Code for CVPR 2021 paper: Anchor-Free Person Search

(open-mmlab) goo@goo-Z390-GAMING-X:~/yx/AlignPS$ sh run_test.sh loading annotations into memory... Done (t=0.12s) creating index... index created! /home/goo/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/mmcv/cnn/bricks/conv_module.py:100: UserWarning: ConvModule has norm and bias at the same time warnings.warn('ConvModule has norm and bias at the same time') [ ] 0/6978, elapsed: 0s, ETA:/home/goo/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/functional.py:3328: UserWarning: nn.functional.upsample is deprecated. Use nn.functional.interpolate instead. warnings.warn("nn.functional.upsample is deprecated. Use nn.functional.interpolate instead.") /home/goo/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/functional.py:3458: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. "See the documentation of nn.Upsample for details.".format(mode) Traceback (most recent call last): File "./tools/test.py", line 226, in main() File "./tools/test.py", line 187, in main args.gpu_collect) File "/home/goo/yx/AlignPS/mmdet/apis/test.py", line 98, in multi_gpu_test result = model(return_loss=False, rescale=True, **data) File "/home/goo/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/home/goo/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 705, in forward output = self.module(*inputs[0], **kwargs[0]) File "/home/goo/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/home/goo/yx/AlignPS/mmdet/core/fp16/decorators.py", line 51, in new_func return old_func(*args, **kwargs) File "/home/goo/yx/AlignPS/mmdet/models/detectors/base.py", line 170, in forward return self.forward_test(img, img_metas, **kwargs) File "/home/goo/yx/AlignPS/mmdet/models/detectors/base.py", line 147, in forward_test return self.simple_test(imgs[0], img_metas[0], **kwargs) File "/home/goo/yx/AlignPS/mmdet/models/detectors/single_stage_reid.py", line 118, in simple_test *outs, img_metas, rescale=rescale) File "/home/goo/yx/AlignPS/mmdet/core/fp16/decorators.py", line 131, in new_func return old_func(*args, **kwargs) File "/home/goo/yx/AlignPS/mmdet/models/dense_heads/fcos_reid_head_focal_sub_triqueue.py", line 454, in get_bboxes img_shape = img_metas[img_id]['img_shape'] TypeError: 'DataContainer' object is not subscriptable Killing subprocess 6428 Traceback (most recent call last): File "/home/goo/anaconda3/envs/open-mmlab/lib/python3.7/runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "/home/goo/anaconda3/envs/open-mmlab/lib/python3.7/runpy.py", line 85, in _run_code exec(code, run_globals) File "/home/goo/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/distributed/launch.py", line 340, in main() File "/home/goo/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/distributed/launch.py", line 326, in main sigkill_handler(signal.SIGTERM, None) # not coming back File "/home/goo/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/distributed/launch.py", line 301, in sigkill_handler raise subprocess.CalledProcessError(returncode=last_return_code, cmd=cmd) subprocess.CalledProcessError: Command '['/home/goo/anaconda3/envs/open-mmlab/bin/python', '-u', './tools/test.py', '--local_rank=0', './configs/fcos/fcos_center-normbbox-centeronreg-giou_r50_caffe_fpn_gn-head_dcn_4x4_1x_cuhk_reid_1500_stage1_fpncat_dcn_epoch24_multiscale_focal_x4_bg-2_lconv3dcn_sub_triqueue_dcn0.py', 'work_dirs/fcos_center-normbbox-centeronreg-giou_r50_caffe_fpn_gn-head_dcn_4x4_1x_cuhk_reid_1500_stage1_fpncat_dcn_epoch24_multiscale_focal_x4_bg-2_lconv3dcn_sub_triqueue_dcn0/epoch_24.pth', '--launcher', 'pytorch', '--out', 'work_dirs/fcos_center-normbbox-centeronreg-giou_r50_caffe_fpn_gn-head_dcn_4x4_1x_cuhk_reid_1500_stage1_fpncat_dcn_epoch24_multiscale_focal_x4_bg-2_lconv3dcn_sub_triqueue_dcn0/results_1000.pkl']' returned non-zero exit status 1.

Traceback (most recent call last): File "./tools/test_results.py", line 75, in with open(os.path.join(results_path, 'results_1000.pkl'), 'rb') as fid: FileNotFoundError: [Errno 2] No such file or directory: '/home/goo/yx/AlignPS/work_dirs/fcos_center-normbbox-centeronreg-giou_r50_caffe_fpn_gn-head_dcn_4x4_1x_cuhk_reid_1500_stage1_fpncat_dcn_epoch24_multiscale_focal_x4_bg-2_lconv3dcn_sub_triqueue_dcn0/results_1000.pkl' fcos_center-normbbox-centeronreg-giou_r50_caffe_fpn_gn-head_dcn_4x4_1x_cuhk_reid_1500_stage1_fpncat_dcn_epoch24_multiscale_focal_x4_bg-2_lconv3dcn_sub_triqueue_dcn0 I don't know why .Maybe you can help me .Thank you !

when i run 'bash run_test.sh', I can get results_1000.pkl successfully. However, there is a FileNotFoundError after that. There are not data, of which the structrue is like '.mat' in CUHK-SYSU. I will appreciate it if you can help.

