{"env_info": "sys.platform: linux\nPython: 3.8.0 | packaged by conda-forge | (default, Nov 22 2019, 19:11:38) [GCC 7.3.0]\nCUDA available: True\nGPU 0,1: NVIDIA RTX A6000\nCUDA_HOME: /usr/local/cuda\nNVCC: Cuda compilation tools, release 11.6, V11.6.124\nGCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0\nPyTorch: 1.9.0\nPyTorch compiling details: PyTorch built with:\n  - GCC 7.5\n  - C++ Version: 201402\n  - Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications\n  - OpenMP 201511 (a.k.a. OpenMP 4.5)\n  - NNPACK is enabled\n  - CPU capability usage: AVX2\n  - CUDA Runtime 11.3\n  - Built with CUDA Runtime 11.2\n  - NVCC architecture flags: -gencode;arch=compute_35,code=sm_35;-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_50,code=compute_50\n  - CuDNN 8.4.1  (built against CUDA 11.6)\n    - Built with CuDNN 8.2.1\n  - Magma 2.5.4\n  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.2, CUDNN_VERSION=8.2.1, CXX_COMPILER=/home/conda/feedstock_root/build_artifacts/pytorch-recipe_1627889194240/_build_env/bin/x86_64-conda-linux-gnu-c++, CXX_FLAGS=-std=c++14 -fmessage-length=0 -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O2 -ffunction-sections -pipe -isystem /home/conda/feedstock_root/build_artifacts/pytorch-recipe_1627889194240/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placeh/include -fdebug-prefix-map=/home/conda/feedstock_root/build_artifacts/pytorch-recipe_1627889194240/work=/usr/local/src/conda/pytorch-1.9.0 -fdebug-prefix-map=/home/conda/feedstock_root/build_artifacts/pytorch-recipe_1627889194240/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placeh=/usr/local/src/conda-prefix -I/usr/local/cuda/include -Wno-deprecated-declarations -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -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-variable -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=1.9.0, USE_CUDA=1, 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, \n\nTorchVision: 0.10.0a0\nOpenCV: 4.7.0\nMMCV: 1.6.0\nMMCV Compiler: GCC 9.4\nMMCV CUDA Compiler: 11.6\nMMDetection: 2.25.0+7abd76b", "config": "dataset_type = 'CocoDataset'\ndata_root = '/data/coco/'\nimg_norm_cfg = dict(\n    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)\ntrain_pipeline = [\n    dict(type='LoadImageFromFile', to_float32=True),\n    dict(type='LoadAnnotations', with_bbox=True, with_mask=False),\n    dict(type='GenerateBoxMask'),\n    dict(type='RandomFlip', flip_ratio=0.5),\n    dict(\n        type='Resize',\n        img_scale=(800, 1333),\n        multiscale_mode='value',\n        keep_ratio=True),\n    dict(type='Pad', size_divisor=32),\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='DefaultFormatBundle', img_to_float=True),\n    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks'])\n]\ntest_pipeline = [\n    dict(type='LoadImageFromFile'),\n    dict(\n        type='MultiScaleFlipAug',\n        img_scale=(1333, 800),\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='Pad', size_divisor=32),\n            dict(type='ImageToTensor', keys=['img']),\n            dict(type='Collect', keys=['img'])\n        ])\n]\ndata = dict(\n    samples_per_gpu=6,\n    workers_per_gpu=20,\n    train=dict(\n        type='CocoDataset',\n        ann_file='/data/cvprw/AIC23/dataset/coco_AIC23/train/train.json',\n        img_prefix='/data/cvprw/AIC23/dataset/train_result/detect_result',\n        pipeline=[\n            dict(type='LoadImageFromFile', to_float32=True),\n            dict(type='LoadAnnotations', with_bbox=True, with_mask=False),\n            dict(type='GenerateBoxMask'),\n            dict(type='RandomFlip', flip_ratio=0.5),\n            dict(\n                type='Resize',\n                img_scale=(800, 1333),\n                multiscale_mode='value',\n                keep_ratio=True),\n            dict(type='Pad', size_divisor=32),\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='DefaultFormatBundle', img_to_float=True),\n            dict(\n                type='Collect',\n                keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks'])\n        ],\n        classes=('person', 'none')),\n    val=dict(\n        type='CocoDataset',\n        