, "lr": 0.0, "memory": 8517, "data_time": 0.31498, "loss": 0.37988, "time": 0.44733}
{"mode": "val", "epoch": 13, "iter": 310, "lr": 0.0, "mAP": 95.00614, "CP": 91.5125, "CR": 87.07498, "CF1": 89.23861, "OP": 93.58184, "OR": 88.77798, "OF1": 91.11664}
{"mode": "train", "epoch": 14, "iter": 100, "lr": 0.0, "memory": 8517, "data_time": 0.33758, "loss": 0.36469, "time": 0.4688}
{"mode": "train", "epoch": 14, "iter": 200, "lr": 0.0, "memory": 8517, "data_time": 0.33758, "loss": 0.34569, "time": 0.47348}
{"mode": "train", "epoch": 14, "iter": 300, "lr": 0.0, "memory": 8517, "data_time": 0.30596, "loss": 0.33942, "time": 0.43752}
{"mode": "val", "epoch": 14, "iter": 310, "lr": 0.0, "mAP": 95.04142, "CP": 92.18998, "CR": 86.46409, "CF1": 89.23528, "OP": 94.14634, "OR": 88.06502, "OF1": 91.0042}
{"mode": "train", "epoch": 15, "iter": 100, "lr": 0.0, "memory": 8517, "data_time": 0.38029, "loss": 0.35332, "time": 0.51991}
{"mode": "train", "epoch": 15, "iter": 200, "lr": 0.0, "memory": 8517, "data_time": 0.33375, "loss": 0.35839, "time": 0.46826}
{"mode": "train", "epoch": 15, "iter": 300, "lr": 0.0, "memory": 8517, "data_time": 0.37051, "loss": 0.36708, "time": 0.5035}
{"mode": "val", "epoch": 15, "iter": 310, "lr": 0.0, "mAP": 94.99121, "CP": 91.95761, "CR": 86.33566, "CF1": 89.058, "OP": 94.04327, "OR": 88.02224, "OF1": 90.9332}
{"mode": "train", "epoch": 16, "iter": 100, "lr": 0.0, "memory": 8517, "data_time": 0.38824, "loss": 0.34927, "time": 0.52697}
{"mode": "train", "epoch": 16, "iter": 200, "lr": 0.0, "memory": 8517, "data_time": 0.32964, "loss": 0.35058, "time": 0.46581}
{"mode": "train", "epoch": 16, "iter": 300, "lr": 0.0, "memory": 8517, "data_time": 0.30355, "loss": 0.34972, "time": 0.43708}
{"mode": "val", "epoch": 16, "iter": 310, "lr": 0.0, "mAP": 95.04966, "CP": 92.26471, "CR": 86.71448, "CF1": 89.40354, "OP": 94.14264, "OR": 88.46428, "OF1": 91.21517}
{"mode": "train", "epoch": 17, "iter": 100, "lr": 0.0, "memory": 8517, "data_time": 0.39397, "loss": 0.33805, "time": 0.52872}
{"mode": "train", "epoch": 17, "iter": 200, "lr": 0.0, "memory": 8517, "data_time": 0.33222, "loss": 0.35739, "time": 0.47279}
{"mode": "train", "epoch": 17, "iter": 300, "lr": 0.0, "memory": 8517, "data_time": 0.29073, "loss": 0.3552, "time": 0.42406}
{"mode": "val", "epoch": 17, "iter": 310, "lr": 0.0, "mAP": 94.94824, "CP": 91.86617, "CR": 87.08003, "CF1": 89.40909, "OP": 93.86401, "OR": 88.77798, "OF1": 91.25018}
{"mode": "train", "epoch": 18, "iter": 100, "lr": 0.0, "memory": 8517, "data_time": 0.37947, "loss": 0.34978, "time": 0.51582}
{"mode": "train", "epoch": 18, "iter": 200, "lr": 0.0, "memory": 8517, "data_time": 0.37795, "loss": 0.34522, "time": 0.51238}
{"mode": "train", "epoch": 18, "iter": 300, "lr": 0.0, "memory": 8517, "data_time": 0.40505, "loss": 0.33318, "time": 0.54058}
{"mode": "val", "epoch": 18, "iter": 310, "lr": 0.0, "mAP": 94.9949, "CP": 92.31482, "CR": 86.35481, "CF1": 89.23541, "OP": 94.06226, "OR": 88.32169, "OF1": 91.10163}
{"mode": "train", "epoch": 19, "iter": 100, "lr": 0.0, "memory": 8517, "data_time": 0.38704, "loss": 0.3567, "time": 0.52099}
{"mode": "train", "epoch": 19, "iter": 200, "lr": 0.0, "memory": 8517, "data_time": 0.3306, "loss": 0.33551, "time": 0.45975}
{"mode": "train", "epoch": 19, "iter": 300, "lr": 0.0, "memory": 8517, "data_time": 0.32516, "loss": 0.34797, "time": 0.4563}
{"mode": "val", "epoch": 19, "iter": 310, "lr": 0.0, "mAP": 94.99269, "CP": 92.15557, "CR": 86.21698, "CF1": 89.08742, "OP": 94.16336, "OR": 88.1078, "OF1": 91.03499}
{"mode": "train", "epoch": 20, "iter": 100, "lr": 0.0, "memory": 8517, "data_time": 0.33947, "loss": 0.37634, "time": 0.47167}
{"mode": "train", "epoch": 20, "iter": 200, "lr": 0.0, "memory": 8517, "data_time": 0.31724, "loss": 0.33469, "time": 0.44515}
{"mode": "train", "epoch": 20, "iter": 300, "lr": 0.0, "memory": 8517, "data_time": 0.3287, "loss": 0.33432, "time": 0.46011}
{"mode": "val", "epoch": 20, "iter": 310, "lr": 0.0, "mAP": 94.98606, "CP": 92.06705, "CR": 86.44007, "CF1": 89.16488, "OP": 93.97498, "OR": 87.85113, "OF1": 90.80993}