problem about: KeyError: 'loss_cls'

[JayYangSS]

I use soft_teacher_faster_rcnn_r50_caffe_fpn_coco_full_720k.py to start train process, but got KeyError problem, since I don't have unlabeled2017 , I use train2017 as labeled data, and use val2017 as unlabeled data to test the enviroment, is the problem associated with this operation?

"2021-10-21T11:21:15+08:00" 2021-10-21 11:21:15,622 - mmdet.ssod - INFO - Iter [2400/720000]    lr: 1.000e-02, eta: 7 days, 1:59:23, time: 0.846, data_time: 0.029, memory: 10432, ema_momentum: 0.9990, sup_loss_rpn_cls: nan, sup_loss_rpn_bbox: nan, sup_loss_cls: nan, sup_acc: 59.1420, sup_loss_bbox: nan, unsup_loss_rpn_cls: nan, unsup_loss_rpn_bbox: nan, unsup_loss_cls: nan, unsup_acc: 72.6390, unsup_loss_bbox: 0.0000, loss: nan
"2021-10-21T11:21:16+08:00" 2021-10-21 11:21:16,471 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:17+08:00" 2021-10-21 11:21:17,431 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:18+08:00" 2021-10-21 11:21:18,085 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:18+08:00" 2021-10-21 11:21:18,875 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:19+08:00" 2021-10-21 11:21:19,708 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:20+08:00" 2021-10-21 11:21:20,523 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:21+08:00" 2021-10-21 11:21:21,371 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:22+08:00" 2021-10-21 11:21:22,261 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:23+08:00" 2021-10-21 11:21:23,183 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:24+08:00" 2021-10-21 11:21:24,159 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:25+08:00" 2021-10-21 11:21:25,089 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:26+08:00" 2021-10-21 11:21:26,074 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:27+08:00" 2021-10-21 11:21:27,022 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:27+08:00" 2021-10-21 11:21:27,721 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:28+08:00" 2021-10-21 11:21:28,629 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:29+08:00" 2021-10-21 11:21:29,480 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:30+08:00" 2021-10-21 11:21:30,250 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:30+08:00" 2021-10-21 11:21:30,997 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:31+08:00" 2021-10-21 11:21:31,885 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:32+08:00" 2021-10-21 11:21:32,697 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:33+08:00" 2021-10-21 11:21:33,555 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:34+08:00" 2021-10-21 11:21:34,504 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:35+08:00" 2021-10-21 11:21:35,409 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:36+08:00" 2021-10-21 11:21:36,270 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:37+08:00" 2021-10-21 11:21:37,181 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:38+08:00" 2021-10-21 11:21:38,194 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:39+08:00" 2021-10-21 11:21:39,072 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T11:21:39+08:00" Traceback (most recent call last):
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/tools/train.py", line 198, in <module>
"2021-10-21T11:21:39+08:00"     main()
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/tools/train.py", line 193, in main
"2021-10-21T11:21:39+08:00"     meta=meta,
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/ssod/apis/train.py", line 206, in train_detector
"2021-10-21T11:21:39+08:00"     runner.run(data_loaders, cfg.workflow)
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/thirdparty/mmcv-1.3.9/mmcv/runner/iter_based_runner.py", line 133, in run
"2021-10-21T11:21:39+08:00"     iter_runner(iter_loaders[i], **kwargs)
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/thirdparty/mmcv-1.3.9/mmcv/runner/iter_based_runner.py", line 60, in train
"2021-10-21T11:21:39+08:00"     outputs = self.model.train_step(data_batch, self.optimizer, **kwargs)
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/thirdparty/mmcv-1.3.9/mmcv/parallel/distributed.py", line 53, in train_step
"2021-10-21T11:21:39+08:00"     output = self.module.train_step(*inputs[0], **kwargs[0])
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/thirdparty/mmdetection/mmdet/models/detectors/base.py", line 238, in train_step
"2021-10-21T11:21:39+08:00"     losses = self(**data)
"2021-10-21T11:21:39+08:00"   File "/usr/local/miniconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in __call__
"2021-10-21T11:21:39+08:00"     result = self.forward(*input, **kwargs)
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/thirdparty/mmcv-1.3.9/mmcv/runner/fp16_utils.py", line 130, in new_func
"2021-10-21T11:21:39+08:00"     output = old_func(*new_args, **new_kwargs)
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/thirdparty/mmdetection/mmdet/models/detectors/base.py", line 172, in forward
"2021-10-21T11:21:39+08:00"     return self.forward_train(img, img_metas, **kwargs)
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/ssod/models/soft_teacher.py", line 50, in forward_train
"2021-10-21T11:21:39+08:00"     data_groups["unsup_teacher"], data_groups["unsup_student"]
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/ssod/models/soft_teacher.py", line 77, in foward_unsup_train
"2021-10-21T11:21:39+08:00"     return self.compute_pseudo_label_loss(student_info, teacher_info)
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/ssod/models/soft_teacher.py", line 120, in compute_pseudo_label_loss
"2021-10-21T11:21:39+08:00"     student_info=student_info,
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/ssod/models/soft_teacher.py", line 243, in unsup_rcnn_cls_loss
"2021-10-21T11:21:39+08:00"     loss["loss_cls"] = loss["loss_cls"].sum() / max(bbox_targets[1].sum(), 1.0)
"2021-10-21T11:21:39+08:00" KeyError: 'loss_cls'
"2021-10-21T11:21:47+08:00" Traceback (most recent call last):
"2021-10-21T11:21:47+08:00"   File "/usr/local/miniconda3/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"2021-10-21T11:21:47+08:00"     "__main__", mod_spec)
"2021-10-21T11:21:47+08:00"   File "/usr/local/miniconda3/lib/python3.6/runpy.py", line 85, in _run_code
"2021-10-21T11:21:47+08:00"     exec(code, run_globals)
"2021-10-21T11:21:47+08:00"   File "/usr/local/miniconda3/lib/python3.6/site-packages/torch/distributed/launch.py", line 263, in <module>
"2021-10-21T11:21:47+08:00"     main()
"2021-10-21T11:21:47+08:00"   File "/usr/local/miniconda3/lib/python3.6/site-packages/torch/distributed/launch.py", line 259, in main
"2021-10-21T11:21:47+08:00"     cmd=cmd)
"2021-10-21T11:21:47+08:00" subprocess.CalledProcessError: Command '['/usr/bin/python', '-u', '/data1/train_code/SoftTeacher/tools/train.py', '--local_rank=0', '/data1/train_code/SoftTeacher/configs/exp-test/soft_teacher_faster_rcnn_r50_caffe_fpn_coco_full_720k.py', '--launcher', 'pytorch']' returned non-zero exit status 1.
"2021-10-21T11:21:47+08:00" [INFO] recv error: exit status 1
"2021-10-21T11:21:47+08:00" [ERROR] error happends during process: exit status 1
"2021-10-21T11:21:48+08:00" [INFO] still reserved
"2021-10-21T11:21:48+08:00" [INFO] recv flag (false)
"2021-10-21T11:21:48+08:00" [INFO] sleeping
"2021-10-21T11:22:03+08:00" [ERROR] kill process failed with error: timed out waiting for the condition

[MendelXu]

Could you upload the full log？

[JayYangSS]