ann_file='/data/cvprw/AIC23/dataset/coco_AIC23/val/val.json',\n        img_prefix='/data/cvprw/AIC23/dataset/val_result/detect_result',\n        pipeline=[\n            dict(type='LoadImageFromFile'),\n            dict(\n                type='MultiScaleFlipAug',\n                img_scale=(1333, 800),\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='Pad', size_divisor=32),\n                    dict(type='ImageToTensor', keys=['img']),\n                    dict(type='Collect', keys=['img'])\n                ])\n        ],\n        classes=('person', 'none')),\n    test=dict(\n        type='CocoDataset',\n        ann_file='/data/cvprw/AIC23/dataset/coco_AIC23/val/val.json',\n        img_prefix='/data/cvprw/AIC23/dataset/val_result/detect_result',\n        pipeline=[\n            dict(type='LoadImageFromFile'),\n            dict(\n                type='MultiScaleFlipAug',\n                img_scale=(1333, 800),\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='Pad', size_divisor=32),\n                    dict(type='ImageToTensor', keys=['img']),\n                    dict(type='Collect', keys=['img'])\n                ])\n        ],\n        classes=('person', 'none')))\nevaluation = dict(\n    interval=20000,\n    metric=['bbox', 'segm'],\n    dynamic_intervals=[(365001, 368750)],\n    classwise=True)\nlog_config = dict(\n    interval=50, hooks=[dict(type='TextLoggerHook', by_epoch=False)])\ncustom_hooks = [dict(type='NumClassCheckHook')]\ndist_params = dict(backend='nccl')\nlog_level = 'INFO'\nload_from = None\nresume_from = None\nworkflow = [('train', 5000)]\nopencv_num_threads = 0\nmp_start_method = 'fork'\nauto_scale_lr = dict(enable=False, base_batch_size=16)\nmodel = dict(\n    type='Box2Mask',\n    backbone=dict(\n        type='ResNet',\n        depth=101,\n        num_stages=4,\n        out_indices=(0, 1, 2, 3),\n        frozen_stages=-1,\n        norm_cfg=dict(type='BN', requires_grad=False),\n        norm_eval=True,\n        style='pytorch',\n        init_cfg=dict(\n            type='Pretrained',\n            checkpoint=\n            'https://download.pytorch.org/models/resnet101-b641f3a9.pth')),\n    panoptic_head=dict(\n        type='Box2MaskHead',\n        in_channels=[256, 512, 1024, 2048],\n        strides=[4, 8, 16, 32],\n        feat_channels=256,\n        out_channels=256,\n        num_things_classes=2,\n        num_stuff_classes=0,\n        num_queries=100,\n        num_transformer_feat_level=3,\n        pixel_decoder=dict(\n            type='MSDeformAttnPixelDecoder',\n            num_outs=3,\n            norm_cfg=dict(type='GN', num_groups=32),\n            act_cfg=dict(type='ReLU'),\n            encoder=dict(\n                type='DetrTransformerEncoder',\n                num_layers=6,\n                transformerlayers=dict(\n                    type='BaseTransformerLayer',\n                    attn_cfgs=dict(\n                        type='MultiScaleDeformableAttention',\n                        embed_dims=256,\n                        num_heads=8,\n                        num_levels=3,\n                        num_points=4,\n                        im2col_step=64,\n                        dropout=0.0,\n                        batch_first=False,\n                        norm_cfg=None,\n                        init_cfg=None),\n                    ffn_cfgs=dict(\n                        type='FFN',\n                        embed_dims=256,\n                        feedforward_channels=1024,\n                        num_fcs=2,\n                        ffn_drop=0.0,\n                        act_cfg=dict(type='ReLU', inplace=True)),\n                    operation_order=('self_attn', 'norm', 'ffn', 'norm')),\n                init_cfg=None),\n            positional_encoding=dict(\n                type='SinePositionalEncoding', num_feats=128, normalize=True),\n            init_cfg=None),\n        enforce_decoder_input_project=False,\n        positional_encoding=dict(\n            type='SinePositionalEncoding', num_feats=128, normalize=True),\n        transformer_decoder=dict(\n            type='DetrTransformerDecoder',\n            return_intermediate=True,\n            num_layers=9,\n            