Traceback (most recent call last): File "***/yes/lib/python3.7/site-packages/scipy/io/matlab/mio.py", line 33, in _open_file return open(file_like, 'rb'), True FileNotFoundError: [Errno 2] No such file or directory: '***/data/CUHK-SYSU/annotation/test/train_test/TestG100.mat'

Hello, I want to reimplement the experiment, however, when I started training AlignPS (on CUHK), I encountered the following problems. No errors were reported, but the network is not training. '''''''' 2021-04-11 00:00:02,350 - mmdet - INFO - load model from: open-mmlab://detectron2/resnet50_caffe 2021-04-11 00:00:02,719 - mmdet - WARNING - The model and loaded state dict do not match exactly

unexpected key in source state_dict: conv1.bias

2021-04-11 00:00:08,895 - mmdet - INFO - Start running, host: xxxxx, work_dir: /home/xxxxx/AlignPS/work_dirs/fcos_center-normbbox-centeronreg-giou_r50_caffe_fpn_gn-head_dcn_4x4_1x_cuhk_reid_1500_stage1_fpncat_dcn_epoch24_multiscale_focal_x4_bg-2_lconv3dcn_sub_triqueue_dcn0 2021-04-11 00:00:08,908 - mmdet - INFO - workflow: [('train', 1)], max: 24 epochs '''''''''

I completely followed the steps in install.md to configure the environment, and my conda list is as follows(python3.6.13 + pytorch1.4.0 + mmdet2.4.0 + mmcv-full1.1.5): _libgcc_mutex 0.1 main https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main addict 2.4.0 pypi_0 pypi blas 1.0 mkl https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main ca-certificates 2021.1.19 h06a4308_1 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main certifi 2020.12.5 py36h06a4308_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main cudatoolkit 10.1.243 h6bb024c_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main cycler 0.10.0 pypi_0 pypi cython 0.29.22 pypi_0 pypi freetype 2.10.4 h5ab3b9f_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main intel-openmp 2020.2 254 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main jpeg 9b h024ee3a_2 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main kiwisolver 1.3.1 pypi_0 pypi lcms2 2.12 h3be6417_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main ld_impl_linux-64 2.33.1 h53a641e_7 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main libffi 3.3 he6710b0_2 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main libgcc-ng 9.1.0 hdf63c60_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main libgfortran-ng 7.3.0 hdf63c60_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main libpng 1.6.37 hbc83047_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main libstdcxx-ng 9.1.0 hdf63c60_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main libtiff 4.1.0 h2733197_1 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main lz4-c 1.9.3 h2531618_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main matplotlib 3.3.4 pypi_0 pypi mkl 2020.2 256 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main mkl-service 2.3.0 py36he8ac12f_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main mkl_fft 1.3.0 py36h54f3939_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main mkl_random 1.1.1 py36h0573a6f_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main mmcv-full 1.1.5 pypi_0 pypi mmdet 2.4.0 dev_0 mmpycocotools 12.0.3 pypi_0 pypi ncurses 6.2 he6710b0_1 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main ninja 1.10.2 py36hff7bd54_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main numpy 1.19.2 py36h54aff64_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main numpy-base 1.19.2 py36hfa32c7d_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main olefile 0.46 py36_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main opencv-python 4.5.1.48 pypi_0 pypi openssl 1.1.1k h27cfd23_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main pillow 8.2.0 py36he98fc37_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main pip 21.0.1 py36h06a4308_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main pyparsing 2.4.7 pypi_0 pypi python 3.6.13 hdb3f193_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main python-dateutil 2.8.1 pypi_0 pypi pytorch 1.4.0 py3.6_cuda10.1.243_cudnn7.6.3_0 pytorch pyyaml 5.4.1 pypi_0 pypi readline 8.1 h27cfd23_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main scipy 1.5.2 py36h0b6359f_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main setuptools 52.0.0 py36h06a4308_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main six 1.15.0 py36h06a4308_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main sqlite 3.35.4 hdfb4753_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main terminaltables 3.1.0 pypi_0 pypi tk 8.6.10 hbc83047_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main torchvision 0.5.0 py36_cu101 pytorch wheel 0.36.2 pyhd3eb1b0_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main xz 5.2.5 h7b6447c_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main yapf 0.31.0 pypi_0 pypi zlib 1.2.11 h7b6447c_3 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main zstd 1.4.9 haebb681_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main

I checked ISSUES in open-mmlab/mmdetection, someone said: "This is not an error. It is normal when using the resnet pre-trained model as the conv1.bais has been absorbed in the conv1.weight." But my network cannot continue training. Could you give me some guidance? Thank you!

Environment sys.platform: linux Python: 3.6.13 |Anaconda, Inc.| (default, Feb 23 2021, 21:15:04) [GCC 7.3.0] CUDA available: True CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 10.1, V10.1.243 GPU 0,1,2,3: Tesla P100-PCIE-16GB GCC: gcc (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609 PyTorch: 1.4.0 PyTorch compiling details: PyTorch built with:

• GCC 7.3
• Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
• Intel(R) MKL-DNN v0.21.1 (Git Hash 7d2fd500bc78936d1d648ca713b901012f470dbc)
• OpenMP 201511 (a.k.a. OpenMP 4.5)
• NNPACK is enabled
• CUDA Runtime 10.1
• 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
• CuDNN 7.6.3
• Magma 2.5.1
• Build settings: BLAS=MKL, BUILD_NAMEDTENSOR=OFF, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -fopenmp -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -O2 -fPIC -Wno-narrowing -Wall -Wextra -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 -Wno-stringop-overflow, DISABLE_NUMA=1, 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,

TorchVision: 0.5.0 OpenCV: 4.5.1 MMCV: 1.1.5 MMDetection: 2.4.0+c20cf32 MMDetection Compiler: GCC 7.3 MMDetection CUDA Compiler: 10.1

Hello, I'm very new in this field. And I want run and show the results by the images of the videos. MMDetect provides some demos like image_demo.py or webcam_demo.py. Do you have any scripts or code like this, or how can I get this?