Could you upload the full log？

"2021-10-21T10:45:16+08:00" [INFO] TASK_NAME=coco-full-train-4gpu-1
"2021-10-21T10:45:16+08:00" USER_NAME=jiyang5
"2021-10-21T10:45:16+08:00" TASKPLATFORM_NAME=train
"2021-10-21T10:45:16+08:00" DL_NODE_TYPE=1
"2021-10-21T10:45:16+08:00" DL_HOSTS_LIST=train-coco-full-train-4gpu-1:4
"2021-10-21T10:45:16+08:00" [INFO] localIp is 172.30.43.4
"2021-10-21T10:45:16+08:00" [INFO] single DL_HOST: train-coco-full-train-4gpu-1-0:4
"2021-10-21T10:45:16+08:00" [INFO] get bash path: /bin/bash
"2021-10-21T10:45:16+08:00" [INFO] already start process
"2021-10-21T10:45:26+08:00" fatal: Not a git repository (or any parent up to mount point /data1)
"2021-10-21T10:45:26+08:00" Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
"2021-10-21T10:45:26+08:00" 2021-10-21 10:45:26,416 - mmdet.ssod - INFO - [<StreamHandler <stderr> (INFO)>, <FileHandler /data1/train_code/SoftTeacher/workdir/soft_teacher_faster_rcnn_r50_caffe_fpn_adas_full_720k/20211021_104526.log (INFO)>]
"2021-10-21T10:45:26+08:00" 2021-10-21 10:45:26,416 - mmdet.ssod - INFO - Environment info:
"2021-10-21T10:45:26+08:00" ------------------------------------------------------------
"2021-10-21T10:45:26+08:00" sys.platform: linux
"2021-10-21T10:45:26+08:00" Python: 3.6.5 |Anaconda, Inc.| (default, Apr 29 2018, 16:14:56) [GCC 7.2.0]
"2021-10-21T10:45:26+08:00" CUDA available: True
"2021-10-21T10:45:26+08:00" GPU 0,1,2,3: Tesla V100-SXM2-32GB
"2021-10-21T10:45:26+08:00" CUDA_HOME: /usr/local/cuda
"2021-10-21T10:45:26+08:00" NVCC: Cuda compilation tools, release 10.1, V10.1.243
"2021-10-21T10:45:26+08:00" GCC: gcc (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609
"2021-10-21T10:45:26+08:00" PyTorch: 1.5.0+cu101
"2021-10-21T10:45:26+08:00" PyTorch compiling details: PyTorch built with:
"2021-10-21T10:45:26+08:00"   - GCC 7.3
"2021-10-21T10:45:26+08:00"   - C++ Version: 201402
"2021-10-21T10:45:26+08:00"   - Intel(R) Math Kernel Library Version 2019.0.5 Product Build 20190808 for Intel(R) 64 architecture applications
"2021-10-21T10:45:26+08:00"   - Intel(R) MKL-DNN v0.21.1 (Git Hash 7d2fd500bc78936d1d648ca713b901012f470dbc)
"2021-10-21T10:45:26+08:00"   - OpenMP 201511 (a.k.a. OpenMP 4.5)
"2021-10-21T10:45:26+08:00"   - NNPACK is enabled
"2021-10-21T10:45:26+08:00"   - CPU capability usage: AVX2
"2021-10-21T10:45:26+08:00"   - CUDA Runtime 10.1
"2021-10-21T10:45:26+08:00"   - 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_37,code=compute_37
"2021-10-21T10:45:26+08:00"   - CuDNN 7.6.3
"2021-10-21T10:45:26+08:00"   - Magma 2.5.2
"2021-10-21T10:45:26+08:00"   - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_INTERNAL_THREADPOOL_IMPL -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-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -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, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=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_STATIC_DISPATCH=OFF, 
"2021-10-21T10:45:26+08:00" 
"2021-10-21T10:45:26+08:00" TorchVision: 0.6.0+cu101
"2021-10-21T10:45:26+08:00" OpenCV: 4.4.0
"2021-10-21T10:45:26+08:00" MMCV: 1.3.9
"2021-10-21T10:45:26+08:00" MMCV Compiler: GCC 5.4
"2021-10-21T10:45:26+08:00" MMCV CUDA Compiler: 10.1
"2021-10-21T10:45:26+08:00" MMDetection: 2.16.0+
"2021-10-21T10:45:26+08:00" ------------------------------------------------------------
"2021-10-21T10:45:26+08:00" 
"2021-10-21T10:45:29+08:00" 2021-10-21 10:45:29,186 - mmdet.ssod - INFO - Distributed training: True
"2021-10-21T10:45:31+08:00" 2021-10-21 10:45:31,806 - mmdet.ssod - INFO - Config:
"2021-10-21T10:45:31+08:00" model = dict(
"2021-10-21T10:45:31+08:00"     type='SoftTeacher',
"2021-10-21T10:45:31+08:00"     model=dict(
"2021-10-21T10:45:31+08:00"         type='FasterRCNN',
"2021-10-21T10:45:31+08:00"         backbone=dict(
"2021-10-21T10:45:31+08:00"             type='ResNet',
"2021-10-21T10:45:31+08:00"             depth=50,
"2021-10-21T10:45:31+08:00"             num_stages=4,
"2021-10-21T10:45:31+08:00"             out_indices=(0, 1, 2, 3),
"2021-10-21T10:45:31+08:00"             frozen_stages=1,
"2021-10-21T10:45:31+08:00"             norm_cfg=dict(type='BN', requires_grad=False),
"2021-10-21T10:45:31+08:00"             norm_eval=True,
"2021-10-21T10:45:31+08:00"             style='caffe',
"2021-10-21T10:45:31+08:00"             init_cfg=dict(
"2021-10-21T10:45:31+08:00"                 type='Pretrained',
"2021-10-21T10:45:31+08:00"                 checkpoint='/data1/train_code/model_zoo/resnet50-19c8e357.pth')
"2021-10-21T10:45:31+08:00"         ),
"2021-10-21T10:45:31+08:00"         neck=dict(
"2021-10-21T10:45:31+08:00"             type='FPN',
"2021-10-21T10:45:31+08:00"             in_channels=[256, 512, 1024, 2048],
"2021-10-21T10:45:31+08:00"             out_channels=256,
"2021-10-21T10:45:31+08:00"             num_outs=5),
"2021-10-21T10:45:31+08:00"         rpn_head=dict(
"2021-10-21T10:45:31+08:00"             type='RPNHead',
"2021-10-21T10:45:31+08:00"             in_channels=256,
"2021-10-21T10:45:31+08:00"             feat_channels=256,
"2021-10-21T10:45:31+08:00"             anchor_generator=dict(
"2021-10-21T10:45:31+08:00"                 type='AnchorGenerator',
"2021-10-21T10:45:31+08:00"                 scales=[8],
"2021-10-21T10:45:31+08:00"                 ratios=[0.5, 1.0, 2.0],
"2021-10-21T10:45:31+08:00"                 strides=[4, 8, 16, 32, 64]),
"2021-10-21T10:45:31+08:00"             bbox_coder=dict(
"2021-10-21T10:45:31+08:00"                 type='DeltaXYWHBBoxCoder',
"2021-10-21T10:45:31+08:00"                 target_means=[0.0, 0.0, 0.0, 0.0],
"2021-10-21T10:45:31+08:00"                 target_stds=[1.0, 1.0, 1.0, 1.0]),
"2021-10-21T10:45:31+08:00"             loss_cls=dict(
"2021-10-21T10:45:31+08:00"                 type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
"2021-10-21T10:45:31+08:00"             loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
"2021-10-21T10:45:31+08:00"         roi_head=dict(
"2021-10-21T10:45:31+08:00"             type='StandardRoIHead',
"2021-10-21T10:45:31+08:00"             bbox_roi_extractor=dict(
"2021-10-21T10:45:31+08:00"                 type='SingleRoIExtractor',
"2021-10-21T10:45:31+08:00"                 roi_layer=dict(
"2021-10-21T10:45:31+08:00"                     type='RoIAlign', output_size=7, sampling_ratio=0),
"2021-10-21T10:45:31+08:00"                 out_channels=256,
"2021-10-21T10:45:31+08:00"                 featmap_strides=[4, 8, 16, 32]),
"2021-10-21T10:45:31+08:00"             bbox_head=dict(
"2021-10-21T10:45:31+08:00"                 type='Shared2FCBBoxHead',
"2021-10-21T10:45:31+08:00"                 in_channels=256,
"2021-10-21T10:45:31+08:00"                 fc_out_channels=1024,
"2021-10-21T10:45:31+08:00"                 roi_feat_size=7,
"2021-10-21T10:45:31+08:00"                 num_classes=80,
"2021-10-21T10:45:31+08:00"                 bbox_coder=dict(
"2021-10-21T10:45:31+08:00"                     type='DeltaXYWHBBoxCoder',
"2021-10-21T10:45:31+08:00"                     target_means=[0.0, 0.0, 0.0, 0.0],
"2021-10-21T10:45:31+08:00"                     target_stds=[0.1, 0.1, 0.2, 0.2]),
"2021-10-21T10:45:31+08:00"                 reg_class_agnostic=False,
"2021-10-21T10:45:31+08:00"                 loss_cls=dict(
"2021-10-21T10:45:31+08:00"                     type='CrossEntropyLoss',
"2021-10-21T10:45:31+08:00"                     use_sigmoid=False,
"2021-10-21T10:45:31+08:00"                     loss_weight=1.0),
"2021-10-21T10:45:31+08:00"                 loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
"2021-10-21T10:45:31+08:00"         train_cfg=dict(
"2021-10-21T10:45:31+08:00"             rpn=dict(
"2021-10-21T10:45:31+08:00"                 assigner=dict(
"2021-10-21T10:45:31+08:00"                     type='MaxIoUAssigner',
"2021-10-21T10:45:31+08:00"                     pos_iou_thr=0.7,
"2021-10-21T10:45:31+08:00"                     neg_iou_thr=0.3,
"2021-10-21T10:45:31+08:00"                     min_pos_iou=0.3,
"2021-10-21T10:45:31+08:00"                     match_low_quality=True,
"2021-10-21T10:45:31+08:00"                     ignore_iof_thr=-1),
"2021-10-21T10:45:31+08:00"                 sampler=dict(
"2021-10-21T10:45:31+08:00"                     type='RandomSampler',
"2021-10-21T10:45:31+08:00"                     num=256,
"2021-10-21T10:45:31+08:00"                     pos_fraction=0.5,
"2021-10-21T10:45:31+08:00"                     neg_pos_ub=-1,
"2021-10-21T10:45:31+08:00"                     add_gt_as_proposals=False),
"2021-10-21T10:45:31+08:00"                 allowed_border=-1,
"2021-10-21T10:45:31+08:00"                 pos_weight=-1,
"2021-10-21T10:45:31+08:00"                 debug=False),
"2021-10-21T10:45:31+08:00"             rpn_proposal=dict(
"2021-10-21T10:45:31+08:00"                 nms_pre=2000,
"2021-10-21T10:45:31+08:00"                 max_per_img=1000,
"2021-10-21T10:45:31+08:00"                 nms=dict(type='nms', iou_threshold=0.7),
"2021-10-21T10:45:31+08:00"                 min_bbox_size=0),
"2021-10-21T10:45:31+08:00"             rcnn=dict(
"2021-10-21T10:45:31+08:00"                 assigner=dict(
"2021-10-21T10:45:31+08:00"                     type='MaxIoUAssigner',
"2021-10-21T10:45:31+08:00"                     pos_iou_thr=0.5,
"2021-10-21T10:45:31+08:00"                     neg_iou_thr=0.5,
"2021-10-21T10:45:31+08:00"                     min_pos_iou=0.5,
"2021-10-21T10:45:31+08:00"                     match_low_quality=False,
"2021-10-21T10:45:31+08:00"                     ignore_iof_thr=-1),
"2021-10-21T10:45:31+08:00"                 sampler=dict(
"2021-10-21T10:45:31+08:00"                     type='RandomSampler',
"2021-10-21T10:45:31+08:00"                     num=512,
"2021-10-21T10:45:31+08:00"                     pos_fraction=0.25,
"2021-10-21T10:45:31+08:00"                     neg_pos_ub=-1,
"2021-10-21T10:45:31+08:00"                     add_gt_as_proposals=True),
"2021-10-21T10:45:31+08:00"                 pos_weight=-1,
"2021-10-21T10:45:31+08:00"                 debug=False)),
"2021-10-21T10:45:31+08:00"         test_cfg=dict(
"2021-10-21T10:45:31+08:00"             rpn=dict(
"2021-10-21T10:45:31+08:00"                 nms_pre=1000,
"2021-10-21T10:45:31+08:00"                 max_per_img=1000,
"2021-10-21T10:45:31+08:00"                 nms=dict(type='nms', iou_threshold=0.7),
"2021-10-21T10:45:31+08:00"                 min_bbox_size=0),
"2021-10-21T10:45:31+08:00"             rcnn=dict(
"2021-10-21T10:45:31+08:00"                 score_thr=0.05,
"2021-10-21T10:45:31+08:00"                 nms=dict(type='nms', iou_threshold=0.5),
"2021-10-21T10:45:31+08:00"                 max_per_img=100))),
"2021-10-21T10:45:31+08:00"     train_cfg=dict(
"2021-10-21T10:45:31+08:00"         use_teacher_proposal=False,
"2021-10-21T10:45:31+08:00"         pseudo_label_initial_score_thr=0.5,
"2021-10-21T10:45:31+08:00"         rpn_pseudo_threshold=0.9,
"2021-10-21T10:45:31+08:00"         cls_pseudo_threshold=0.9,
"2021-10-21T10:45:31+08:00"         reg_pseudo_threshold=0.01,
"2021-10-21T10:45:31+08:00"         jitter_times=10,
"2021-10-21T10:45:31+08:00"         jitter_scale=0.06,
"2021-10-21T10:45:31+08:00"         min_pseduo_box_size=0,
"2021-10-21T10:45:31+08:00"         unsup_weight=2.0),
"2021-10-21T10:45:31+08:00"     test_cfg=dict(inference_on='student'))
"2021-10-21T10:45:31+08:00" dataset_type = 'CocoDataset'
"2021-10-21T10:45:31+08:00" data_root = '/dataset/public/coco/'
"2021-10-21T10:45:31+08:00" img_norm_cfg = dict(
"2021-10-21T10:45:31+08:00"     mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
"2021-10-21T10:45:31+08:00" train_pipeline = [
"2021-10-21T10:45:31+08:00"     dict(type='LoadImageFromFile'),
"2021-10-21T10:45:31+08:00"     dict(type='LoadAnnotations', with_bbox=True),
"2021-10-21T10:45:31+08:00"     dict(
"2021-10-21T10:45:31+08:00"         type='Sequential',
"2021-10-21T10:45:31+08:00"         transforms=[
"2021-10-21T10:45:31+08:00"             dict(
"2021-10-21T10:45:31+08:00"                 type='RandResize',
"2021-10-21T10:45:31+08:00"                 img_scale=[(1333, 400), (1333, 1200)],
"2021-10-21T10:45:31+08:00"                 multiscale_mode='range',
"2021-10-21T10:45:31+08:00"                 keep_ratio=True),
"2021-10-21T10:45:31+08:00"             dict(type='RandFlip', flip_ratio=0.5),
"2021-10-21T10:45:31+08:00"             dict(
"2021-10-21T10:45:31+08:00"                 type='OneOf',
"2021-10-21T10:45:31+08:00"                 transforms=[
"2021-10-21T10:45:31+08:00"                     dict(type='Identity'),
"2021-10-21T10:45:31+08:00"                     dict(type='AutoContrast'),
"2021-10-21T10:45:31+08:00"                     dict(type='RandEqualize'),
"2021-10-21T10:45:31+08:00"                     dict(type='RandSolarize'),
"2021-10-21T10:45:31+08:00"                     dict(type='RandColor'),
"2021-10-21T10:45:31+08:00"                     dict(type='RandContrast'),
"2021-10-21T10:45:31+08:00"                     dict(type='RandBrightness'),
"2021-10-21T10:45:31+08:00"                     dict(type='RandSharpness'),
"2021-10-21T10:45:31+08:00"                     dict(type='RandPosterize')
"2021-10-21T10:45:31+08:00"                 ])
"2021-10-21T10:45:31+08:00"         ],
"2021-10-21T10:45:31+08:00"         record=True),
"2021-10-21T10:45:31+08:00"     dict(type='Pad', size_divisor=32),
"2021-10-21T10:45:31+08:00"     dict(
"2021-10-21T10:45:31+08:00"         type='Normalize',
"2021-10-21T10:45:31+08:00"         mean=[103.53, 116.28, 123.675],
"2021-10-21T10:45:31+08:00"         std=[1.0, 1.0, 1.0],
"2021-10-21T10:45:31+08:00"         to_rgb=False),
"2021-10-21T10:45:31+08:00"     dict(type='ExtraAttrs', tag='sup'),
"2021-10-21T10:45:31+08:00"     dict(type='DefaultFormatBundle'),
"2021-10-21T10:45:31+08:00"     dict(
"2021-10-21T10:45:31+08:00"         type='Collect',
"2021-10-21T10:45:31+08:00"         keys=['img', 'gt_bboxes', 'gt_labels'],
"2021-10-21T10:45:31+08:00"         meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
"2021-10-21T10:45:31+08:00"                    'pad_shape', 'scale_factor', 'tag'))
"2021-10-21T10:45:31+08:00" ]
"2021-10-21T10:45:31+08:00" test_pipeline = [
"2021-10-21T10:45:31+08:00"     dict(type='LoadImageFromFile'),
"2021-10-21T10:45:31+08:00"     dict(
"2021-10-21T10:45:31+08:00"         type='MultiScaleFlipAug',
"2021-10-21T10:45:31+08:00"         img_scale=(1333, 800),
"2021-10-21T10:45:31+08:00"         flip=False,
"2021-10-21T10:45:31+08:00"         transforms=[
"2021-10-21T10:45:31+08:00"             dict(type='Resize', keep_ratio=True),
"2021-10-21T10:45:31+08:00"             dict(type='RandomFlip'),
"2021-10-21T10:45:31+08:00"             dict(
"2021-10-21T10:45:31+08:00"                 type='Normalize',
"2021-10-21T10:45:31+08:00"                 mean=[103.53, 116.28, 123.675],
"2021-10-21T10:45:31+08:00"                 std=[1.0, 1.0, 1.0],
"2021-10-21T10:45:31+08:00"                 to_rgb=False),
"2021-10-21T10:45:31+08:00"             dict(type='Pad', size_divisor=32),
"2021-10-21T10:45:31+08:00"             dict(type='ImageToTensor', keys=['img']),
"2021-10-21T10:45:31+08:00"             dict(type='Collect', keys=['img'])
"2021-10-21T10:45:31+08:00"         ])
"2021-10-21T10:45:31+08:00" ]
"2021-10-21T10:45:31+08:00" data = dict(
"2021-10-21T10:45:31+08:00"     samples_per_gpu=8,
"2021-10-21T10:45:31+08:00"     workers_per_gpu=4,
"2021-10-21T10:45:31+08:00"     train=dict(
"2021-10-21T10:45:31+08:00"         type='SemiDataset',
"2021-10-21T10:45:31+08:00"         sup=dict(
"2021-10-21T10:45:31+08:00"             type='CocoDataset',
"2021-10-21T10:45:31+08:00"             ann_file='/dataset/public/coco/annotations/instances_val2017.json',
"2021-10-21T10:45:31+08:00"             img_prefix='/dataset/public/coco/images/val2017/',
"2021-10-21T10:45:31+08:00"             pipeline=[
"2021-10-21T10:45:31+08:00"                 dict(type='LoadImageFromFile'),
"2021-10-21T10:45:31+08:00"                 dict(type='LoadAnnotations', with_bbox=True),
"2021-10-21T10:45:31+08:00"                 dict(
"2021-10-21T10:45:31+08:00"                     type='Sequential',
"2021-10-21T10:45:31+08:00"                     transforms=[
"2021-10-21T10:45:31+08:00"                         dict(
"2021-10-21T10:45:31+08:00"                             type='RandResize',
"2021-10-21T10:45:31+08:00"                             img_scale=[(1333, 400), (1333, 1200)],
"2021-10-21T10:45:31+08:00"                             multiscale_mode='range',
"2021-10-21T10:45:31+08:00"                             keep_ratio=True),
"2021-10-21T10:45:31+08:00"                         dict(type='RandFlip', flip_ratio=0.5),
"2021-10-21T10:45:31+08:00"                         dict(
"2021-10-21T10:45:31+08:00"                             type='OneOf',
"2021-10-21T10:45:31+08:00"                             transforms=[
"2021-10-21T10:45:31+08:00"                                 dict(type='Identity'),
"2021-10-21T10:45:31+08:00"                                 dict(type='AutoContrast'),