transformerlayers=dict(\n                type='DetrTransformerDecoderLayer',\n                attn_cfgs=dict(\n                    type='MultiheadAttention',\n                    embed_dims=256,\n                    num_heads=8,\n                    attn_drop=0.0,\n                    proj_drop=0.0,\n                    dropout_layer=None,\n                    batch_first=False),\n                ffn_cfgs=dict(\n                    embed_dims=256,\n                    feedforward_channels=2048,\n                    num_fcs=2,\n                    act_cfg=dict(type='ReLU', inplace=True),\n                    ffn_drop=0.0,\n                    dropout_layer=None,\n                    add_identity=True),\n                feedforward_channels=2048,\n                operation_order=('cross_attn', 'norm', 'self_attn', 'norm',\n                                 'ffn', 'norm')),\n            init_cfg=None),\n        loss_cls=dict(\n            type='CrossEntropyLoss',\n            use_sigmoid=False,\n            loss_weight=2.0,\n            reduction='mean',\n            class_weight=[1.0, 1.0, 0.1]),\n        loss_mask=dict(type='LevelsetLoss', loss_weight=1.0),\n        loss_box=dict(type='BoxProjectionLoss', loss_weight=5.0)),\n    panoptic_fusion_head=dict(\n        type='MaskFormerFusionHead',\n        num_things_classes=2,\n        num_stuff_classes=0,\n        loss_panoptic=None,\n        init_cfg=None),\n    train_cfg=dict(\n        assigner=dict(\n            type='MaskHungarianAssigner',\n            cls_cost=dict(type='ClassificationCost', weight=2.0),\n            dice_cost=dict(\n                type='BoxMatchingCost', weight=5.0, pred_act=True, eps=1.0)),\n        sampler=dict(type='MaskPseudoSampler')),\n    test_cfg=dict(\n        panoptic_on=False,\n        semantic_on=False,\n        instance_on=True,\n        max_per_image=100,\n        iou_thr=0.8,\n        filter_low_score=True),\n    init_cfg=None)\nimage_size = (800, 1333)\npad_cfg = dict(img=(128, 128, 128), masks=0, seg=255)\nembed_multi = dict(lr_mult=1.0, decay_mult=0.0)\noptimizer = dict(\n    type='AdamW',\n    lr=0.0001,\n    weight_decay=0.05,\n    eps=1e-08,\n    betas=(0.9, 0.999),\n    paramwise_cfg=dict(\n        custom_keys=dict(\n            backbone=dict(lr_mult=0.1, decay_mult=1.0),\n            query_embed=dict(lr_mult=1.0, decay_mult=0.0),\n            query_feat=dict(lr_mult=1.0, decay_mult=0.0),\n            level_embed=dict(lr_mult=1.0, decay_mult=0.0)),\n        norm_decay_mult=0.0))\noptimizer_config = dict(grad_clip=dict(max_norm=0.01, norm_type=2))\nlr_config = dict(\n    policy='step',\n    gamma=0.1,\n    by_epoch=False,\n    step=[327778, 355092],\n    warmup='linear',\n    warmup_by_epoch=False,\n    warmup_ratio=1.0,\n    warmup_iters=10)\nmax_iters = 368750\nrunner = dict(type='IterBasedRunner', max_iters=368750)\ninterval = 5000\ncheckpoint_config = dict(\n    by_epoch=False, interval=5000, save_last=True, max_keep_ckpts=3)\ndynamic_intervals = [(365001, 368750)]\nfind_unused_parameters = True\nwork_dir = './work_dirs/box2mask_r101_coco_50e'\nclasses_list = ('person', 'none')\nclass_num = 2\nauto_resume = False\ngpu_ids = range(0, 2)\n", "seed": 751186076, "exp_name": "resnet-101.py"}
{"mode": "train", "epoch": 1, "iter": 50, "lr": 1e-05, "memory": 37877, "data_time": 0.21878, "loss_cls": 1.06176, "loss_project": 4.98895, "loss_levelset": 0.08231, "d0.loss_cls": 1.94318, "d0.loss_project": 4.50304, "d0.loss_levelset": 0.08942, "d1.loss_cls": 0.52765, "d1.loss_project": 4.51126, "d1.loss_levelset": 0.09445, "d2.loss_cls": 0.52774, "d2.loss_project": 4.56764, "d2.loss_levelset": 0.09511, "d3.loss_cls": 0.61199, "d3.loss_project": 4.61094, "d3.loss_levelset": 0.0971, "d4.loss_cls": 0.6885, "d4.loss_project": 4.68854, "d4.loss_levelset": 0.09596, "d5.loss_cls": 0.77901, "d5.loss_project": 4.72174, "d5.loss_levelset": 0.09253, "d6.loss_cls": 0.84941, "d6.loss_project": 4.85147, "d6.loss_levelset": 0.09345, "d7.loss_cls": 0.89794, "d7.loss_project": 4.88195, "d7.loss_levelset": 0.0889, "d8.loss_cls": 0.97069, "d8.loss_project": 4.94791, "d8.loss_levelset": 0.08875, "loss": 57.04929, "grad_norm": 189.26932, "time": 2.77895}