Thank you for your helps.

(open-mmlab) lxz@lxz-System-Product-Name:~/KunPeng_Liu/AlignPS$ /bin/bash /home/lxz/KunPeng_Liu/AlignPS/run_train.sh fatal: not a git repository (or any of the parent directories): .git 2021-09-13 17:36:13,497 - mmdet - INFO - Environment info:

sys.platform: linux Python: 3.7.10 | packaged by conda-forge | (default, Feb 19 2021, 16:07:37) [GCC 9.3.0] CUDA available: True CUDA_HOME: /usr/local/cuda-11.0 NVCC: Build cuda_11.0_bu.TC445_37.28845127_0 GPU 0: NVIDIA GeForce RTX 3090 GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 PyTorch: 1.7.0 PyTorch compiling details: PyTorch built with:

• GCC 7.3
• C++ Version: 201402
• Intel(R) oneAPI Math Kernel Library Version 2021.3-Product Build 20210617 for Intel(R) 64 architecture applications
• Intel(R) MKL-DNN v1.6.0 (Git Hash 5ef631a030a6f73131c77892041042805a06064f)
• OpenMP 201511 (a.k.a. OpenMP 4.5)
• NNPACK is enabled
• CPU capability usage: AVX2
• CUDA Runtime 11.0
• NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_37,code=compute_37
• CuDNN 8.0.3
• Magma 2.5.2
• Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, 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,

TorchVision: 0.8.0 OpenCV: 4.5.3 MMCV: 1.3.13 MMDetection: 2.4.0+ MMDetection Compiler: GCC 7.3 MMDetection CUDA Compiler: 11.0

2021-09-13 17:36:14,238 - mmdet - INFO - Distributed training: False 2021-09-13 17:36:14,971 - mmdet - INFO - Config: dataset_type = 'CuhkDataset' data_root = '/home/lxz/KunPeng_Liu/dataset/PRW/PRW-v16.04.20/' img_norm_cfg = dict( mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( type='Resize', img_scale=[(667, 400), (1000, 600), (1333, 800), (1500, 900), (1666, 1000), (2000, 1200)], multiscale_mode='value', keep_ratio=True), dict(type='RandomFlip', flip_ratio=0.5), dict( type='Normalize', mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_ids']) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1500, 900), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Normalize', mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ] data = dict( samples_per_gpu=5, workers_per_gpu=5, train=dict( type='CuhkDataset', ann_file= '/home/lxz/KunPeng_Liu/dataset/PRW/PRW-v16.04.20/train_pid.json', img_prefix='/home/lxz/KunPeng_Liu/dataset/PRW/PRW-v16.04.20/frames/', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( type='Resize', img_scale=[(667, 400), (1000, 600), (1333, 800), (1500, 900), (1666, 1000), (2000, 1200)], multiscale_mode='value', keep_ratio=True), dict(type='RandomFlip', flip_ratio=0.5), dict( type='Normalize', mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict( type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_ids']) ]), val=dict( type='CuhkDataset', ann_file= '/home/lxz/KunPeng_Liu/dataset/PRW/PRW-v16.04.20/test_pid.json', img_prefix='/home/lxz/KunPeng_Liu/dataset/PRW/PRW-v16.04.20/frames/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1500, 900), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Normalize', mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ]), test=dict( type='CuhkDataset', ann_file= '/home/lxz/KunPeng_Liu/dataset/PRW/PRW-v16.04.20/test_pid.json', img_prefix='/home/lxz/KunPeng_Liu/dataset/PRW/PRW-v16.04.20/frames/', proposal_file= '/home/lxz/KunPeng_Liu/dataset/PRW/PRW-v16.04.20/annotation/test/train_test/TestG50.mat', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1500, 900), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict( type='Normalize', mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ])) evaluation = dict(interval=1, metric='bbox') norm_cfg = dict(type='BN', requires_grad=False) model = dict( type='SingleTwoStageDetector176PRW', pretrained='open-mmlab://detectron2/resnet50_caffe', backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(0, 1, 2, 3), frozen_stages=1, norm_cfg=dict(type='BN', requires_grad=False), norm_eval=True, style='caffe'), rpn_head=dict( type='RPNHead', in_channels=1024, feat_channels=1024, anchor_generator=dict( type='AnchorGenerator', scales=[2, 4, 8, 16, 32], ratios=[0.5, 1.0, 2.0], strides=[16]), bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[1.0, 1.0, 1.0, 1.0]), loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=1.0)), roi_head=dict( type='PersonSearchRoIHead2Input1', shared_head=dict( type='ResLayer', depth=50, stage=3, stride=2, dilation=1, style='caffe', norm_cfg=dict(type='BN', requires_grad=False), norm_eval=True), bbox_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict(type='RoIAlign', out_size=14, sample_num=0), out_channels=1024, featmap_strides=[16]), bbox_head=dict( type='PersonSearchNormAwareNewoim2InputBNBBoxHeadPRW', with_avg_pool=True, roi_feat_size=7, in_channels=2048, num_classes=1, bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[0.1, 0.1, 0.2, 0.2]), reg_class_agnostic=False, loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=10.0))), neck=dict( type='FPNDcnLconv3Dcn', in_channels=[256, 512, 1024, 2048], out_channels=256, start_level=1, add_extra_convs=True, extra_convs_on_inputs=False, num_outs=5, relu_before_extra_convs=True), bbox_head=dict( type='FCOSReidHeadFocalSubTriQueue3PRW', num_classes=1, in_channels=256, stacked_convs=4, feat_channels=256, strides=[8, 16, 32, 64, 128], loss_cls=dict( type='FocalLoss', use_sigmoid=True, gamma=2.0, alpha=0.25, loss_weight=1.0), loss_bbox=dict(type='GIoULoss', loss_weight=1.0), loss_centerness=dict( type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0), norm_on_bbox=True, centerness_on_reg=True, dcn_on_last_conv=True, center_sampling=True, conv_bias=True)) train_cfg = dict( rpn=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.7, neg_iou_thr=0.3, min_pos_iou=0.3, match_low_quality=True, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=256, pos_fraction=0.5, neg_pos_ub=-1, add_gt_as_proposals=False), allowed_border=0, pos_weight=-1, debug=False), rpn_proposal=dict( nms_across_levels=False, nms_pre=12000, nms_post=2000, max_num=2000, nms_thr=0.7, min_bbox_size=0), rcnn=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.5, neg_iou_thr=0.1, min_pos_iou=0.5, match_low_quality=False, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=128, pos_fraction=0.5, neg_pos_ub=-1, add_gt_as_proposals=True), pos_weight=-1, debug=False), assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.5, neg_iou_thr=0.4, min_pos_iou=0, ignore_iof_thr=-1), allowed_border=-1, pos_weight=-1, debug=False) test_cfg = dict( rpn=dict( nms_across_levels=False, nms_pre=6000, nms_post=300, max_num=1000, nms_thr=0.7, min_bbox_size=0), rcnn=dict( score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100), nms_pre=1000, min_bbox_size=0, score_thr=0.05, nms=dict(type='nms', iou_threshold=0.5), max_per_img=100) optimizer = dict(type='SGD', lr=0.0015, momentum=0.9, weight_decay=0.0005) optimizer_config = dict(grad_clip=dict(max_norm=10, norm_type=2)) lr_config = dict( policy='step', warmup='linear', warmup_iters=1141, warmup_ratio=0.005, step=[16, 22]) total_epochs = 24 checkpoint_config = dict(interval=1) log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')]) dist_params = dict(backend='nccl') log_level = 'INFO' load_from = None resume_from = None workflow = [('train', 1)] work_dir = './work_dirs/faster_rcnn_r50_caffe_c4_1x_cuhk_single_two_stage17_6_nae1_prw' gpu_ids = [0]