"2021-10-21T10:45:31+08:00"                                 dict(type='RandEqualize'),
"2021-10-21T10:45:31+08:00"                                 dict(type='RandSolarize'),
"2021-10-21T10:45:31+08:00"                                 dict(type='RandColor'),
"2021-10-21T10:45:31+08:00"                                 dict(type='RandContrast'),
"2021-10-21T10:45:31+08:00"                                 dict(type='RandBrightness'),
"2021-10-21T10:45:31+08:00"                                 dict(type='RandSharpness'),
"2021-10-21T10:45:31+08:00"                                 dict(type='RandPosterize')
"2021-10-21T10:45:31+08:00"                             ])
"2021-10-21T10:45:31+08:00"                     ],
"2021-10-21T10:45:31+08:00"                     record=True),
"2021-10-21T10:45:31+08:00"                 dict(type='Pad', size_divisor=32),
"2021-10-21T10:45:31+08:00"                 dict(
"2021-10-21T10:45:31+08:00"                     type='Normalize',
"2021-10-21T10:45:31+08:00"                     mean=[103.53, 116.28, 123.675],
"2021-10-21T10:45:31+08:00"                     std=[1.0, 1.0, 1.0],
"2021-10-21T10:45:31+08:00"                     to_rgb=False),
"2021-10-21T10:45:31+08:00"                 dict(type='ExtraAttrs', tag='sup'),
"2021-10-21T10:45:31+08:00"                 dict(type='DefaultFormatBundle'),
"2021-10-21T10:45:31+08:00"                 dict(
"2021-10-21T10:45:31+08:00"                     type='Collect',
"2021-10-21T10:45:31+08:00"                     keys=['img', 'gt_bboxes', 'gt_labels'],
"2021-10-21T10:45:31+08:00"                     meta_keys=('filename', 'ori_shape', 'img_shape',
"2021-10-21T10:45:31+08:00"                                'img_norm_cfg', 'pad_shape', 'scale_factor',
"2021-10-21T10:45:31+08:00"                                'tag'))
"2021-10-21T10:45:31+08:00"             ]),
"2021-10-21T10:45:31+08:00"         unsup=dict(
"2021-10-21T10:45:31+08:00"             type='CocoDataset',
"2021-10-21T10:45:31+08:00"             ann_file=
"2021-10-21T10:45:31+08:00"             '/dataset/public/coco/annotations/instances_train2017.json',
"2021-10-21T10:45:31+08:00"             img_prefix='/dataset/public/coco/images/train2017/',
"2021-10-21T10:45:31+08:00"             pipeline=[
"2021-10-21T10:45:31+08:00"                 dict(type='LoadImageFromFile'),
"2021-10-21T10:45:31+08:00"                 dict(type='PseudoSamples', with_bbox=True),
"2021-10-21T10:45:31+08:00"                 dict(
"2021-10-21T10:45:31+08:00"                     type='MultiBranch',
"2021-10-21T10:45:31+08:00"                     unsup_teacher=[
"2021-10-21T10:45:31+08:00"                         dict(
"2021-10-21T10:45:31+08:00"                             type='Sequential',
"2021-10-21T10:45:31+08:00"                             transforms=[
"2021-10-21T10:45:31+08:00"                                 dict(
"2021-10-21T10:45:31+08:00"                                     type='RandResize',
"2021-10-21T10:45:31+08:00"                                     img_scale=[(1333, 400), (1333, 1200)],
"2021-10-21T10:45:31+08:00"                                     multiscale_mode='range',
"2021-10-21T10:45:31+08:00"                                     keep_ratio=True),
"2021-10-21T10:45:31+08:00"                                 dict(type='RandFlip', flip_ratio=0.5),
"2021-10-21T10:45:31+08:00"                                 dict(
"2021-10-21T10:45:31+08:00"                                     type='ShuffledSequential',
"2021-10-21T10:45:31+08:00"                                     transforms=[
"2021-10-21T10:45:31+08:00"                                         dict(
"2021-10-21T10:45:31+08:00"                                             type='OneOf',
"2021-10-21T10:45:31+08:00"                                             transforms=[
"2021-10-21T10:45:31+08:00"                                                 dict(type='Identity'),
"2021-10-21T10:45:31+08:00"                                                 dict(type='AutoContrast'),
"2021-10-21T10:45:31+08:00"                                                 dict(type='RandEqualize'),
"2021-10-21T10:45:31+08:00"                                                 dict(type='RandSolarize'),
"2021-10-21T10:45:31+08:00"                                                 dict(type='RandColor'),
"2021-10-21T10:45:31+08:00"                                                 dict(type='RandContrast'),
"2021-10-21T10:45:31+08:00"                                                 dict(type='RandBrightness'),
"2021-10-21T10:45:31+08:00"                                                 dict(type='RandSharpness'),
"2021-10-21T10:45:31+08:00"                                                 dict(type='RandPosterize')
"2021-10-21T10:45:31+08:00"                                             ]),
"2021-10-21T10:45:31+08:00"                                         dict(
"2021-10-21T10:45:31+08:00"                                             type='OneOf',
"2021-10-21T10:45:31+08:00"                                             transforms=[{
"2021-10-21T10:45:31+08:00"                                                 'type': 'RandTranslate',
"2021-10-21T10:45:31+08:00"                                                 'x': (-0.1, 0.1)
"2021-10-21T10:45:31+08:00"                                             }, {
"2021-10-21T10:45:31+08:00"                                                 'type': 'RandTranslate',
"2021-10-21T10:45:31+08:00"                                                 'y': (-0.1, 0.1)
"2021-10-21T10:45:31+08:00"                                             }, {
"2021-10-21T10:45:31+08:00"                                                 'type': 'RandRotate',
"2021-10-21T10:45:31+08:00"                                                 'angle': (-30, 30)
"2021-10-21T10:45:31+08:00"                                             },
"2021-10-21T10:45:31+08:00"                                                         [{
"2021-10-21T10:45:31+08:00"                                                             'type':
"2021-10-21T10:45:31+08:00"                                                             'RandShear',
"2021-10-21T10:45:31+08:00"                                                             'x': (-30, 30)
"2021-10-21T10:45:31+08:00"                                                         }, {
"2021-10-21T10:45:31+08:00"                                                             'type':
"2021-10-21T10:45:31+08:00"                                                             'RandShear',
"2021-10-21T10:45:31+08:00"                                                             'y': (-30, 30)
"2021-10-21T10:45:31+08:00"                                                         }]])
"2021-10-21T10:45:31+08:00"                                     ]),
"2021-10-21T10:45:31+08:00"                                 dict(
"2021-10-21T10:45:31+08:00"                                     type='RandErase',
"2021-10-21T10:45:31+08:00"                                     n_iterations=(1, 5),
"2021-10-21T10:45:31+08:00"                                     size=[0, 0.2],
"2021-10-21T10:45:31+08:00"                                     squared=True)
"2021-10-21T10:45:31+08:00"                             ],
"2021-10-21T10:45:31+08:00"                             record=True),
"2021-10-21T10:45:31+08:00"                         dict(type='Pad', size_divisor=32),
"2021-10-21T10:45:31+08:00"                         dict(
"2021-10-21T10:45:31+08:00"                             type='Normalize',
"2021-10-21T10:45:31+08:00"                             mean=[103.53, 116.28, 123.675],
"2021-10-21T10:45:31+08:00"                             std=[1.0, 1.0, 1.0],
"2021-10-21T10:45:31+08:00"                             to_rgb=False),
"2021-10-21T10:45:31+08:00"                         dict(type='ExtraAttrs', tag='unsup_student'),
"2021-10-21T10:45:31+08:00"                         dict(type='DefaultFormatBundle'),
"2021-10-21T10:45:31+08:00"                         dict(
"2021-10-21T10:45:31+08:00"                             type='Collect',
"2021-10-21T10:45:31+08:00"                             keys=['img', 'gt_bboxes', 'gt_labels'],
"2021-10-21T10:45:31+08:00"                             meta_keys=('filename', 'ori_shape', 'img_shape',
"2021-10-21T10:45:31+08:00"                                        'img_norm_cfg', 'pad_shape',
"2021-10-21T10:45:31+08:00"                                        'scale_factor', 'tag',
"2021-10-21T10:45:31+08:00"                                        'transform_matrix'))
"2021-10-21T10:45:31+08:00"                     ],
"2021-10-21T10:45:31+08:00"                     unsup_student=[
"2021-10-21T10:45:31+08:00"                         dict(
"2021-10-21T10:45:31+08:00"                             type='Sequential',
"2021-10-21T10:45:31+08:00"                             transforms=[
"2021-10-21T10:45:31+08:00"                                 dict(
"2021-10-21T10:45:31+08:00"                                     type='RandResize',
"2021-10-21T10:45:31+08:00"                                     img_scale=[(1333, 400), (1333, 1200)],
"2021-10-21T10:45:31+08:00"                                     multiscale_mode='range',
"2021-10-21T10:45:31+08:00"                                     keep_ratio=True),
"2021-10-21T10:45:31+08:00"                                 dict(type='RandFlip', flip_ratio=0.5)
"2021-10-21T10:45:31+08:00"                             ],
"2021-10-21T10:45:31+08:00"                             record=True),
"2021-10-21T10:45:31+08:00"                         dict(type='Pad', size_divisor=32),
"2021-10-21T10:45:31+08:00"                         dict(
"2021-10-21T10:45:31+08:00"                             type='Normalize',
"2021-10-21T10:45:31+08:00"                             mean=[103.53, 116.28, 123.675],
"2021-10-21T10:45:31+08:00"                             std=[1.0, 1.0, 1.0],
"2021-10-21T10:45:31+08:00"                             to_rgb=False),
"2021-10-21T10:45:31+08:00"                         dict(type='ExtraAttrs', tag='unsup_teacher'),
"2021-10-21T10:45:31+08:00"                         dict(type='DefaultFormatBundle'),
"2021-10-21T10:45:31+08:00"                         dict(
"2021-10-21T10:45:31+08:00"                             type='Collect',
"2021-10-21T10:45:31+08:00"                             keys=['img', 'gt_bboxes', 'gt_labels'],
"2021-10-21T10:45:31+08:00"                             meta_keys=('filename', 'ori_shape', 'img_shape',
"2021-10-21T10:45:31+08:00"                                        'img_norm_cfg', 'pad_shape',
"2021-10-21T10:45:31+08:00"                                        'scale_factor', 'tag',
"2021-10-21T10:45:31+08:00"                                        'transform_matrix'))
"2021-10-21T10:45:31+08:00"                     ])
"2021-10-21T10:45:31+08:00"             ],
"2021-10-21T10:45:31+08:00"             filter_empty_gt=False)),
"2021-10-21T10:45:31+08:00"     val=dict(
"2021-10-21T10:45:31+08:00"         type='CocoDataset',
"2021-10-21T10:45:31+08:00"         ann_file='/dataset/public/coco/annotations/instances_val2017.json',
"2021-10-21T10:45:31+08:00"         img_prefix='/dataset/public/coco/images/val2017/',
"2021-10-21T10:45:31+08:00"         pipeline=[
"2021-10-21T10:45:31+08:00"             dict(type='LoadImageFromFile'),
"2021-10-21T10:45:31+08:00"             dict(
"2021-10-21T10:45:31+08:00"                 type='MultiScaleFlipAug',
"2021-10-21T10:45:31+08:00"                 img_scale=(1333, 800),
"2021-10-21T10:45:31+08:00"                 flip=False,
"2021-10-21T10:45:31+08:00"                 transforms=[
"2021-10-21T10:45:31+08:00"                     dict(type='Resize', keep_ratio=True),
"2021-10-21T10:45:31+08:00"                     dict(type='RandomFlip'),
"2021-10-21T10:45:31+08:00"                     dict(
"2021-10-21T10:45:31+08:00"                         type='Normalize',
"2021-10-21T10:45:31+08:00"                         mean=[103.53, 116.28, 123.675],
"2021-10-21T10:45:31+08:00"                         std=[1.0, 1.0, 1.0],
"2021-10-21T10:45:31+08:00"                         to_rgb=False),
"2021-10-21T10:45:31+08:00"                     dict(type='Pad', size_divisor=32),
"2021-10-21T10:45:31+08:00"                     dict(type='ImageToTensor', keys=['img']),
"2021-10-21T10:45:31+08:00"                     dict(type='Collect', keys=['img'])
"2021-10-21T10:45:31+08:00"                 ])
"2021-10-21T10:45:31+08:00"         ]),
"2021-10-21T10:45:31+08:00"     test=dict(
"2021-10-21T10:45:31+08:00"         type='CocoDataset',
"2021-10-21T10:45:31+08:00"         ann_file='/dataset/public/coco/annotations/instances_val2017.json',
"2021-10-21T10:45:31+08:00"         img_prefix='/dataset/public/coco/images/val2017/',
"2021-10-21T10:45:31+08:00"         pipeline=[
"2021-10-21T10:45:31+08:00"             dict(type='LoadImageFromFile'),
"2021-10-21T10:45:31+08:00"             dict(
"2021-10-21T10:45:31+08:00"                 type='MultiScaleFlipAug',
"2021-10-21T10:45:31+08:00"                 img_scale=(1333, 800),
"2021-10-21T10:45:31+08:00"                 flip=False,
"2021-10-21T10:45:31+08:00"                 transforms=[
"2021-10-21T10:45:31+08:00"                     dict(type='Resize', keep_ratio=True),
"2021-10-21T10:45:31+08:00"                     dict(type='RandomFlip'),
"2021-10-21T10:45:31+08:00"                     dict(
"2021-10-21T10:45:31+08:00"                         type='Normalize',
"2021-10-21T10:45:31+08:00"                         mean=[103.53, 116.28, 123.675],
"2021-10-21T10:45:31+08:00"                         std=[1.0, 1.0, 1.0],
"2021-10-21T10:45:31+08:00"                         to_rgb=False),
"2021-10-21T10:45:31+08:00"                     dict(type='Pad', size_divisor=32),
"2021-10-21T10:45:31+08:00"                     dict(type='ImageToTensor', keys=['img']),
"2021-10-21T10:45:31+08:00"                     dict(type='Collect', keys=['img'])
"2021-10-21T10:45:31+08:00"                 ])
"2021-10-21T10:45:31+08:00"         ]),
"2021-10-21T10:45:31+08:00"     sampler=dict(
"2021-10-21T10:45:31+08:00"         train=dict(
"2021-10-21T10:45:31+08:00"             type='SemiBalanceSampler',
"2021-10-21T10:45:31+08:00"             sample_ratio=[1, 1],
"2021-10-21T10:45:31+08:00"             by_prob=True,
"2021-10-21T10:45:31+08:00"             epoch_length=7330)))
"2021-10-21T10:45:31+08:00" evaluation = dict(interval=4000, metric='bbox', type='SubModulesDistEvalHook')
"2021-10-21T10:45:31+08:00" optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
"2021-10-21T10:45:31+08:00" optimizer_config = dict(grad_clip=None)
"2021-10-21T10:45:31+08:00" lr_config = dict(
"2021-10-21T10:45:31+08:00"     policy='step',
"2021-10-21T10:45:31+08:00"     warmup='linear',
"2021-10-21T10:45:31+08:00"     warmup_iters=500,
"2021-10-21T10:45:31+08:00"     warmup_ratio=0.001,
"2021-10-21T10:45:31+08:00"     step=[480000, 640000])
"2021-10-21T10:45:31+08:00" runner = dict(type='IterBasedRunner', max_iters=720000)
"2021-10-21T10:45:31+08:00" checkpoint_config = dict(interval=4000, by_epoch=False, max_keep_ckpts=20)
"2021-10-21T10:45:31+08:00" log_config = dict(
"2021-10-21T10:45:31+08:00"     interval=50,
"2021-10-21T10:45:31+08:00"     hooks=[
"2021-10-21T10:45:31+08:00"         dict(type='TextLoggerHook', by_epoch=False),
"2021-10-21T10:45:31+08:00"         dict(type='TensorboardLoggerHook')
"2021-10-21T10:45:31+08:00"     ])
"2021-10-21T10:45:31+08:00" custom_hooks = [
"2021-10-21T10:45:31+08:00"     dict(type='NumClassCheckHook'),
"2021-10-21T10:45:31+08:00"     dict(type='WeightSummary'),
"2021-10-21T10:45:31+08:00"     dict(type='MeanTeacher', momentum=0.999, interval=1, warm_up=0)
"2021-10-21T10:45:31+08:00" ]
"2021-10-21T10:45:31+08:00" dist_params = dict(backend='nccl')
"2021-10-21T10:45:31+08:00" log_level = 'INFO'
"2021-10-21T10:45:31+08:00" load_from = None
"2021-10-21T10:45:31+08:00" resume_from = None
"2021-10-21T10:45:31+08:00" workflow = [('train', 1)]
"2021-10-21T10:45:31+08:00" mmdet_base = '../../thirdparty/mmdetection/configs/_base_'
"2021-10-21T10:45:31+08:00" strong_pipeline = [
"2021-10-21T10:45:31+08:00"     dict(
"2021-10-21T10:45:31+08:00"         type='Sequential',
"2021-10-21T10:45:31+08:00"         transforms=[
"2021-10-21T10:45:31+08:00"             dict(
"2021-10-21T10:45:31+08:00"                 type='RandResize',
"2021-10-21T10:45:31+08:00"                 img_scale=[(1333, 400), (1333, 1200)],
"2021-10-21T10:45:31+08:00"                 multiscale_mode='range',
"2021-10-21T10:45:31+08:00"                 keep_ratio=True),
"2021-10-21T10:45:31+08:00"             dict(type='RandFlip', flip_ratio=0.5),
"2021-10-21T10:45:31+08:00"             dict(
"2021-10-21T10:45:31+08:00"                 type='ShuffledSequential',
"2021-10-21T10:45:31+08:00"                 transforms=[
"2021-10-21T10:45:31+08:00"                     dict(
"2021-10-21T10:45:31+08:00"                         type='OneOf',
"2021-10-21T10:45:31+08:00"                         transforms=[
"2021-10-21T10:45:31+08:00"                             dict(type='Identity'),
"2021-10-21T10:45:31+08:00"                             dict(type='AutoContrast'),
"2021-10-21T10:45:31+08:00"                             dict(type='RandEqualize'),
"2021-10-21T10:45:31+08:00"                             dict(type='RandSolarize'),
"2021-10-21T10:45:31+08:00"                             dict(type='RandColor'),
"2021-10-21T10:45:31+08:00"                             dict(type='RandContrast'),
"2021-10-21T10:45:31+08:00"                             dict(type='RandBrightness'),
"2021-10-21T10:45:31+08:00"                             dict(type='RandSharpness'),
"2021-10-21T10:45:31+08:00"                             dict(type='RandPosterize')
"2021-10-21T10:45:31+08:00"                         ]),
"2021-10-21T10:45:31+08:00"                     dict(
"2021-10-21T10:45:31+08:00"                         type='OneOf',
"2021-10-21T10:45:31+08:00"                         transforms=[{
"2021-10-21T10:45:31+08:00"                             'type': 'RandTranslate',
"2021-10-21T10:45:31+08:00"                             'x': (-0.1, 0.1)
"2021-10-21T10:45:31+08:00"                         }, {
"2021-10-21T10:45:31+08:00"                             'type': 'RandTranslate',
"2021-10-21T10:45:31+08:00"                             'y': (-0.1, 0.1)
"2021-10-21T10:45:31+08:00"                         }, {
"2021-10-21T10:45:31+08:00"                             'type': 'RandRotate',
"2021-10-21T10:45:31+08:00"                             'angle': (-30, 30)
"2021-10-21T10:45:31+08:00"                         },
"2021-10-21T10:45:31+08:00"                                     [{
"2021-10-21T10:45:31+08:00"                                         'type': 'RandShear',
"2021-10-21T10:45:31+08:00"                                         'x': (-30, 30)
"2021-10-21T10:45:31+08:00"                                     }, {
"2021-10-21T10:45:31+08:00"                                         'type': 'RandShear',
"2021-10-21T10:45:31+08:00"                                         'y': (-30, 30)
"2021-10-21T10:45:31+08:00"                                     }]])
"2021-10-21T10:45:31+08:00"                 ]),
"2021-10-21T10:45:31+08:00"             dict(
"2021-10-21T10:45:31+08:00"                 type='RandErase',
"2021-10-21T10:45:31+08:00"                 n_iterations=(1, 5),
"2021-10-21T10:45:31+08:00"                 size=[0, 0.2],
"2021-10-21T10:45:31+08:00"                 squared=True)
"2021-10-21T10:45:31+08:00"         ],
"2021-10-21T10:45:31+08:00"         record=True),
"2021-10-21T10:45:31+08:00"     dict(type='Pad', size_divisor=32),
"2021-10-21T10:45:31+08:00"     dict(
"2021-10-21T10:45:31+08:00"         type='Normalize',
"2021-10-21T10:45:31+08:00"         mean=[103.53, 116.28, 123.675],
"2021-10-21T10:45:31+08:00"         std=[1.0, 1.0, 1.0],
"2021-10-21T10:45:31+08:00"         to_rgb=False),
"2021-10-21T10:45:31+08:00"     dict(type='ExtraAttrs', tag='unsup_student'),
"2021-10-21T10:45:31+08:00"     dict(type='DefaultFormatBundle'),
"2021-10-21T10:45:31+08:00"     dict(
"2021-10-21T10:45:31+08:00"         type='Collect',
"2021-10-21T10:45:31+08:00"         keys=['img', 'gt_bboxes', 'gt_labels'],
"2021-10-21T10:45:31+08:00"         meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
"2021-10-21T10:45:31+08:00"                    'pad_shape', 'scale_factor', 'tag', 'transform_matrix'))
"2021-10-21T10:45:31+08:00" ]
"2021-10-21T10:45:31+08:00" weak_pipeline = [
"2021-10-21T10:45:31+08:00"     dict(
"2021-10-21T10:45:31+08:00"         type='Sequential',
"2021-10-21T10:45:31+08:00"         transforms=[
"2021-10-21T10:45:31+08:00"             dict(
"2021-10-21T10:45:31+08:00"                 type='RandResize',
"2021-10-21T10:45:31+08:00"                 img_scale=[(1333, 400), (1333, 1200)],
"2021-10-21T10:45:31+08:00"                 multiscale_mode='range',
"2021-10-21T10:45:31+08:00"                 keep_ratio=True),
"2021-10-21T10:45:31+08:00"             dict(type='RandFlip', flip_ratio=0.5)
"2021-10-21T10:45:31+08:00"         ],
"2021-10-21T10:45:31+08:00"         record=True),
"2021-10-21T10:45:31+08:00"     dict(type='Pad', size_divisor=32),
"2021-10-21T10:45:31+08:00"     dict(
"2021-10-21T10:45:31+08:00"         type='Normalize',
"2021-10-21T10:45:31+08:00"         mean=[103.53, 116.28, 123.675],
"2021-10-21T10:45:31+08:00"         std=[1.0, 1.0, 1.0],
"2021-10-21T10:45:31+08:00"         to_rgb=False),
"2021-10-21T10:45:31+08:00"     dict(type='ExtraAttrs', tag='unsup_teacher'),
"2021-10-21T10:45:31+08:00"     dict(type='DefaultFormatBundle'),
"2021-10-21T10:45:31+08:00"     dict(
"2021-10-21T10:45:31+08:00"         type='Collect',
"2021-10-21T10:45:31+08:00"         keys=['img', 'gt_bboxes', 'gt_labels'],
"2021-10-21T10:45:31+08:00"         meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
"2021-10-21T10:45:31+08:00"                    'pad_shape', 'scale_factor', 'tag', 'transform_matrix'))
"2021-10-21T10:45:31+08:00" ]
"2021-10-21T10:45:31+08:00" unsup_pipeline = [
"2021-10-21T10:45:31+08:00"     dict(type='LoadImageFromFile'),
"2021-10-21T10:45:31+08:00"     dict(type='PseudoSamples', with_bbox=True),
"2021-10-21T10:45:31+08:00"     dict(
"2021-10-21T10:45:31+08:00"         type='MultiBranch',
"2021-10-21T10:45:31+08:00"         unsup_teacher=[
"2021-10-21T10:45:31+08:00"             dict(
"2021-10-21T10:45:31+08:00"                 type='Sequential',
"2021-10-21T10:45:31+08:00"                 transforms=[
"2021-10-21T10:45:31+08:00"                     dict(
"2021-10-21T10:45:31+08:00"                         type='RandResize',
"2021-10-21T10:45:31+08:00"                         img_scale=[(1333, 400), (1333, 1200)],
"2021-10-21T10:45:31+08:00"                         multiscale_mode='range',
"2021-10-21T10:45:31+08:00"                         keep_ratio=True),
"2021-10-21T10:45:31+08:00"                     dict(type='RandFlip', flip_ratio=0.5),
"2021-10-21T10:45:31+08:00"                     dict(
"2021-10-21T10:45:31+08:00"                         type='ShuffledSequential',
"2021-10-21T10:45:31+08:00"                         transforms=[
"2021-10-21T10:45:31+08:00"                             dict(
"2021-10-21T10:45:31+08:00"                                 type='OneOf',
"2021-10-21T10:45:31+08:00"                                 transforms=[
"2021-10-21T10:45:31+08:00"                                     dict(type='Identity'),
"2021-10-21T10:45:31+08:00"                                     dict(type='AutoContrast'),
"2021-10-21T10:45:31+08:00"                                     dict(type='RandEqualize'),
"2021-10-21T10:45:31+08:00"                                     dict(type='RandSolarize'),
"2021-10-21T10:45:31+08:00"                                     dict(type='RandColor'),
"2021-10-21T10:45:31+08:00"                                     dict(type='RandContrast'),
"2021-10-21T10:45:31+08:00"                                     dict(type='RandBrightness'),
"2021-10-21T10:45:31+08:00"                                     dict(type='RandSharpness'),
"2021-10-21T10:45:31+08:00"                                     dict(type='RandPosterize')
"2021-10-21T10:45:31+08:00"                                 ]),
"2021-10-21T10:45:31+08:00"                             dict(
"2021-10-21T10:45:31+08:00"                                 type='OneOf',
"2021-10-21T10:45:31+08:00"                                 transforms=[{
"2021-10-21T10:45:31+08:00"                                     'type': 'RandTranslate',
"2021-10-21T10:45:31+08:00"                                     'x': (-0.1, 0.1)
"2021-10-21T10:45:31+08:00"                                 }, {
"2021-10-21T10:45:31+08:00"                                     'type': 'RandTranslate',
"2021-10-21T10:45:31+08:00"                                     'y': (-0.1, 0.1)
"2021-10-21T10:45:31+08:00"                                 }, {
"2021-10-21T10:45:31+08:00"                                     'type': 'RandRotate',
"2021-10-21T10:45:31+08:00"                                     'angle': (-30, 30)
"2021-10-21T10:45:31+08:00"                                 },
"2021-10-21T10:45:31+08:00"                                             [{
"2021-10-21T10:45:31+08:00"                                                 'type': 'RandShear',
"2021-10-21T10:45:31+08:00"                                                 'x': (-30, 30)
"2021-10-21T10:45:31+08:00"                                             }, {
"2021-10-21T10:45:31+08:00"                                                 'type': 'RandShear',
"2021-10-21T10:45:31+08:00"                                                 'y': (-30, 30)
"2021-10-21T10:45:31+08:00"                                             }]])
"2021-10-21T10:45:31+08:00"                         ]),
"2021-10-21T10:45:31+08:00"                     dict(
"2021-10-21T10:45:31+08:00"                         type='RandErase',
"2021-10-21T10:45:31+08:00"                         n_iterations=(1, 5),
"2021-10-21T10:45:31+08:00"                         size=[0, 0.2],
"2021-10-21T10:45:31+08:00"                         squared=True)
"2021-10-21T10:45:31+08:00"                 ],
"2021-10-21T10:45:31+08:00"                 record=True),
"2021-10-21T10:45:31+08:00"             dict(type='Pad', size_divisor=32),
"2021-10-21T10:45:31+08:00"             dict(
"2021-10-21T10:45:31+08:00"                 type='Normalize',
"2021-10-21T10:45:31+08:00"                 mean=[103.53, 116.28, 123.675],
"2021-10-21T10:45:31+08:00"                 std=[1.0, 1.0, 1.0],
"2021-10-21T10:45:31+08:00"                 to_rgb=False),
"2021-10-21T10:45:31+08:00"             dict(type='ExtraAttrs', tag='unsup_student'),
"2021-10-21T10:45:31+08:00"             dict(type='DefaultFormatBundle'),
"2021-10-21T10:45:31+08:00"             dict(
"2021-10-21T10:45:31+08:00"                 type='Collect',
"2021-10-21T10:45:31+08:00"                 keys=['img', 'gt_bboxes', 'gt_labels'],
"2021-10-21T10:45:31+08:00"                 meta_keys=('filename', 'ori_shape', 'img_shape',
"2021-10-21T10:45:31+08:00"                            'img_norm_cfg', 'pad_shape', 'scale_factor', 'tag',
"2021-10-21T10:45:31+08:00"                            'transform_matrix'))
"2021-10-21T10:45:31+08:00"         ],
"2021-10-21T10:45:31+08:00"         unsup_student=[
"2021-10-21T10:45:31+08:00"             dict(
"2021-10-21T10:45:31+08:00"                 type='Sequential',
"2021-10-21T10:45:31+08:00"                 transforms=[
"2021-10-21T10:45:31+08:00"                     dict(
"2021-10-21T10:45:31+08:00"                         type='RandResize',
"2021-10-21T10:45:31+08:00"                         img_scale=[(1333, 400), (1333, 1200)],
"2021-10-21T10:45:31+08:00"                         multiscale_mode='range',
"2021-10-21T10:45:31+08:00"                         keep_ratio=True),
"2021-10-21T10:45:31+08:00"                     dict(type='RandFlip', flip_ratio=0.5)
"2021-10-21T10:45:31+08:00"                 ],
"2021-10-21T10:45:31+08:00"                 record=True),
"2021-10-21T10:45:31+08:00"             dict(type='Pad', size_divisor=32),
"2021-10-21T10:45:31+08:00"             dict(
"2021-10-21T10:45:31+08:00"                 type='Normalize',
"2021-10-21T10:45:31+08:00"                 mean=[103.53, 116.28, 123.675],
"2021-10-21T10:45:31+08:00"                 std=[1.0, 1.0, 1.0],
"2021-10-21T10:45:31+08:00"                 to_rgb=False),
"2021-10-21T10:45:31+08:00"             dict(type='ExtraAttrs', tag='unsup_teacher'),
"2021-10-21T10:45:31+08:00"             dict(type='DefaultFormatBundle'),
"2021-10-21T10:45:31+08:00"             dict(
"2021-10-21T10:45:31+08:00"                 type='Collect',
"2021-10-21T10:45:31+08:00"                 keys=['img', 'gt_bboxes', 'gt_labels'],
"2021-10-21T10:45:31+08:00"                 meta_keys=('filename', 'ori_shape', 'img_shape',
"2021-10-21T10:45:31+08:00"                            'img_norm_cfg', 'pad_shape', 'scale_factor', 'tag',
"2021-10-21T10:45:31+08:00"                            'transform_matrix'))
"2021-10-21T10:45:31+08:00"         ])
"2021-10-21T10:45:31+08:00" ]
"2021-10-21T10:45:31+08:00" fp16 = dict(loss_scale='dynamic')
"2021-10-21T10:45:31+08:00" work_dir = '/data1/train_code/SoftTeacher/workdir/soft_teacher_faster_rcnn_r50_caffe_fpn_adas_full_720k'
"2021-10-21T10:45:31+08:00" cfg_name = 'soft_teacher_faster_rcnn_r50_caffe_fpn_adas_full_720k'
"2021-10-21T10:45:31+08:00" gpu_ids = range(0, 1)
"2021-10-21T10:45:31+08:00" 
"2021-10-21T10:45:32+08:00" /data1/train_code/SoftTeacher/thirdparty/mmdetection/mmdet/core/anchor/builder.py:17: UserWarning: ``build_anchor_generator`` would be deprecated soon, please use ``build_prior_generator`` 
"2021-10-21T10:45:32+08:00"   '``build_anchor_generator`` would be deprecated soon, please use '
"2021-10-21T10:45:32+08:00" 2021-10-21 10:45:32,497 - mmcv - INFO - load model from: /data1/train_code/model_zoo/resnet50-19c8e357.pth
"2021-10-21T10:45:32+08:00" 2021-10-21 10:45:32,497 - mmcv - INFO - Use load_from_local loader
"2021-10-21T10:45:32+08:00" 2021-10-21 10:45:32,729 - mmcv - WARNING - The model and loaded state dict do not match exactly
"2021-10-21T10:45:32+08:00" 
"2021-10-21T10:45:32+08:00" unexpected key in source state_dict: fc.weight, fc.bias
"2021-10-21T10:45:32+08:00" 
"2021-10-21T10:45:32+08:00" 2021-10-21 10:45:32,985 - mmcv - INFO - load model from: /data1/train_code/model_zoo/resnet50-19c8e357.pth
"2021-10-21T10:45:32+08:00" 2021-10-21 10:45:32,985 - mmcv - INFO - Use load_from_local loader
"2021-10-21T10:45:33+08:00" 2021-10-21 10:45:33,285 - mmcv - WARNING - The model and loaded state dict do not match exactly
"2021-10-21T10:45:33+08:00" 
"2021-10-21T10:45:33+08:00" unexpected key in source state_dict: fc.weight, fc.bias
"2021-10-21T10:45:33+08:00" 
"2021-10-21T10:45:33+08:00" /data1/train_code/SoftTeacher/thirdparty/mmdetection/mmdet/datasets/api_wrappers/coco_api.py:22: UserWarning: mmpycocotools is deprecated. Please install official pycocotools by "pip install pycocotools"
"2021-10-21T10:45:33+08:00"   UserWarning)
"2021-10-21T10:45:33+08:00" loading annotations into memory...
"2021-10-21T10:45:34+08:00" Done (t=0.57s)
"2021-10-21T10:45:34+08:00" creating index...
"2021-10-21T10:45:34+08:00" index created!
"2021-10-21T10:45:34+08:00" loading annotations into memory...
"2021-10-21T10:45:46+08:00" Done (t=11.99s)
"2021-10-21T10:45:46+08:00" creating index...
"2021-10-21T10:45:47+08:00" index created!
"2021-10-21T10:45:49+08:00" fatal: Not a git repository (or any parent up to mount point /data1)
"2021-10-21T10:45:49+08:00" Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
"2021-10-21T10:45:53+08:00" /data1/train_code/SoftTeacher/thirdparty/mmdetection/mmdet/datasets/api_wrappers/coco_api.py:22: UserWarning: mmpycocotools is deprecated. Please install official pycocotools by "pip install pycocotools"
"2021-10-21T10:45:53+08:00"   UserWarning)
"2021-10-21T10:45:53+08:00" loading annotations into memory...
"2021-10-21T10:45:53+08:00" Done (t=0.39s)
"2021-10-21T10:45:53+08:00" creating index...
"2021-10-21T10:45:53+08:00" index created!
"2021-10-21T10:45:54+08:00" 2021-10-21 10:45:54,124 - mmdet.ssod - INFO - Start running, host: root@train-coco-full-train-4gpu-1-0, work_dir: /data1/train_code/SoftTeacher/workdir/soft_teacher_faster_rcnn_r50_caffe_fpn_adas_full_720k
"2021-10-21T10:45:54+08:00" 2021-10-21 10:45:54,125 - mmdet.ssod - INFO - Hooks will be executed in the following order:
"2021-10-21T10:45:54+08:00" before_run:
"2021-10-21T10:45:54+08:00" (VERY_HIGH   ) StepLrUpdaterHook                  
"2021-10-21T10:45:54+08:00" (ABOVE_NORMAL) Fp16OptimizerHook                  
"2021-10-21T10:45:54+08:00" (NORMAL      ) CheckpointHook                     
"2021-10-21T10:45:54+08:00" (NORMAL      ) WeightSummary                      
"2021-10-21T10:45:54+08:00" (NORMAL      ) MeanTeacher                        
"2021-10-21T10:45:54+08:00" (80          ) SubModulesDistEvalHook             
"2021-10-21T10:45:54+08:00" (VERY_LOW    ) TextLoggerHook                     
"2021-10-21T10:45:54+08:00" (VERY_LOW    ) TensorboardLoggerHook              
"2021-10-21T10:45:54+08:00"  -------------------- 
"2021-10-21T10:45:54+08:00" before_train_epoch:
"2021-10-21T10:45:54+08:00" (VERY_HIGH   ) StepLrUpdaterHook                  
"2021-10-21T10:45:54+08:00" (NORMAL      ) IterTimerHook                      
"2021-10-21T10:45:54+08:00" (NORMAL      ) NumClassCheckHook                  
"2021-10-21T10:45:54+08:00" (80          ) SubModulesDistEvalHook             
"2021-10-21T10:45:54+08:00" (VERY_LOW    ) TextLoggerHook                     
"2021-10-21T10:45:54+08:00" (VERY_LOW    ) TensorboardLoggerHook              
"2021-10-21T10:45:54+08:00"  -------------------- 
"2021-10-21T10:45:54+08:00" before_train_iter:
"2021-10-21T10:45:54+08:00" (VERY_HIGH   ) StepLrUpdaterHook                  
"2021-10-21T10:45:54+08:00" (NORMAL      ) IterTimerHook                      
"2021-10-21T10:45:54+08:00" (NORMAL      ) MeanTeacher                        
"2021-10-21T10:45:54+08:00" (80          ) SubModulesDistEvalHook             