/home/lxz/.local/lib/python3.7/site-packages/mmcv/utils/misc.py:324: UserWarning: "out_size" is deprecated in RoIAlign.__init__, please use "output_size" instead f'"{src_arg_name}" is deprecated in ' /home/lxz/.local/lib/python3.7/site-packages/mmcv/utils/misc.py:324: UserWarning: "sample_num" is deprecated in RoIAlign.__init__, please use "sampling_ratio" instead f'"{src_arg_name}" is deprecated in ' 2021-09-13 17:36:15,307 - mmdet - INFO - load model from: open-mmlab://detectron2/resnet50_caffe 2021-09-13 17:36:15,308 - mmdet - INFO - Use load_from_openmmlab loader 2021-09-13 17:36:15,367 - mmdet - WARNING - The model and loaded state dict do not match exactly

unexpected key in source state_dict: conv1.bias

2021-09-13 17:36:15,432 - mmdet - INFO - Use load_from_openmmlab loader 2021-09-13 17:36:15,477 - mmdet - WARNING - The model and loaded state dict do not match exactly

unexpected key in source state_dict: conv1.weight, conv1.bias, bn1.bias, bn1.weight, bn1.running_mean, bn1.running_var, layer1.0.downsample.0.weight, layer1.0.downsample.1.bias, layer1.0.downsample.1.weight, layer1.0.downsample.1.running_mean, layer1.0.downsample.1.running_var, layer1.0.conv1.weight, layer1.0.bn1.bias, layer1.0.bn1.weight, layer1.0.bn1.running_mean, layer1.0.bn1.running_var, layer1.0.conv2.weight, layer1.0.bn2.bias, layer1.0.bn2.weight, layer1.0.bn2.running_mean, layer1.0.bn2.running_var, layer1.0.conv3.weight, layer1.0.bn3.bias, layer1.0.bn3.weight, layer1.0.bn3.running_mean, layer1.0.bn3.running_var, layer1.1.conv1.weight, layer1.1.bn1.bias, layer1.1.bn1.weight, layer1.1.bn1.running_mean, layer1.1.bn1.running_var, layer1.1.conv2.weight, layer1.1.bn2.bias, layer1.1.bn2.weight, layer1.1.bn2.running_mean, layer1.1.bn2.running_var, layer1.1.conv3.weight, layer1.1.bn3.bias, layer1.1.bn3.weight, layer1.1.bn3.running_mean, layer1.1.bn3.running_var, layer1.2.conv1.weight, layer1.2.bn1.bias, layer1.2.bn1.weight, layer1.2.bn1.running_mean, layer1.2.bn1.running_var, layer1.2.conv2.weight, layer1.2.bn2.bias, layer1.2.bn2.weight, layer1.2.bn2.running_mean, layer1.2.bn2.running_var, layer1.2.conv3.weight, layer1.2.bn3.bias, layer1.2.bn3.weight, layer1.2.bn3.running_mean, layer1.2.bn3.running_var, layer2.0.downsample.0.weight, layer2.0.downsample.1.bias, layer2.0.downsample.1.weight, layer2.0.downsample.1.running_mean, layer2.0.downsample.1.running_var, layer2.0.conv1.weight, layer2.0.bn1.bias, layer2.0.bn1.weight, layer2.0.bn1.running_mean, layer2.0.bn1.running_var, layer2.0.conv2.weight, layer2.0.bn2.bias, layer2.0.bn2.weight, layer2.0.bn2.running_mean, layer2.0.bn2.running_var, layer2.0.conv3.weight, layer2.0.bn3.bias, layer2.0.bn3.weight, layer2.0.bn3.running_mean, layer2.0.bn3.running_var, layer2.1.conv1.weight, layer2.1.bn1.bias, layer2.1.bn1.weight, layer2.1.bn1.running_mean, layer2.1.bn1.running_var, layer2.1.conv2.weight, layer2.1.bn2.bias, layer2.1.bn2.weight, layer2.1.bn2.running_mean, layer2.1.bn2.running_var, layer2.1.conv3.weight, layer2.1.bn3.bias, layer2.1.bn