"2021-10-21T10:45:54+08:00"  -------------------- 
"2021-10-21T10:45:54+08:00" after_train_iter:
"2021-10-21T10:45:54+08:00" (ABOVE_NORMAL) Fp16OptimizerHook                  
"2021-10-21T10:45:54+08:00" (NORMAL      ) CheckpointHook                     
"2021-10-21T10:45:54+08:00" (NORMAL      ) IterTimerHook                      
"2021-10-21T10:45:54+08:00" (NORMAL      ) MeanTeacher                        
"2021-10-21T10:45:54+08:00" (80          ) SubModulesDistEvalHook             
"2021-10-21T10:45:54+08:00" (VERY_LOW    ) TextLoggerHook                     
"2021-10-21T10:45:54+08:00" (VERY_LOW    ) TensorboardLoggerHook              
"2021-10-21T10:45:54+08:00"  -------------------- 
"2021-10-21T10:45:54+08:00" after_train_epoch:
"2021-10-21T10:45:54+08:00" (NORMAL      ) CheckpointHook                     
"2021-10-21T10:45:54+08:00" (80          ) SubModulesDistEvalHook             
"2021-10-21T10:45:54+08:00" (VERY_LOW    ) TextLoggerHook                     
"2021-10-21T10:45:54+08:00" (VERY_LOW    ) TensorboardLoggerHook              
"2021-10-21T10:45:54+08:00"  -------------------- 
"2021-10-21T10:45:54+08:00" before_val_epoch:
"2021-10-21T10:45:54+08:00" (NORMAL      ) IterTimerHook                      
"2021-10-21T10:45:54+08:00" (NORMAL      ) NumClassCheckHook                  
"2021-10-21T10:45:54+08:00" (VERY_LOW    ) TextLoggerHook                     
"2021-10-21T10:45:54+08:00" (VERY_LOW    ) TensorboardLoggerHook              
"2021-10-21T10:45:54+08:00"  -------------------- 
"2021-10-21T10:45:54+08:00" before_val_iter:
"2021-10-21T10:45:54+08:00" (NORMAL      ) IterTimerHook                      
"2021-10-21T10:45:54+08:00"  -------------------- 
"2021-10-21T10:45:54+08:00" after_val_iter:
"2021-10-21T10:45:54+08:00" (NORMAL      ) IterTimerHook                      
"2021-10-21T10:45:54+08:00"  -------------------- 
"2021-10-21T10:45:54+08:00" after_val_epoch:
"2021-10-21T10:45:54+08:00" (VERY_LOW    ) TextLoggerHook                     
"2021-10-21T10:45:54+08:00" (VERY_LOW    ) TensorboardLoggerHook              
"2021-10-21T10:45:54+08:00"  -------------------- 
"2021-10-21T10:45:54+08:00" after_run:
"2021-10-21T10:45:54+08:00" (VERY_LOW    ) TensorboardLoggerHook              
"2021-10-21T10:45:54+08:00"  -------------------- 
"2021-10-21T10:45:54+08:00" 2021-10-21 10:45:54,127 - mmdet.ssod - INFO - workflow: [('train', 1)], max: 720000 iters
"2021-10-21T10:45:54+08:00" 2021-10-21 10:45:54,270 - mmdet.ssod - INFO - 
"2021-10-21T10:45:54+08:00" +--------------------------------------------------------------------------------------------------------------------+
"2021-10-21T10:45:54+08:00" |                                                 Model Information                                                  |
"2021-10-21T10:45:54+08:00" +------------------------------------------------+-----------+---------------+-----------------------+------+--------+
"2021-10-21T10:45:54+08:00" |                      Name                      | Optimized |     Shape     | Value Scale [Min,Max] |  Lr  |   Wd   |
"2021-10-21T10:45:54+08:00" +------------------------------------------------+-----------+---------------+-----------------------+------+--------+
"2021-10-21T10:45:54+08:00" |         teacher.backbone.conv1.weight          |     N     |    64X3X7X7   |  Min:-0.782 Max:0.781 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |          teacher.backbone.bn1.weight           |     N     |       64      |  Min:0.000 Max:0.508  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |           teacher.backbone.bn1.bias            |     N     |       64      |  Min:-0.503 Max:0.848 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer1.0.conv1.weight     |     N     |   64X64X1X1   |  Min:-0.727 Max:0.389 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer1.0.bn1.weight      |     N     |       64      |  Min:0.000 Max:0.375  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer1.0.bn1.bias       |     N     |       64      |  Min:-0.279 Max:0.529 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer1.0.conv2.weight     |     N     |   64X64X3X3   |  Min:-0.468 Max:0.443 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer1.0.bn2.weight      |     N     |       64      |  Min:0.000 Max:0.272  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer1.0.bn2.bias       |     N     |       64      |  Min:-0.228 Max:0.525 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer1.0.conv3.weight     |     N     |   256X64X1X1  |  Min:-0.364 Max:0.394 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer1.0.bn3.weight      |     N     |      256      |  Min:-0.113 Max:0.389 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer1.0.bn3.bias       |     N     |      256      |  Min:-0.307 Max:0.217 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | teacher.backbone.layer1.0.downsample.0.weight  |     N     |   256X64X1X1  |  Min:-0.745 Max:0.988 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | teacher.backbone.layer1.0.downsample.1.weight  |     N     |      256      |  Min:-0.042 Max:0.456 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |  teacher.backbone.layer1.0.downsample.1.bias   |     N     |      256      |  Min:-0.307 Max:0.217 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer1.1.conv1.weight     |     N     |   64X256X1X1  |  Min:-0.202 Max:0.262 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer1.1.bn1.weight      |     N     |       64      |  Min:0.000 Max:0.341  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer1.1.bn1.bias       |     N     |       64      |  Min:-0.405 Max:0.392 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer1.1.conv2.weight     |     N     |   64X64X3X3   |  Min:-0.404 Max:0.520 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer1.1.bn2.weight      |     N     |       64      |  Min:0.119 Max:0.300  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer1.1.bn2.bias       |     N     |       64      |  Min:-0.335 Max:0.313 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer1.1.conv3.weight     |     N     |   256X64X1X1  |  Min:-0.295 Max:0.285 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer1.1.bn3.weight      |     N     |      256      |  Min:-0.114 Max:0.275 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer1.1.bn3.bias       |     N     |      256      |  Min:-0.148 Max:0.156 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer1.2.conv1.weight     |     N     |   64X256X1X1  |  Min:-0.192 Max:0.158 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer1.2.bn1.weight      |     N     |       64      |  Min:0.100 Max:0.245  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer1.2.bn1.bias       |     N     |       64      |  Min:-0.192 Max:0.179 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer1.2.conv2.weight     |     N     |   64X64X3X3   |  Min:-0.225 Max:0.286 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer1.2.bn2.weight      |     N     |       64      |  Min:0.116 Max:0.315  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer1.2.bn2.bias       |     N     |       64      |  Min:-0.341 Max:0.260 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer1.2.conv3.weight     |     N     |   256X64X1X1  |  Min:-0.217 Max:0.275 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer1.2.bn3.weight      |     N     |      256      |  Min:-0.098 Max:0.375 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer1.2.bn3.bias       |     N     |      256      |  Min:-0.168 Max:0.197 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer2.0.conv1.weight     |     N     |  128X256X1X1  |  Min:-0.290 Max:0.353 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer2.0.bn1.weight      |     N     |      128      |  Min:0.108 Max:0.351  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer2.0.bn1.bias       |     N     |      128      |  Min:-0.303 Max:0.116 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer2.0.conv2.weight     |     N     |  128X128X3X3  |  Min:-0.299 Max:0.162 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer2.0.bn2.weight      |     N     |      128      |  Min:0.145 Max:0.291  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer2.0.bn2.bias       |     N     |      128      |  Min:-0.316 Max:0.259 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer2.0.conv3.weight     |     N     |  512X128X1X1  |  Min:-0.340 Max:0.392 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer2.0.bn3.weight      |     N     |      512      |  Min:-0.036 Max:0.328 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer2.0.bn3.bias       |     N     |      512      |  Min:-0.171 Max:0.198 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | teacher.backbone.layer2.0.downsample.0.weight  |     N     |  512X256X1X1  |  Min:-0.329 Max:0.566 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | teacher.backbone.layer2.0.downsample.1.weight  |     N     |      512      |  Min:-0.019 Max:0.373 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |  teacher.backbone.layer2.0.downsample.1.bias   |     N     |      512      |  Min:-0.171 Max:0.198 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer2.1.conv1.weight     |     N     |  128X512X1X1  |  Min:-0.166 Max:0.252 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer2.1.bn1.weight      |     N     |      128      |  Min:0.051 Max:0.219  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer2.1.bn1.bias       |     N     |      128      |  Min:-0.187 Max:0.385 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer2.1.conv2.weight     |     N     |  128X128X3X3  |  Min:-0.242 Max:0.300 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer2.1.bn2.weight      |     N     |      128      |  Min:0.080 Max:0.287  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer2.1.bn2.bias       |     N     |      128      |  Min:-0.182 Max:0.198 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer2.1.conv3.weight     |     N     |  512X128X1X1  |  Min:-0.292 Max:0.304 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer2.1.bn3.weight      |     N     |      512      |  Min:-0.071 Max:0.391 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer2.1.bn3.bias       |     N     |      512      |  Min:-0.238 Max:0.156 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer2.2.conv1.weight     |     N     |  128X512X1X1  |  Min:-0.238 Max:0.189 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer2.2.bn1.weight      |     N     |      128      |  Min:0.107 Max:0.240  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer2.2.bn1.bias       |     N     |      128      |  Min:-0.202 Max:0.268 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer2.2.conv2.weight     |     N     |  128X128X3X3  |  Min:-0.206 Max:0.256 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer2.2.bn2.weight      |     N     |      128      |  Min:0.108 Max:0.254  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer2.2.bn2.bias       |     N     |      128      |  Min:-0.173 Max:0.281 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer2.2.conv3.weight     |     N     |  512X128X1X1  |  Min:-0.284 Max:0.352 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer2.2.bn3.weight      |     N     |      512      |  Min:-0.065 Max:0.329 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer2.2.bn3.bias       |     N     |      512      |  Min:-0.269 Max:0.166 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer2.3.conv1.weight     |     N     |  128X512X1X1  |  Min:-0.180 Max:0.281 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer2.3.bn1.weight      |     N     |      128      |  Min:0.119 Max:0.239  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer2.3.bn1.bias       |     N     |      128      |  Min:-0.235 Max:0.111 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer2.3.conv2.weight     |     N     |  128X128X3X3  |  Min:-0.179 Max:0.221 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer2.3.bn2.weight      |     N     |      128      |  Min:0.121 Max:0.259  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer2.3.bn2.bias       |     N     |      128      |  Min:-0.218 Max:0.278 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer2.3.conv3.weight     |     N     |  512X128X1X1  |  Min:-0.258 Max:0.296 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer2.3.bn3.weight      |     N     |      512      |  Min:-0.051 Max:0.316 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer2.3.bn3.bias       |     N     |      512      |  Min:-0.213 Max:0.123 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.0.conv1.weight     |     N     |  256X512X1X1  |  Min:-0.334 Max:0.343 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.0.bn1.weight      |     N     |      256      |  Min:0.145 Max:0.316  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.0.bn1.bias       |     N     |      256      |  Min:-0.379 Max:0.113 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.0.conv2.weight     |     N     |  256X256X3X3  |  Min:-0.201 Max:0.195 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.0.bn2.weight      |     N     |      256      |  Min:0.127 Max:0.322  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.0.bn2.bias       |     N     |      256      |  Min:-0.177 Max:0.268 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.0.conv3.weight     |     N     |  1024X256X1X1 |  Min:-0.287 Max:0.321 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.0.bn3.weight      |     N     |      1024     |  Min:-0.002 Max:0.346 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.0.bn3.bias       |     N     |      1024     |  Min:-0.123 Max:0.163 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | teacher.backbone.layer3.0.downsample.0.weight  |     N     |  1024X512X1X1 |  Min:-0.286 Max:0.346 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | teacher.backbone.layer3.0.downsample.1.weight  |     N     |      1024     |  Min:-0.080 Max:0.298 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |  teacher.backbone.layer3.0.downsample.1.bias   |     N     |      1024     |  Min:-0.123 Max:0.163 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.1.conv1.weight     |     N     |  256X1024X1X1 |  Min:-0.182 Max:0.294 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.1.bn1.weight      |     N     |      256      |  Min:0.095 Max:0.303  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.1.bn1.bias       |     N     |      256      |  Min:-0.154 Max:0.175 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.1.conv2.weight     |     N     |  256X256X3X3  |  Min:-0.177 Max:0.263 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.1.bn2.weight      |     N     |      256      |  Min:0.102 Max:0.419  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.1.bn2.bias       |     N     |      256      |  Min:-0.384 Max:0.197 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.1.conv3.weight     |     N     |  1024X256X1X1 |  Min:-0.497 Max:0.444 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.1.bn3.weight      |     N     |      1024     |  Min:-0.015 Max:0.411 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.1.bn3.bias       |     N     |      1024     |  Min:-0.215 Max:0.149 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.2.conv1.weight     |     N     |  256X1024X1X1 |  Min:-0.202 Max:0.271 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.2.bn1.weight      |     N     |      256      |  Min:0.098 Max:0.237  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.2.bn1.bias       |     N     |      256      |  Min:-0.232 Max:0.119 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.2.conv2.weight     |     N     |  256X256X3X3  |  Min:-0.195 Max:0.210 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.2.bn2.weight      |     N     |      256      |  Min:0.097 Max:0.318  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.2.bn2.bias       |     N     |      256      |  Min:-0.220 Max:0.219 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.2.conv3.weight     |     N     |  1024X256X1X1 |  Min:-0.354 Max:0.305 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.2.bn3.weight      |     N     |      1024     |  Min:-0.034 Max:0.246 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.2.bn3.bias       |     N     |      1024     |  Min:-0.263 Max:0.174 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.3.conv1.weight     |     N     |  256X1024X1X1 |  Min:-0.212 Max:0.239 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.3.bn1.weight      |     N     |      256      |  Min:0.095 Max:0.245  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.3.bn1.bias       |     N     |      256      |  Min:-0.260 Max:0.111 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.3.conv2.weight     |     N     |  256X256X3X3  |  Min:-0.158 Max:0.279 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.3.bn2.weight      |     N     |      256      |  Min:0.097 Max:0.259  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.3.bn2.bias       |     N     |      256      |  Min:-0.208 Max:0.172 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.3.conv3.weight     |     N     |  1024X256X1X1 |  Min:-0.244 Max:0.313 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.3.bn3.weight      |     N     |      1024     |  Min:-0.030 Max:0.294 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.3.bn3.bias       |     N     |      1024     |  Min:-0.225 Max:0.138 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.4.conv1.weight     |     N     |  256X1024X1X1 |  Min:-0.194 Max:0.272 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.4.bn1.weight      |     N     |      256      |  Min:0.095 Max:0.269  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.4.bn1.bias       |     N     |      256      |  Min:-0.324 Max:0.125 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.4.conv2.weight     |     N     |  256X256X3X3  |  Min:-0.181 Max:0.192 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.4.bn2.weight      |     N     |      256      |  Min:0.099 Max:0.259  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.4.bn2.bias       |     N     |      256      |  Min:-0.330 Max:0.209 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.4.conv3.weight     |     N     |  1024X256X1X1 |  Min:-0.237 Max:0.316 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.4.bn3.weight      |     N     |      1024     |  Min:-0.049 Max:0.235 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.4.bn3.bias       |     N     |      1024     |  Min:-0.316 Max:0.128 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.5.conv1.weight     |     N     |  256X1024X1X1 |  Min:-0.220 Max:0.399 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.5.bn1.weight      |     N     |      256      |  Min:0.090 Max:0.294  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.5.bn1.bias       |     N     |      256      |  Min:-0.314 Max:0.136 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.5.conv2.weight     |     N     |  256X256X3X3  |  Min:-0.224 Max:0.214 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.5.bn2.weight      |     N     |      256      |  Min:0.124 Max:0.525  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.5.bn2.bias       |     N     |      256      |  Min:-0.399 Max:0.166 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer3.5.conv3.weight     |     N     |  1024X256X1X1 |  Min:-0.329 Max:0.267 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer3.5.bn3.weight      |     N     |      1024     |  Min:-0.066 Max:0.301 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer3.5.bn3.bias       |     N     |      1024     |  Min:-0.371 Max:0.147 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer4.0.conv1.weight     |     N     |  512X1024X1X1 |  Min:-0.341 Max:0.342 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer4.0.bn1.weight      |     N     |      512      |  Min:0.107 Max:0.294  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer4.0.bn1.bias       |     N     |      512      |  Min:-0.350 Max:0.127 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer4.0.conv2.weight     |     N     |  512X512X3X3  |  Min:-0.309 Max:0.399 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer4.0.bn2.weight      |     N     |      512      |  Min:0.149 Max:0.296  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer4.0.bn2.bias       |     N     |      512      |  Min:-0.188 Max:0.164 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer4.0.conv3.weight     |     N     |  2048X512X1X1 |  Min:-0.262 Max:0.355 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer4.0.bn3.weight      |     N     |      2048     |  Min:0.034 Max:0.640  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer4.0.bn3.bias       |     N     |      2048     |  Min:-0.141 Max:0.206 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | teacher.backbone.layer4.0.downsample.0.weight  |     N     | 2048X1024X1X1 |  Min:-0.346 Max:0.641 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | teacher.backbone.layer4.0.downsample.1.weight  |     N     |      2048     |  Min:0.112 Max:0.898  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |  teacher.backbone.layer4.0.downsample.1.bias   |     N     |      2048     |  Min:-0.141 Max:0.206 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer4.1.conv1.weight     |     N     |  512X2048X1X1 |  Min:-0.429 Max:0.700 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer4.1.bn1.weight      |     N     |      512      |  Min:0.094 Max:0.291  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer4.1.bn1.bias       |     N     |      512      |  Min:-0.320 Max:0.117 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer4.1.conv2.weight     |     N     |  512X512X3X3  |  Min:-0.226 Max:0.169 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer4.1.bn2.weight      |     N     |      512      |  Min:0.147 Max:0.305  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer4.1.bn2.bias       |     N     |      512      |  Min:-0.348 Max:0.081 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer4.1.conv3.weight     |     N     |  2048X512X1X1 |  Min:-0.205 Max:0.243 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer4.1.bn3.weight      |     N     |      2048     |  Min:0.130 Max:0.764  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer4.1.bn3.bias       |     N     |      2048     |  Min:-0.216 Max:0.221 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer4.2.conv1.weight     |     N     |  512X2048X1X1 |  Min:-0.454 Max:0.325 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer4.2.bn1.weight      |     N     |      512      |  Min:0.113 Max:0.487  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer4.2.bn1.bias       |     N     |      512      |  Min:-0.335 Max:0.081 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer4.2.conv2.weight     |     N     |  512X512X3X3  |  Min:-0.142 Max:0.088 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer4.2.bn2.weight      |     N     |      512      |  Min:0.134 Max:0.329  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer4.2.bn2.bias       |     N     |      512      |  Min:-0.294 Max:0.201 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.backbone.layer4.2.conv3.weight     |     N     |  2048X512X1X1 |  Min:-0.151 Max:0.280 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.backbone.layer4.2.bn3.weight      |     N     |      2048     |  Min:0.112 Max:1.320  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.backbone.layer4.2.bn3.bias       |     N     |      2048     |  Min:-0.150 Max:0.188 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |    teacher.neck.lateral_convs.0.conv.weight    |     N     |  256X256X1X1  |  Min:-0.108 Max:0.108 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.neck.lateral_convs.0.conv.bias     |     N     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |    teacher.neck.lateral_convs.1.conv.weight    |     N     |  256X512X1X1  |  Min:-0.088 Max:0.088 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.neck.lateral_convs.1.conv.bias     |     N     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |    teacher.neck.lateral_convs.2.conv.weight    |     N     |  256X1024X1X1 |  Min:-0.068 Max:0.068 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.neck.lateral_convs.2.conv.bias     |     N     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |    teacher.neck.lateral_convs.3.conv.weight    |     N     |  256X2048X1X1 |  Min:-0.051 Max:0.051 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.neck.lateral_convs.3.conv.bias     |     N     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.neck.fpn_convs.0.conv.weight      |     N     |  256X256X3X3  |  Min:-0.036 Max:0.036 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.neck.fpn_convs.0.conv.bias       |     N     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.neck.fpn_convs.1.conv.weight      |     N     |  256X256X3X3  |  Min:-0.036 Max:0.036 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.neck.fpn_convs.1.conv.bias       |     N     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.neck.fpn_convs.2.conv.weight      |     N     |  256X256X3X3  |  Min:-0.036 Max:0.036 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.neck.fpn_convs.2.conv.bias       |     N     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      teacher.neck.fpn_convs.3.conv.weight      |     N     |  256X256X3X3  |  Min:-0.036 Max:0.036 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       teacher.neck.fpn_convs.3.conv.bias       |     N     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |        teacher.rpn_head.rpn_conv.weight        |     N     |  256X256X3X3  |  Min:-0.047 Max:0.046 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |         teacher.rpn_head.rpn_conv.bias         |     N     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |        teacher.rpn_head.rpn_cls.weight         |     N     |   3X256X1X1   |  Min:-0.033 Max:0.036 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |         teacher.rpn_head.rpn_cls.bias          |     N     |       3       |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |        teacher.rpn_head.rpn_reg.weight         |     N     |   12X256X1X1  |  Min:-0.040 Max:0.034 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |         teacher.rpn_head.rpn_reg.bias          |     N     |       12      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |    teacher.roi_head.bbox_head.fc_cls.weight    |     N     |    81X1024    |  Min:-0.186 Max:0.190 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.roi_head.bbox_head.fc_cls.bias     |     N     |       81      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |    teacher.roi_head.bbox_head.fc_reg.weight    |     N     |    320X1024   |  Min:-0.186 Max:0.198 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     teacher.roi_head.bbox_head.fc_reg.bias     |     N     |      320      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | teacher.roi_head.bbox_head.shared_fcs.0.weight |     N     |   1024X12544  |  Min:-0.065 Max:0.065 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |  teacher.roi_head.bbox_head.shared_fcs.0.bias  |     N     |      1024     |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | teacher.roi_head.bbox_head.shared_fcs.1.weight |     N     |   1024X1024   |  Min:-0.147 Max:0.159 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |  teacher.roi_head.bbox_head.shared_fcs.1.bias  |     N     |      1024     |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |         student.backbone.conv1.weight          |     N     |    64X3X7X7   |  Min:-0.782 Max:0.781 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |          student.backbone.bn1.weight           |     N     |       64      |  Min:0.000 Max:0.508  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |           student.backbone.bn1.bias            |     N     |       64      |  Min:-0.503 Max:0.848 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer1.0.conv1.weight     |     N     |   64X64X1X1   |  Min:-0.727 Max:0.389 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer1.0.bn1.weight      |     N     |       64      |  Min:0.000 Max:0.375  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer1.0.bn1.bias       |     N     |       64      |  Min:-0.279 Max:0.529 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer1.0.conv2.weight     |     N     |   64X64X3X3   |  Min:-0.468 Max:0.443 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer1.0.bn2.weight      |     N     |       64      |  Min:0.000 Max:0.272  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer1.0.bn2.bias       |     N     |       64      |  Min:-0.228 Max:0.525 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer1.0.conv3.weight     |     N     |   256X64X1X1  |  Min:-0.364 Max:0.394 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer1.0.bn3.weight      |     N     |      256      |  Min:-0.113 Max:0.389 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer1.0.bn3.bias       |     N     |      256      |  Min:-0.307 Max:0.217 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | student.backbone.layer1.0.downsample.0.weight  |     N     |   256X64X1X1  |  Min:-0.745 Max:0.988 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | student.backbone.layer1.0.downsample.1.weight  |     N     |      256      |  Min:-0.042 Max:0.456 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |  student.backbone.layer1.0.downsample.1.bias   |     N     |      256      |  Min:-0.307 Max:0.217 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer1.1.conv1.weight     |     N     |   64X256X1X1  |  Min:-0.202 Max:0.262 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer1.1.bn1.weight      |     N     |       64      |  Min:0.000 Max:0.341  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer1.1.bn1.bias       |     N     |       64      |  Min:-0.405 Max:0.392 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer1.1.conv2.weight     |     N     |   64X64X3X3   |  Min:-0.404 Max:0.520 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer1.1.bn2.weight      |     N     |       64      |  Min:0.119 Max:0.300  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer1.1.bn2.bias       |     N     |       64      |  Min:-0.335 Max:0.313 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer1.1.conv3.weight     |     N     |   256X64X1X1  |  Min:-0.295 Max:0.285 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer1.1.bn3.weight      |     N     |      256      |  Min:-0.114 Max:0.275 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer1.1.bn3.bias       |     N     |      256      |  Min:-0.148 Max:0.156 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer1.2.conv1.weight     |     N     |   64X256X1X1  |  Min:-0.192 Max:0.158 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer1.2.bn1.weight      |     N     |       64      |  Min:0.100 Max:0.245  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer1.2.bn1.bias       |     N     |       64      |  Min:-0.192 Max:0.179 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer1.2.conv2.weight     |     N     |   64X64X3X3   |  Min:-0.225 Max:0.286 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer1.2.bn2.weight      |     N     |       64      |  Min:0.116 Max:0.315  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer1.2.bn2.bias       |     N     |       64      |  Min:-0.341 Max:0.260 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer1.2.conv3.weight     |     N     |   256X64X1X1  |  Min:-0.217 Max:0.275 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer1.2.bn3.weight      |     N     |      256      |  Min:-0.098 Max:0.375 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer1.2.bn3.bias       |     N     |      256      |  Min:-0.168 Max:0.197 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer2.0.conv1.weight     |     Y     |  128X256X1X1  |  Min:-0.290 Max:0.353 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer2.0.bn1.weight      |     N     |      128      |  Min:0.108 Max:0.351  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer2.0.bn1.bias       |     N     |      128      |  Min:-0.303 Max:0.116 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer2.0.conv2.weight     |     Y     |  128X128X3X3  |  Min:-0.299 Max:0.162 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer2.0.bn2.weight      |     N     |      128      |  Min:0.145 Max:0.291  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer2.0.bn2.bias       |     N     |      128      |  Min:-0.316 Max:0.259 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer2.0.conv3.weight     |     Y     |  512X128X1X1  |  Min:-0.340 Max:0.392 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer2.0.bn3.weight      |     N     |      512      |  Min:-0.036 Max:0.328 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer2.0.bn3.bias       |     N     |      512      |  Min:-0.171 Max:0.198 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | student.backbone.layer2.0.downsample.0.weight  |     Y     |  512X256X1X1  |  Min:-0.329 Max:0.566 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | student.backbone.layer2.0.downsample.1.weight  |     N     |      512      |  Min:-0.019 Max:0.373 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |  student.backbone.layer2.0.downsample.1.bias   |     N     |      512      |  Min:-0.171 Max:0.198 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer2.1.conv1.weight     |     Y     |  128X512X1X1  |  Min:-0.166 Max:0.252 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer2.1.bn1.weight      |     N     |      128      |  Min:0.051 Max:0.219  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer2.1.bn1.bias       |     N     |      128      |  Min:-0.187 Max:0.385 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer2.1.conv2.weight     |     Y     |  128X128X3X3  |  Min:-0.242 Max:0.300 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer2.1.bn2.weight      |     N     |      128      |  Min:0.080 Max:0.287  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer2.1.bn2.bias       |     N     |      128      |  Min:-0.182 Max:0.198 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer2.1.conv3.weight     |     Y     |  512X128X1X1  |  Min:-0.292 Max:0.304 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer2.1.bn3.weight      |     N     |      512      |  Min:-0.071 Max:0.391 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer2.1.bn3.bias       |     N     |      512      |  Min:-0.238 Max:0.156 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer2.2.conv1.weight     |     Y     |  128X512X1X1  |  Min:-0.238 Max:0.189 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer2.2.bn1.weight      |     N     |      128      |  Min:0.107 Max:0.240  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer2.2.bn1.bias       |     N     |      128      |  Min:-0.202 Max:0.268 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer2.2.conv2.weight     |     Y     |  128X128X3X3  |  Min:-0.206 Max:0.256 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer2.2.bn2.weight      |     N     |      128      |  Min:0.108 Max:0.254  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer2.2.bn2.bias       |     N     |      128      |  Min:-0.173 Max:0.281 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer2.2.conv3.weight     |     Y     |  512X128X1X1  |  Min:-0.284 Max:0.352 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer2.2.bn3.weight      |     N     |      512      |  Min:-0.065 Max:0.329 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer2.2.bn3.bias       |     N     |      512      |  Min:-0.269 Max:0.166 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer2.3.conv1.weight     |     Y     |  128X512X1X1  |  Min:-0.180 Max:0.281 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer2.3.bn1.weight      |     N     |      128      |  Min:0.119 Max:0.239  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer2.3.bn1.bias       |     N     |      128      |  Min:-0.235 Max:0.111 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer2.3.conv2.weight     |     Y     |  128X128X3X3  |  Min:-0.179 Max:0.221 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer2.3.bn2.weight      |     N     |      128      |  Min:0.121 Max:0.259  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer2.3.bn2.bias       |     N     |      128      |  Min:-0.218 Max:0.278 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer2.3.conv3.weight     |     Y     |  512X128X1X1  |  Min:-0.258 Max:0.296 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer2.3.bn3.weight      |     N     |      512      |  Min:-0.051 Max:0.316 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer2.3.bn3.bias       |     N     |      512      |  Min:-0.213 Max:0.123 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.0.conv1.weight     |     Y     |  256X512X1X1  |  Min:-0.334 Max:0.343 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.0.bn1.weight      |     N     |      256      |  Min:0.145 Max:0.316  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.0.bn1.bias       |     N     |      256      |  Min:-0.379 Max:0.113 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.0.conv2.weight     |     Y     |  256X256X3X3  |  Min:-0.201 Max:0.195 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.0.bn2.weight      |     N     |      256      |  Min:0.127 Max:0.322  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.0.bn2.bias       |     N     |      256      |  Min:-0.177 Max:0.268 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.0.conv3.weight     |     Y     |  1024X256X1X1 |  Min:-0.287 Max:0.321 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.0.bn3.weight      |     N     |      1024     |  Min:-0.002 Max:0.346 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.0.bn3.bias       |     N     |      1024     |  Min:-0.123 Max:0.163 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | student.backbone.layer3.0.downsample.0.weight  |     Y     |  1024X512X1X1 |  Min:-0.286 Max:0.346 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | student.backbone.layer3.0.downsample.1.weight  |     N     |      1024     |  Min:-0.080 Max:0.298 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |  student.backbone.layer3.0.downsample.1.bias   |     N     |      1024     |  Min:-0.123 Max:0.163 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.1.conv1.weight     |     Y     |  256X1024X1X1 |  Min:-0.182 Max:0.294 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.1.bn1.weight      |     N     |      256      |  Min:0.095 Max:0.303  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.1.bn1.bias       |     N     |      256      |  Min:-0.154 Max:0.175 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.1.conv2.weight     |     Y     |  256X256X3X3  |  Min:-0.177 Max:0.263 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.1.bn2.weight      |     N     |      256      |  Min:0.102 Max:0.419  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.1.bn2.bias       |     N     |      256      |  Min:-0.384 Max:0.197 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.1.conv3.weight     |     Y     |  1024X256X1X1 |  Min:-0.497 Max:0.444 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.1.bn3.weight      |     N     |      1024     |  Min:-0.015 Max:0.411 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.1.bn3.bias       |     N     |      1024     |  Min:-0.215 Max:0.149 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.2.conv1.weight     |     Y     |  256X1024X1X1 |  Min:-0.202 Max:0.271 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.2.bn1.weight      |     N     |      256      |  Min:0.098 Max:0.237  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.2.bn1.bias       |     N     |      256      |  Min:-0.232 Max:0.119 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.2.conv2.weight     |     Y     |  256X256X3X3  |  Min:-0.195 Max:0.210 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.2.bn2.weight      |     N     |      256      |  Min:0.097 Max:0.318  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.2.bn2.bias       |     N     |      256      |  Min:-0.220 Max:0.219 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.2.conv3.weight     |     Y     |  1024X256X1X1 |  Min:-0.354 Max:0.305 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.2.bn3.weight      |     N     |      1024     |  Min:-0.034 Max:0.246 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.2.bn3.bias       |     N     |      1024     |  Min:-0.263 Max:0.174 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.3.conv1.weight     |     Y     |  256X1024X1X1 |  Min:-0.212 Max:0.239 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.3.bn1.weight      |     N     |      256      |  Min:0.095 Max:0.245  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.3.bn1.bias       |     N     |      256      |  Min:-0.260 Max:0.111 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.3.conv2.weight     |     Y     |  256X256X3X3  |  Min:-0.158 Max:0.279 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.3.bn2.weight      |     N     |      256      |  Min:0.097 Max:0.259  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.3.bn2.bias       |     N     |      256      |  Min:-0.208 Max:0.172 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.3.conv3.weight     |     Y     |  1024X256X1X1 |  Min:-0.244 Max:0.313 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.3.bn3.weight      |     N     |      1024     |  Min:-0.030 Max:0.294 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.3.bn3.bias       |     N     |      1024     |  Min:-0.225 Max:0.138 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.4.conv1.weight     |     Y     |  256X1024X1X1 |  Min:-0.194 Max:0.272 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.4.bn1.weight      |     N     |      256      |  Min:0.095 Max:0.269  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.4.bn1.bias       |     N     |      256      |  Min:-0.324 Max:0.125 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.4.conv2.weight     |     Y     |  256X256X3X3  |  Min:-0.181 Max:0.192 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.4.bn2.weight      |     N     |      256      |  Min:0.099 Max:0.259  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.4.bn2.bias       |     N     |      256      |  Min:-0.330 Max:0.209 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.4.conv3.weight     |     Y     |  1024X256X1X1 |  Min:-0.237 Max:0.316 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.4.bn3.weight      |     N     |      1024     |  Min:-0.049 Max:0.235 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.4.bn3.bias       |     N     |      1024     |  Min:-0.316 Max:0.128 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.5.conv1.weight     |     Y     |  256X1024X1X1 |  Min:-0.220 Max:0.399 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.5.bn1.weight      |     N     |      256      |  Min:0.090 Max:0.294  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.5.bn1.bias       |     N     |      256      |  Min:-0.314 Max:0.136 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.5.conv2.weight     |     Y     |  256X256X3X3  |  Min:-0.224 Max:0.214 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.5.bn2.weight      |     N     |      256      |  Min:0.124 Max:0.525  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.5.bn2.bias       |     N     |      256      |  Min:-0.399 Max:0.166 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer3.5.conv3.weight     |     Y     |  1024X256X1X1 |  Min:-0.329 Max:0.267 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer3.5.bn3.weight      |     N     |      1024     |  Min:-0.066 Max:0.301 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer3.5.bn3.bias       |     N     |      1024     |  Min:-0.371 Max:0.147 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer4.0.conv1.weight     |     Y     |  512X1024X1X1 |  Min:-0.341 Max:0.342 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer4.0.bn1.weight      |     N     |      512      |  Min:0.107 Max:0.294  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer4.0.bn1.bias       |     N     |      512      |  Min:-0.350 Max:0.127 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer4.0.conv2.weight     |     Y     |  512X512X3X3  |  Min:-0.309 Max:0.399 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer4.0.bn2.weight      |     N     |      512      |  Min:0.149 Max:0.296  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer4.0.bn2.bias       |     N     |      512      |  Min:-0.188 Max:0.164 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer4.0.conv3.weight     |     Y     |  2048X512X1X1 |  Min:-0.262 Max:0.355 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer4.0.bn3.weight      |     N     |      2048     |  Min:0.034 Max:0.640  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer4.0.bn3.bias       |     N     |      2048     |  Min:-0.141 Max:0.206 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | student.backbone.layer4.0.downsample.0.weight  |     Y     | 2048X1024X1X1 |  Min:-0.346 Max:0.641 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | student.backbone.layer4.0.downsample.1.weight  |     N     |      2048     |  Min:0.112 Max:0.898  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |  student.backbone.layer4.0.downsample.1.bias   |     N     |      2048     |  Min:-0.141 Max:0.206 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer4.1.conv1.weight     |     Y     |  512X2048X1X1 |  Min:-0.429 Max:0.700 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer4.1.bn1.weight      |     N     |      512      |  Min:0.094 Max:0.291  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer4.1.bn1.bias       |     N     |      512      |  Min:-0.320 Max:0.117 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer4.1.conv2.weight     |     Y     |  512X512X3X3  |  Min:-0.226 Max:0.169 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer4.1.bn2.weight      |     N     |      512      |  Min:0.147 Max:0.305  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer4.1.bn2.bias       |     N     |      512      |  Min:-0.348 Max:0.081 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer4.1.conv3.weight     |     Y     |  2048X512X1X1 |  Min:-0.205 Max:0.243 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer4.1.bn3.weight      |     N     |      2048     |  Min:0.130 Max:0.764  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer4.1.bn3.bias       |     N     |      2048     |  Min:-0.216 Max:0.221 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer4.2.conv1.weight     |     Y     |  512X2048X1X1 |  Min:-0.454 Max:0.325 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer4.2.bn1.weight      |     N     |      512      |  Min:0.113 Max:0.487  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer4.2.bn1.bias       |     N     |      512      |  Min:-0.335 Max:0.081 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer4.2.conv2.weight     |     Y     |  512X512X3X3  |  Min:-0.142 Max:0.088 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer4.2.bn2.weight      |     N     |      512      |  Min:0.134 Max:0.329  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer4.2.bn2.bias       |     N     |      512      |  Min:-0.294 Max:0.201 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.backbone.layer4.2.conv3.weight     |     Y     |  2048X512X1X1 |  Min:-0.151 Max:0.280 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.backbone.layer4.2.bn3.weight      |     N     |      2048     |  Min:0.112 Max:1.320  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.backbone.layer4.2.bn3.bias       |     N     |      2048     |  Min:-0.150 Max:0.188 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |    student.neck.lateral_convs.0.conv.weight    |     Y     |  256X256X1X1  |  Min:-0.108 Max:0.108 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.neck.lateral_convs.0.conv.bias     |     Y     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |    student.neck.lateral_convs.1.conv.weight    |     Y     |  256X512X1X1  |  Min:-0.088 Max:0.088 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.neck.lateral_convs.1.conv.bias     |     Y     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |    student.neck.lateral_convs.2.conv.weight    |     Y     |  256X1024X1X1 |  Min:-0.068 Max:0.068 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.neck.lateral_convs.2.conv.bias     |     Y     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |    student.neck.lateral_convs.3.conv.weight    |     Y     |  256X2048X1X1 |  Min:-0.051 Max:0.051 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.neck.lateral_convs.3.conv.bias     |     Y     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.neck.fpn_convs.0.conv.weight      |     Y     |  256X256X3X3  |  Min:-0.036 Max:0.036 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.neck.fpn_convs.0.conv.bias       |     Y     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.neck.fpn_convs.1.conv.weight      |     Y     |  256X256X3X3  |  Min:-0.036 Max:0.036 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.neck.fpn_convs.1.conv.bias       |     Y     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.neck.fpn_convs.2.conv.weight      |     Y     |  256X256X3X3  |  Min:-0.036 Max:0.036 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.neck.fpn_convs.2.conv.bias       |     Y     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |      student.neck.fpn_convs.3.conv.weight      |     Y     |  256X256X3X3  |  Min:-0.036 Max:0.036 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |       student.neck.fpn_convs.3.conv.bias       |     Y     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |        student.rpn_head.rpn_conv.weight        |     Y     |  256X256X3X3  |  Min:-0.052 Max:0.043 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |         student.rpn_head.rpn_conv.bias         |     Y     |      256      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |        student.rpn_head.rpn_cls.weight         |     Y     |   3X256X1X1   |  Min:-0.029 Max:0.034 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |         student.rpn_head.rpn_cls.bias          |     Y     |       3       |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |        student.rpn_head.rpn_reg.weight         |     Y     |   12X256X1X1  |  Min:-0.033 Max:0.034 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |         student.rpn_head.rpn_reg.bias          |     Y     |       12      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |    student.roi_head.bbox_head.fc_cls.weight    |     Y     |    81X1024    |  Min:-0.197 Max:0.201 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.roi_head.bbox_head.fc_cls.bias     |     Y     |       81      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |    student.roi_head.bbox_head.fc_reg.weight    |     Y     |    320X1024   |  Min:-0.203 Max:0.174 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |     student.roi_head.bbox_head.fc_reg.bias     |     Y     |      320      |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | student.roi_head.bbox_head.shared_fcs.0.weight |     Y     |   1024X12544  |  Min:-0.065 Max:0.064 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |  student.roi_head.bbox_head.shared_fcs.0.bias  |     Y     |      1024     |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" | student.roi_head.bbox_head.shared_fcs.1.weight |     Y     |   1024X1024   |  Min:-0.144 Max:0.143 | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" |  student.roi_head.bbox_head.shared_fcs.1.bias  |     Y     |      1024     |  Min:0.000 Max:0.000  | 0.01 | 0.0001 |