3.weight, layer2.1.bn3.running_mean, layer2.1.bn3.running_var, layer2.2.conv1.weight, layer2.2.bn1.bias, layer2.2.bn1.weight, layer2.2.bn1.running_mean, layer2.2.bn1.running_var, layer2.2.conv2.weight, layer2.2.bn2.bias, layer2.2.bn2.weight, layer2.2.bn2.running_mean, layer2.2.bn2.running_var, layer2.2.conv3.weight, layer2.2.bn3.bias, layer2.2.bn3.weight, layer2.2.bn3.running_mean, layer2.2.bn3.running_var, layer2.3.conv1.weight, layer2.3.bn1.bias, layer2.3.bn1.weight, layer2.3.bn1.running_mean, layer2.3.bn1.running_var, layer2.3.conv2.weight, layer2.3.bn2.bias, layer2.3.bn2.weight, layer2.3.bn2.running_mean, layer2.3.bn2.running_var, layer2.3.conv3.weight, layer2.3.bn3.bias, layer2.3.bn3.weight, layer2.3.bn3.running_mean, layer2.3.bn3.running_var, layer3.0.downsample.0.weight, layer3.0.downsample.1.bias, layer3.0.downsample.1.weight, layer3.0.downsample.1.running_mean, layer3.0.downsample.1.running_var, layer3.0.conv1.weight, layer3.0.bn1.bias, layer3.0.bn1.weight, layer3.0.bn1.running_mean, layer3.0.bn1.running_var, layer3.0.conv2.weight, layer3.0.bn2.bias, layer3.0.bn2.weight, layer3.0.bn2.running_mean, layer3.0.bn2.running_var, layer3.0.conv3.weight, layer3.0.bn3.bias, layer3.0.bn3.weight, layer3.0.bn3.running_mean, layer3.0.bn3.running_var, layer3.1.conv1.weight, layer3.1.bn1.bias, layer3.1.bn1.weight, layer3.1.bn1.running_mean, layer3.1.bn1.running_var, layer3.1.conv2.weight, layer3.1.bn2.bias, layer3.1.bn2.weight, layer3.1.bn2.running_mean, layer3.1.bn2.running_var, layer3.1.conv3.weight, layer3.1.bn3.bias, layer3.1.bn3.weight, layer3.1.bn3.running_mean, layer3.1.bn3.running_var, layer3.2.conv1.weight, layer3.2.bn1.bias, layer3.2.bn1.weight, layer3.2.bn1.running_mean, layer3.2.bn1.running_var, layer3.2.conv2.weight, layer3.2.bn2.bias, layer3.2.bn2.weight, layer3.2.bn2.running_mean, layer3.2.bn2.running_var, layer3.2.conv3.weight, layer3.2.bn3.bias, layer3.2.bn3.weight, layer3.2.bn3.running_mean, layer3.2.bn3.running_var, layer3.3.conv1.weight, layer3.3.bn1.bias, layer3.3.bn1.weight, layer3.3.bn1.running_mean, layer3.3.bn1.running_var, layer3.3.conv2.weight, layer3.3.bn2.bias, layer3.3.bn2.weight, layer3.3.bn2.running_mean, layer3.3.bn2.running_var, layer3.3.conv3.weight, layer3.3.bn3.bias, layer3.3.bn3.weight, layer3.3.bn3.running_mean, layer3.3.bn3.running_var, layer3.4.conv1.weight, layer3.4.bn1.bias, layer3.4.bn1.weight, layer3.4.bn1.running_mean, layer3.4.bn1.running_var, layer3.4.conv2.weight, layer3.4.bn2.bias, layer3.4.bn2.weight, layer3.4.bn2.running_mean, layer3.4.bn2.running_var, layer3.4.conv3.weight, layer3.4.bn3.bias, layer3.4.bn3.weight, layer3.4.bn3.running_mean, layer3.4.bn3.running_var, layer3.5.conv1.weight, layer3.5.bn1.bias, layer3.5.bn1.weight, layer3.5.bn1.running_mean, layer3.5.bn1.running_var, layer3.5.conv2.weight, layer3.5.bn2.bias, layer3.5.bn2.weight, layer3.5.bn2.running_mean, layer3.5.bn2.running_var, layer3.5.conv3.weight, layer3.5.bn3.bias, layer3.5.bn3.weight, layer3.5.bn3.running_mean, layer3.5.bn3.running_var