"2021-10-21T10:45:54+08:00" +------------------------------------------------+-----------+---------------+-----------------------+------+--------+
"2021-10-21T10:47:09+08:00" /data1/train_code/SoftTeacher/thirdparty/mmdetection/mmdet/core/anchor/anchor_generator.py:324: UserWarning: ``grid_anchors`` would be deprecated soon. Please use ``grid_priors`` 
"2021-10-21T10:47:09+08:00"   warnings.warn('``grid_anchors`` would be deprecated soon. '
"2021-10-21T10:47:09+08:00" /data1/train_code/SoftTeacher/thirdparty/mmdetection/mmdet/core/anchor/anchor_generator.py:361: UserWarning: ``single_level_grid_anchors`` would be deprecated soon. Please use ``single_level_grid_priors`` 
"2021-10-21T10:47:09+08:00"   '``single_level_grid_anchors`` would be deprecated soon. '
"2021-10-21T10:47:11+08:00" 2021-10-21 10:47:11,950 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 2147483648.0
"2021-10-21T10:47:13+08:00" 2021-10-21 10:47:13,019 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1073741824.0
"2021-10-21T10:47:14+08:00" 2021-10-21 10:47:14,148 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 536870912.0
"2021-10-21T10:47:15+08:00" 2021-10-21 10:47:15,176 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 268435456.0
"2021-10-21T10:47:16+08:00" 2021-10-21 10:47:16,204 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 134217728.0
"2021-10-21T10:47:17+08:00" 2021-10-21 10:47:17,082 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 67108864.0
"2021-10-21T10:47:18+08:00" 2021-10-21 10:47:18,003 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 33554432.0
"2021-10-21T10:47:18+08:00" 2021-10-21 10:47:18,999 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 16777216.0
"2021-10-21T10:47:20+08:00" 2021-10-21 10:47:20,136 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 8388608.0
"2021-10-21T10:47:21+08:00" 2021-10-21 10:47:21,097 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 4194304.0
"2021-10-21T10:47:22+08:00" 2021-10-21 10:47:22,144 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 2097152.0
"2021-10-21T10:47:23+08:00" 2021-10-21 10:47:23,215 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1048576.0
"2021-10-21T10:47:24+08:00" 2021-10-21 10:47:24,115 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 524288.0
"2021-10-21T10:47:24+08:00" 2021-10-21 10:47:24,961 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 262144.0
"2021-10-21T10:47:26+08:00" 2021-10-21 10:47:26,028 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 131072.0
"2021-10-21T10:47:26+08:00" 2021-10-21 10:47:26,989 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 65536.0
"2021-10-21T10:47:27+08:00" 2021-10-21 10:47:27,972 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 32768.0
"2021-10-21T10:47:29+08:00" 2021-10-21 10:47:29,024 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 16384.0
"2021-10-21T10:47:29+08:00" 2021-10-21 10:47:29,941 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 8192.0
"2021-10-21T10:47:30+08:00" 2021-10-21 10:47:30,900 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 4096.0
"2021-10-21T10:47:32+08:00" 2021-10-21 10:47:32,108 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 2048.0
"2021-10-21T10:47:33+08:00" 2021-10-21 10:47:33,114 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1024.0
"2021-10-21T10:47:33+08:00" 2021-10-21 10:47:33,983 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 512.0
"2021-10-21T10:47:35+08:00" 2021-10-21 10:47:35,078 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 256.0
"2021-10-21T10:47:36+08:00" 2021-10-21 10:47:36,120 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 128.0
"2021-10-21T10:47:38+08:00" 2021-10-21 10:47:38,257 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 64.0
"2021-10-21T10:47:39+08:00" 2021-10-21 10:47:39,329 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 32.0
"2021-10-21T10:47:40+08:00" 2021-10-21 10:47:40,375 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 16.0
"2021-10-21T10:47:41+08:00" 2021-10-21 10:47:41,250 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 8.0
"2021-10-21T10:47:42+08:00" 2021-10-21 10:47:42,157 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 4.0
"2021-10-21T10:47:43+08:00" 2021-10-21 10:47:43,020 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 2.0
"2021-10-21T10:47:43+08:00" 2021-10-21 10:47:43,949 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1.0
"2021-10-21T10:47:44+08:00" 2021-10-21 10:47:44,841 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:45+08:00" 2021-10-21 10:47:45,667 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:46+08:00" 2021-10-21 10:47:46,564 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:47+08:00" 2021-10-21 10:47:47,531 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:48+08:00" 2021-10-21 10:47:48,349 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:49+08:00" 2021-10-21 10:47:49,092 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:49+08:00" 2021-10-21 10:47:49,717 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:50+08:00" 2021-10-21 10:47:50,526 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:51+08:00" 2021-10-21 10:47:51,409 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:52+08:00" 2021-10-21 10:47:52,132 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:53+08:00" 2021-10-21 10:47:53,001 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:53+08:00" 2021-10-21 10:47:53,862 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:54+08:00" 2021-10-21 10:47:54,695 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:55+08:00" 2021-10-21 10:47:55,463 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:56+08:00" 2021-10-21 10:47:56,211 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:56+08:00" 2021-10-21 10:47:56,869 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:57+08:00" 2021-10-21 10:47:57,569 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:57+08:00" 2021-10-21 10:47:57,570 - mmdet.ssod - INFO - Iter [50/720000]  lr: 9.890e-04, eta: 8 days, 2:38:24, time: 0.973, data_time: 0.042, memory: 9702, ema_momentum: 0.9800, sup_loss_rpn_cls: nan, sup_loss_rpn_bbox: nan, sup_loss_cls: nan, sup_acc: 31.7076, sup_loss_bbox: nan, unsup_loss_rpn_cls: nan, unsup_loss_rpn_bbox: nan, unsup_loss_cls: nan, unsup_acc: 36.2986, unsup_loss_bbox: nan, loss: nan
"2021-10-21T10:47:58+08:00" 2021-10-21 10:47:58,223 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:58+08:00" 2021-10-21 10:47:58,992 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:47:59+08:00" 2021-10-21 10:47:59,758 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:00+08:00" 2021-10-21 10:48:00,536 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:01+08:00" 2021-10-21 10:48:01,357 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:02+08:00" 2021-10-21 10:48:02,134 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:02+08:00" 2021-10-21 10:48:02,928 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:03+08:00" 2021-10-21 10:48:03,734 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:04+08:00" 2021-10-21 10:48:04,652 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:05+08:00" 2021-10-21 10:48:05,415 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:06+08:00" 2021-10-21 10:48:06,254 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:07+08:00" 2021-10-21 10:48:07,028 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:07+08:00" 2021-10-21 10:48:07,716 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:08+08:00" 2021-10-21 10:48:08,671 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:09+08:00" 2021-10-21 10:48:09,465 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:10+08:00" 2021-10-21 10:48:10,259 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:11+08:00" 2021-10-21 10:48:11,019 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:11+08:00" 2021-10-21 10:48:11,635 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:12+08:00" 2021-10-21 10:48:12,388 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:13+08:00" 2021-10-21 10:48:13,123 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:13+08:00" 2021-10-21 10:48:13,890 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:14+08:00" 2021-10-21 10:48:14,849 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:15+08:00" 2021-10-21 10:48:15,680 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:16+08:00" 2021-10-21 10:48:16,551 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:17+08:00" 2021-10-21 10:48:17,450 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:18+08:00" 2021-10-21 10:48:18,338 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:19+08:00" 2021-10-21 10:48:19,133 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:19+08:00" 2021-10-21 10:48:19,934 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:20+08:00" 2021-10-21 10:48:20,688 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:21+08:00" 2021-10-21 10:48:21,482 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:22+08:00" 2021-10-21 10:48:22,269 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:23+08:00" 2021-10-21 10:48:23,047 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:23+08:00" 2021-10-21 10:48:23,993 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:24+08:00" 2021-10-21 10:48:24,719 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:25+08:00" 2021-10-21 10:48:25,412 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:26+08:00" 2021-10-21 10:48:26,192 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:27+08:00" 2021-10-21 10:48:27,001 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:27+08:00" 2021-10-21 10:48:27,781 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:28+08:00" 2021-10-21 10:48:28,682 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:29+08:00" 2021-10-21 10:48:29,655 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:30+08:00" 2021-10-21 10:48:30,543 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:31+08:00" 2021-10-21 10:48:31,369 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:32+08:00" 2021-10-21 10:48:32,217 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:33+08:00" 2021-10-21 10:48:33,070 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:33+08:00" 2021-10-21 10:48:33,879 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:34+08:00" 2021-10-21 10:48:34,625 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:35+08:00" 2021-10-21 10:48:35,497 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:36+08:00" 2021-10-21 10:48:36,356 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:37+08:00" 2021-10-21 10:48:37,067 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:37+08:00" 2021-10-21 10:48:37,818 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
"2021-10-21T10:48:37+08:00" 2021-10-21 10:48:37,819 - mmdet.ssod - INFO - Iter [100/720000] lr: 1.988e-03, eta: 7 days, 9:48:01, time: 0.805, data_time: 0.027, memory: 9884, ema_momentum: 0.9900, sup_loss_rpn_cls: nan, sup_loss_rpn_bbox: nan, sup_loss_cls: nan, sup_acc: 65.5926, sup_loss_bbox: nan, unsup_loss_rpn_cls: nan, unsup_loss_rpn_bbox: nan, unsup_loss_cls: nan, unsup_acc: 76.7965, unsup_loss_bbox: 0.0000, loss: nan
"2021-10-21T10:48:38+08:00" 2021-10-21 10:48:38,686 - mmdet.ssod - WARNING - Check overflow, downscale loss scale to 1
.
.
.
21:39+08:00" Traceback (most recent call last):
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/tools/train.py", line 198, in <module>
"2021-10-21T11:21:39+08:00"     main()
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/tools/train.py", line 193, in main
"2021-10-21T11:21:39+08:00"     meta=meta,
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/ssod/apis/train.py", line 206, in train_detector
"2021-10-21T11:21:39+08:00"     runner.run(data_loaders, cfg.workflow)
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/thirdparty/mmcv-1.3.9/mmcv/runner/iter_based_runner.py", line 133, in run
"2021-10-21T11:21:39+08:00"     iter_runner(iter_loaders[i], **kwargs)
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/thirdparty/mmcv-1.3.9/mmcv/runner/iter_based_runner.py", line 60, in train
"2021-10-21T11:21:39+08:00"     outputs = self.model.train_step(data_batch, self.optimizer, **kwargs)
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/thirdparty/mmcv-1.3.9/mmcv/parallel/distributed.py", line 53, in train_step
"2021-10-21T11:21:39+08:00"     output = self.module.train_step(*inputs[0], **kwargs[0])
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/thirdparty/mmdetection/mmdet/models/detectors/base.py", line 238, in train_step
"2021-10-21T11:21:39+08:00"     losses = self(**data)
"2021-10-21T11:21:39+08:00"   File "/usr/local/miniconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 550, in __call__
"2021-10-21T11:21:39+08:00"     result = self.forward(*input, **kwargs)
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/thirdparty/mmcv-1.3.9/mmcv/runner/fp16_utils.py", line 130, in new_func
"2021-10-21T11:21:39+08:00"     output = old_func(*new_args, **new_kwargs)
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/thirdparty/mmdetection/mmdet/models/detectors/base.py", line 172, in forward
"2021-10-21T11:21:39+08:00"     return self.forward_train(img, img_metas, **kwargs)
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/ssod/models/soft_teacher.py", line 50, in forward_train
"2021-10-21T11:21:39+08:00"     data_groups["unsup_teacher"], data_groups["unsup_student"]
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/ssod/models/soft_teacher.py", line 77, in foward_unsup_train
"2021-10-21T11:21:39+08:00"     return self.compute_pseudo_label_loss(student_info, teacher_info)
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/ssod/models/soft_teacher.py", line 120, in compute_pseudo_label_loss
"2021-10-21T11:21:39+08:00"     student_info=student_info,
"2021-10-21T11:21:39+08:00"   File "/data1/train_code/SoftTeacher/ssod/models/soft_teacher.py", line 243, in unsup_rcnn_cls_loss
"2021-10-21T11:21:39+08:00"     loss["loss_cls"] = loss["loss_cls"].sum() / max(bbox_targets[1].sum(), 1.0)
"2021-10-21T11:21:39+08:00" KeyError: 'loss_cls'
"2021-10-21T11:21:47+08:00" Traceback (most recent call last):
"2021-10-21T11:21:47+08:00"   File "/usr/local/miniconda3/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"2021-10-21T11:21:47+08:00"     "__main__", mod_spec)
"2021-10-21T11:21:47+08:00"   File "/usr/local/miniconda3/lib/python3.6/runpy.py", line 85, in _run_code
"2021-10-21T11:21:47+08:00"     exec(code, run_globals)
"2021-10-21T11:21:47+08:00"   File "/usr/local/miniconda3/lib/python3.6/site-packages/torch/distributed/launch.py", line 263, in <module>
"2021-10-21T11:21:47+08:00"     main()
"2021-10-21T11:21:47+08:00"   File "/usr/local/miniconda3/lib/python3.6/site-packages/torch/distributed/launch.py", line 259, in main
"2021-10-21T11:21:47+08:00"     cmd=cmd)
"2021-10-21T11:21:47+08:00" subprocess.CalledProcessError: Command '['/usr/bin/python', '-u', '/data1/train_code/SoftTeacher/tools/train.py', '--local_rank=0', '/data1/train_code/SoftTeacher/configs/exp-test/soft_teacher_faster_rcnn_r50_caffe_fpn_adas_full_720k.py', '--launcher', 'pytorch']' returned non-zero exit status 1.
"2021-10-21T11:21:47+08:00" [INFO] recv error: exit status 1
"2021-10-21T11:21:47+08:00" [ERROR] error happends during process: exit status 1
"2021-10-21T11:21:48+08:00" [INFO] still reserved
"2021-10-21T11:21:48+08:00" [INFO] recv flag (false)
"2021-10-21T11:21:48+08:00" [INFO] sleeping
"2021-10-21T11:22:03+08:00" [ERROR] kill process failed with error: timed out waiting for the condition

[MendelXu]

I think the config is ok. And as you are facing the NaN issue, there are several things you can try:

• Add fp16=None to the end of the config file. This is to switch the training precision to fp32 and see whether it is an fp16 issue;
• Downscale the learning rate to see whether it is caused by the too large learning rate.

[JayYangSS]

thank you, I add both of your suggestions and the loss seems to be normal. I wonder all your models are trained with fp16 enabled?

[MendelXu]

Yes. By default, we use fp16 for all models. I would prefer you to use fp16 by default too as it will save a lot of memory and time while with few performance drop.