loading annotations into memory... Done (t=0.03s) creating index... index created! fatal: not a git repository (or any of the parent directories): .git 2021-09-13 17:36:16,813 - mmdet - INFO - Start running, host: lxz@lxz-System-Product-Name, work_dir: /home/lxz/KunPeng_Liu/AlignPS/work_dirs/faster_rcnn_r50_caffe_c4_1x_cuhk_single_two_stage17_6_nae1_prw 2021-09-13 17:36:16,813 - mmdet - INFO - Hooks will be executed in the following order: before_run: (VERY_HIGH ) StepLrUpdaterHook
(NORMAL ) CheckpointHook
(VERY_LOW ) TextLoggerHook

before_train_epoch: (VERY_HIGH ) StepLrUpdaterHook
(LOW ) IterTimerHook
(VERY_LOW ) TextLoggerHook

before_train_iter: (VERY_HIGH ) StepLrUpdaterHook
(LOW ) IterTimerHook

after_train_iter: (ABOVE_NORMAL) OptimizerHook
(NORMAL ) CheckpointHook
(LOW ) IterTimerHook
(VERY_LOW ) TextLoggerHook

after_train_epoch: (NORMAL ) CheckpointHook
(VERY_LOW ) TextLoggerHook

before_val_epoch: (LOW ) IterTimerHook
(VERY_LOW ) TextLoggerHook

before_val_iter: (LOW ) IterTimerHook

after_val_iter: (LOW ) IterTimerHook

after_val_epoch: (VERY_LOW ) TextLoggerHook

2021-09-13 17:36:16,813 - mmdet - INFO - workflow: [('train', 1)], max: 24 epochs /home/lxz/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/functional.py:2952: UserWarning: nn.functional.upsample is deprecated. Use nn.functional.interpolate instead. warnings.warn("nn.functional.upsample is deprecated. Use nn.functional.interpolate instead.") /home/lxz/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/nn/functional.py:3063: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. "See the documentation of nn.Upsample for details.".format(mode)) /home/lxz/KunPeng_Liu/AlignPS/mmdet/models/dense_heads/fcos_reid_head_focal_sub_triqueue3_prw.py:306: UserWarning: This overload of nonzero is deprecated: nonzero() Consider using one of the following signatures instead: nonzero(*, bool as_tuple) (Triggered internally at /opt/conda/conda-bld/pytorch_1603729047590/work/torch/csrc/utils/python_arg_parser.cpp:882.) & (flatten_labels < bg_class_ind)).nonzero().reshape(-1) /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [0,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [1,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [2,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [3,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [4,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [5,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [6,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [7,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [8,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [9,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [10,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [11,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [12,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [13,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [14,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [15,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [16,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [17,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [18,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [19,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [20,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [21,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [22,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [23,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [24,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [25,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [26,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [27,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [28,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [29,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [30,0,0] Assertion t >= 0 && t < n_classes failed. /opt/conda/conda-bld/pytorch_1603729047590/work/aten/src/THCUNN/ClassNLLCriterion.cu:187: cunn_ClassNLLCriterion_updateGradInput_kernel: block: [0,0,0], thread: [31,0,0] Assertion t >= 0 && t < n_classes failed. Traceback (most recent call last): File "tools/train.py", line 177, in main() File "tools/train.py", line 173, in main meta=meta) File "/home/lxz/KunPeng_Liu/AlignPS/mmdet/apis/train.py", line 146, in train_detector runner.run(data_loaders, cfg.workflow, cfg.total_epochs) File "/home/lxz/.local/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 127, in run epoch_runner(data_loaders[i], **kwargs) File "/home/lxz/.local/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 51, in train self.call_hook('after_train_iter') File "/home/lxz/.local/lib/python3.7/site-packages/mmcv/runner/base_runner.py", line 307, in call_hook getattr(hook, fn_name)(self) File "/home/lxz/.local/lib/python3.7/site-packages/mmcv/runner/hooks/optimizer.py", line 35, in after_train_iter runner.outputs['loss'].backward() File "/home/lxz/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/tensor.py", line 221, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "/home/lxz/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/autograd/init.py", line 132, in backward allow_unreachable=True) # allow_unreachable flag File "/home/lxz/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/autograd/function.py", line 89, in apply return self._forward_cls.backward(self, *args) # type: ignore File "/home/lxz/KunPeng_Liu/AlignPS/mmdet/models/roi_heads/bbox_heads/oim_nae_new.py", line 29, in backward if y >= 0: RuntimeError: CUDA error: device-side assert triggered

When i implementation AlignPS, the program can run sucessfully.

Hi, Do you have any guideline to use final similarity score? I want to know, how does it work when there is no query person in just one image? Even if it is an incorrect result, since the person with the highest score is found?

Thank you.

I downloaded the PRW dataset by following your link, then i extracted this file but I can't find any TestG50.mat file in PRW dataset https://github.com/daodaofr/AlignPS/blob/master/configs/fcos/prw_base_focal_labelnorm_sub_ldcn_fg15_wd1-3.py#L74 Can you show me how to get this file?

thx for your great work! I wonder if Class OIMLossNewFocal in oim_tri.py can be used as a loss to replace [oim.py] (https://github.com/DeanChan/NAE4PS/blob/master/lib/loss/oim.py) and how to used it

Hi, thanks for your awesome work.

I noticed that the focal and triplet loss are only used in AlignPS branch, not used in RoI-Align branch. And I don't really understand this setting.

But I have a explanation. The reason is positive samples in AlignPS branch (FCOS center 3x3 area) is much more than them in RoI-Align branch (positive proposals). So in AlignPS branch, for focal loss, features from neighbor location is similar and contain many easy samples. For triplet loss, it is much easier to build triplets with more samples.

Looking forward to your reply. Thanks in advance!

1.我理解的对吗？

1.Am I right to understand that?

假如同一个人，他的大图和小图分别对应不同层次的特征图。不同的层次特征图肯定不完全一样。同一个人不同大小的图片的特征竟然在不同的特征图上不一样，很可能认为为不是一个人。如果query是个小图，是高层次的特征，gallery是大图，使用低层次的特，由于两个特征来自不同尺度的特征图，因此有可能导致特征向量点乘不正常，从而造成误判。所以你只用了一层特征图。

If it is the same person, his large picture and small picture correspond to different levels of feature maps. Different hierarchical feature maps are certainly not exactly the same. The characteristics of different size pictures of the same person are different on different feature maps. Probably think not as a person. If the query is a small graph, which is a high-level feature, and the gallery is a large graph, using a low-level feature, because the two features come from a feature map of different scales, it is possible to cause the feature vector point multiplication is not normal, resulting in misjudgment. So you only use one layer of feature maps.

2.有没有好的方法，来解决因为两个特征来自不同特征图，而导致误判的问题呢，这样就不用删掉其他层次的FPN了，这样的话就能进一步提高了。 很期待你的进一步科研成果。

2.Is there a good way to solve the problem of misjudgment because the two features come from different feature maps, so that there is no need to delete other levels of FPN, so that it can be further improved.

I look forward to your further research results

(open-mmlab) a@b:~/AlignPS$ sh run_test.sh Traceback (most recent call last): File "./tools/test.py", line 13, in from mmdet.apis import multi_gpu_test, single_gpu_test File "/home/a/AlignPS/mmdet/apis/init.py", line 1, in from .inference import (async_inference_detector, inference_detector, File "/home/a/AlignPS/mmdet/apis/inference.py", line 7, in from mmcv.ops import RoIAlign, RoIPool File "/home/a/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/mmcv/ops/init.py", line 3, in from .cc_attention import CrissCrossAttention File "/home/a/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/mmcv/ops/cc_attention.py", line 10, in '_ext', ['ca_forward', 'ca_backward', 'ca_map_forward', 'ca_map_backward']) File "/home/a/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/mmcv/utils/ext_loader.py", line 13, in load_ext assert hasattr(ext, fun), f'{fun} miss in module {name}' AssertionError: ca_forward miss in module _ext Traceback (most recent call last): File "/home/a/anaconda3/envs/open-mmlab/lib/python3.7/runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "/home/a/anaconda3/envs/open-mmlab/lib/python3.7/runpy.py", line 85, in _run_code exec(code, run_globals) File "/home/a/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/distributed/launch.py", line 260, in main() File "/home/a/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/distributed/launch.py", line 256, in main cmd=cmd) subprocess.CalledProcessError: Command '['/home/a/anaconda3/envs/open-mmlab/bin/python', '-u', './tools/test.py', '--local_rank=0', './configs/fcos/fcos_center-normbbox-centeronreg-giou_r50_caffe_fpn_gn-head_dcn_4x4_1x_cuhk_reid_1500_stage1_fpncat_dcn_epoch24_multiscale_focal_x4_bg-2_lconv3dcn_sub_triqueue_dcn0.py', 'work_dirs/fcos_center-normbbox-centeronreg-giou_r50_caffe_fpn_gn-head_dcn_4x4_1x_cuhk_reid_1500_stage1_fpncat_dcn_epoch24_multiscale_focal_x4_bg-2_lconv3dcn_sub_triqueue_dcn0/cuhk_alignps.pth', '--launcher', 'pytorch', '--out', 'work_dirs/fcos_center-normbbox-centeronreg-giou_r50_caffe_fpn_gn-head_dcn_4x4_1x_cuhk_reid_1500_stage1_fpncat_dcn_epoch24_multiscale_focal_x4_bg-2_lconv3dcn_sub_triqueue_dcn0/results_1000.pkl']' returned non-zero exit status 1.

Hi, I found a directory named convert_datasets where I further found a script to convert CUHK dataset to COCO format, so I wonder, whether there is a script to convert another dataset PRW to COCO format ?

Hi: I encountered some problems when running the source code： 2022-02-17 14:43:37,319 - mmdet - INFO - Epoch [1][50/2852] lr: 3.987e-04, eta: 2 days, 6:05:49, time: 1.423, data_time: 0.068, memory: 7011, loss_cls: 0.6662, loss_bbox: 0.9846, loss_centerness: 0.6260, loss_oim: 5.6912, loss: 7.9680, grad_norm: 118.5072 2022-02-17 14:44:35,675 - mmdet - INFO - Epoch [1][100/2852] lr: 4.653e-04, eta: 2 days, 1:12:47, time: 1.167, data_time: 0.016, memory: 7363, loss_cls: 0.5805, loss_bbox: 0.8021, loss_centerness: 0.5967, loss_oim: 5.8589, loss: 7.8382, grad_norm: 104.7832 2022-02-17 14:45:52,820 - mmdet - INFO - Epoch [1][150/2852] lr: 5.320e-04, eta: 2 days, 4:19:57, time: 1.543, data_time: 0.017, memory: 7363, loss_cls: 0.6106, loss_bbox: 0.5222, loss_centerness: 0.5782, loss_oim: 6.3371, loss: 8.0482, grad_norm: 108.9552 2022-02-17 14:47:02,130 - mmdet - INFO - Epoch [1][200/2852] lr: 5.987e-04, eta: 2 days, 4:23:37, time: 1.386, data_time: 0.017, memory: 7363, loss_cls: 0.4726, loss_bbox: 0.5253, loss_centerness: 0.6215, loss_oim: 5.8503, loss: 7.4698, grad_norm: 86.1120 2022-02-17 14:48:04,005 - mmdet - INFO - Epoch [1][250/2852] lr: 6.653e-04, eta: 2 days, 3:17:38, time: 1.237, data_time: 0.015, memory: 7363, loss_cls: 0.4858, loss_bbox: 0.4937, loss_centerness: 0.6017, loss_oim: 6.1532, loss: 7.7343, grad_norm: 94.5427 2022-02-17 14:49:06,965 - mmdet - INFO - Epoch [1][300/2852] lr: 7.320e-04, eta: 2 days, 2:41:31, time: 1.259, data_time: 0.017, memory: 7363, loss_cls: 0.5772, loss_bbox: 0.5174, loss_centerness: 0.5998, loss_oim: 6.5115, loss: 8.2059, grad_norm: 92.6229 2022-02-17 14:50:16,175 - mmdet - INFO - Epoch [1][350/2852] lr: 7.987e-04, eta: 2 days, 2:56:04, time: 1.384, data_time: 0.018, memory: 7363, loss_cls: 0.5621, loss_bbox: 0.5079, loss_centerness: 0.6014, loss_oim: 6.6282, loss: 8.2996, grad_norm: 83.7950 2022-02-17 14:51:23,770 - mmdet - INFO - Epoch [1][400/2852] lr: 8.653e-04, eta: 2 days, 2:57:31, time: 1.352, data_time: 0.019, memory: 7363, loss_cls: 0.6787, loss_bbox: 0.5543, loss_centerness: 0.5968, loss_oim: 6.6915, loss: 8.5213, grad_norm: 136.0015 2022-02-17 14:52:28,603 - mmdet - INFO - Epoch [1][450/2852] lr: 9.320e-04, eta: 2 days, 2:44:25, time: 1.297, data_time: 0.016, memory: 7363, loss_cls: 0.6619, loss_bbox: 0.5619, loss_centerness: 0.6255, loss_oim: 8.8492, loss: 10.6984, grad_norm: 40.6709 2022-02-17 14:53:31,481 - mmdet - INFO - Epoch [1][500/2852] lr: 9.987e-04, eta: 2 days, 2:24:51, time: 1.258, data_time: 0.018, memory: 7363, loss_cls: 0.6701, loss_bbox: 0.5613, loss_centerness: 0.6302, loss_oim: 8.8498, loss: 10.7114, grad_norm: 56.6717 2022-02-17 14:54:34,786 - mmdet - INFO - Epoch [1][550/2852] lr: 1.000e-03, eta: 2 days, 2:10:25, time: 1.266, data_time: 0.015, memory: 7363, loss_cls: nan, loss_bbox: nan, loss_centerness: nan, loss_oim: nan, loss: nan, grad_norm: nan 2022-02-17 14:55:39,327 - mmdet - INFO - Epoch [1][600/2852] lr: 1.000e-03, eta: 2 days, 2:02:53, time: 1.291, data_time: 0.018, memory: 7363, loss_cls: nan, loss_bbox: nan, loss_centerness: nan, loss_oim: nan, loss: nan, grad_norm: nan 2022-02-17 14:56:43,064 - mmdet - INFO - Epoch [1][650/2852] lr: 1.000e-03, eta: 2 days, 1:53:32, time: 1.275, data_time: 0.018, memory: 7363, loss_cls: nan, loss_bbox: nan, loss_centerness: nan, loss_oim: nan, loss: nan, grad_norm: nan 2022-02-17 14:57:46,297 - mmdet - INFO - Epoch [1][700/2852] lr: 1.000e-03, eta: 2 days, 1:43:44, time: 1.265, data_time: 0.017, memory: 7363, loss_cls: nan, loss_bbox: nan, loss_centerness: nan, loss_oim: nan, loss: nan, grad_norm: nan All these values become nan，the command I ran was：python tools/train.py configs/fcos/prw_base_focal_labelnorm_sub_ldcn_fg15_wd1-3.py --gpu-ids 6 --no-validate and I did not change the parameters in the configuration file。 Can you help me？

@erjanmx @daodaofr hi thanks for open sourcing the code base, i have a few queries on running the inference

1. I have downloaded the dataset of Chuk-sys and i have only these folders

2. you have mentioned changing the path of the data in the config file "config file L3, L38, L43, L48" i do not have any annotations available with me so how to generate json file

Please share your thoughts

writing results to work_dirs/fcos_center-normbbox-centeronreg-giou_r50_caffe_fpn_gn-head_dcn_4x4_1x_cuhk_reid_1500_stage1_fpncat_dcn_epoch24_multiscale_focal_x4_bg-2_lconv3dcn_sub_triqueue_dcn0/results_1000.pkl

threshold: 0.2 mAP = 0.00% Top- 1 = 0.00% Top- 5 = 0.00% Top-10 = 0.00% fcos_center-normbbox-centeronreg-giou_r50_caffe_fpn_gn-head_dcn_4x4_1x_cuhk_reid_1500_stage1_fpncat_dcn_epoch24_multiscale_focal_x4_bg-2_lconv3dcn_sub_triqueue_dcn0