I would like to ask, yolo only can detect target in a single frame .when defining clip i(p,c,n),by expanding the bounding box by about 25%, the same target between frames at different intervals is cropped. How do you determine the different positions of the same target in different frames? How to cut it?

大佬您好，我想运行试一下效果，运行 video.py 的时候报了这个错误，不知道要怎么解决，谢谢啦

cannot import name 'deform_conv_cuda' from partially initialized module 'thirdparty.deform_conv' (most likely due to a circular import)

报错位置： File "xxx / DCPose/thirdparty/deform_conv/functions/deform_conv.py", line 5, in from .. import deform_conv_cuda

cd demo/                   
mkdir input/
# Put your video in the input directory
python video.py

Your method above didnt work.Maybe because the pretrained model (pretrained_coco_model)is not suitable? thanks a lot !

I tried to run on the windows system, but the problem of VC toolkit parsing was always prompted, and the bug still appeared after referring to the solution.How can i solve？？ build\lib.win-amd64-3.6\deform_conv_cuda.cp36-win_amd64.pyd : fatal error LNK1120: 8 个无法解析的外部命令 error: command 'C:\Program Files (x86)\Microsoft Visual Studio\2019\BuildTools\VC\Tools\MSVC\14.29.30037\bin\HostX86\x64\link.exe' failed with exit status 1120

Thanks for your excellent work!

I run the code successfully and I can use your pretrained model to get a result of 82.8 for PoseTrack17 validation dataset, but if I use the provided code and config files to train a new model and the result is only 81.6.

So I want to know that is there any other settings about the training or the config files about the training are not the updated version?

Thank you for your work!

I noticed the result of your model posted on the leaderboard of PoseTrack17 is with additional COCO data.

Could you give more details of using additional data?

Thanks!

Thank you for your good research. And thank you for revealing the code quickly. I tried to implement your code in the same environment. However, using a single GPU environment, the batch have become 1/2 size. And I got the following results. edit config line 4 : GPUS: (1,) (in my environment using 0:3080, 1:2080TI)

Posetrack 2017 val

| Model | Head | Shoulder | Elbow | Wrist | Hip | Knee | Ankle | Mean | |:-----------|:--------|:-----------|:--------|:--------|:--------|:--------|:--------|:--------| | DcPose_RSN | 86.3907 | 87.718 | 83.2292 | 76.2394 | 80.1681 | 79.1894 | 71.2038 | 80.9779 |

Posetrack 2018 val

| Model | Head | Shoulder | Elbow | Wrist | Hip | Knee | Ankle | Mean | |:-----------|:--------|:-----------|:--------|:--------|:--------|:--------|:--------|:--------| | DcPose_RSN | 83.8176 | 86.2703 | 81.4414 | 75.3437 | 77.1077 | 77.9727 | 72.2061 | 79.4758 |

The result of not achieving the performance suggested is because the batch size is small?

I would like to change the deform conv module to torchvision to run your code on CUDA11.1. https://pytorch.org/vision/stable/_modules/torchvision/ops/deform_conv.html#deform_conv2d

I also encountered an error in the posetrack 2017 test dataset.

2021-04-02 14:23:13 [engine.core.function] INFO: test: [3100/5462]      Time 1.659 (1.713)      Data 0.027s (0.083s)    Accuracy 0.000 (0.006)
2021-04-02 14:25:59 [engine.core.function] INFO: test: [3200/5462]      Time 1.659 (1.712)      Data 0.027s (0.081s)    Accuracy 0.000 (0.006)
Traceback (most recent call last):
  File "run.py", line 33, in <module>
    main()
  File "run.py", line 29, in main
    runner.launch()
  File "/DCPose/engine/defaults/runner.py", line 63, in launch
    evaluator.exec()
  File "/DCPose/engine/defaults/evaluator.py", line 20, in exec
    self.eval()
  File "/DCPose/engine/defaults/evaluator.py", line 73, in eval
    phase=self.phase)
  File "/DCPose/engine/core/function.py", line 165, in eval
    input_x, input_sup_A, input_sup_B, target_heatmaps, target_heatmaps_weight, meta = next(self.dataloader_iter)
  File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 345, in __next__
    data = self._next_data()
  File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 856, in _next_data
    return self._process_data(data)
  File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 881, in _process_data
    data.reraise()
  File "/opt/conda/lib/python3.7/site-packages/torch/_utils.py", line 394, in reraise
    raise self.exc_type(msg)
AttributeError: Caught AttributeError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
    data = fetcher.fetch(index)
  File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/DCPose/datasets/zoo/posetrack/PoseTrack.py", line 100, in __getitem__
    return self._get_spatiotemporal_window(data_item)
  File "/DCPose/datasets/zoo/posetrack/PoseTrack.py", line 166, in _get_spatiotemporal_window
    self.logger.error(error_msg)
AttributeError: 'PoseTrack' object has no attribute 'logger'

`ninja: build stopped: subcommand failed. Traceback (most recent call last): File "/opt/conda/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1673, in _run_ninja_build env=env) File "/opt/conda/lib/python3.6/subprocess.py", line 438, in run output=stdout, stderr=stderr) subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "setup.py", line 42, in zip_safe=False) File "/opt/conda/lib/python3.6/site-packages/setuptools/init.py", line 153, in setup return distutils.core.setup(**attrs) File "/opt/conda/lib/python3.6/distutils/core.py", line 148, in setup dist.run_commands() File "/opt/conda/lib/python3.6/distutils/dist.py", line 955, in run_commands self.run_command(cmd) File "/opt/conda/lib/python3.6/distutils/dist.py", line 974, in run_command cmd_obj.run() File "/opt/conda/lib/python3.6/site-packages/setuptools/command/develop.py", line 34, in run self.install_for_development() File "/opt/conda/lib/python3.6/site-packages/setuptools/command/develop.py", line 136, in install_for_development self.run_command('build_ext') File "/opt/conda/lib/python3.6/distutils/cmd.py", line 313, in run_command self.distribution.run_command(command) File "/opt/conda/lib/python3.6/distutils/dist.py", line 974, in run_command cmd_obj.run() File "/opt/conda/lib/python3.6/site-packages/setuptools/command/build_ext.py", line 79, in run _build_ext.run(self) File "/opt/conda/lib/python3.6/site-packages/Cython/Distutils/old_build_ext.py", line 186, in run _build_ext.build_ext.run(self) File "/opt/conda/lib/python3.6/distutils/command/build_ext.py", line 339, in run self.build_extensions() File "/opt/conda/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 708, in build_extensions build_ext.build_extensions(self) File "/opt/conda/lib/python3.6/site-packages/Cython/Distutils/old_build_ext.py", line 195, in build_extensions _build_ext.build_ext.build_extensions(self) File "/opt/conda/lib/python3.6/distutils/command/build_ext.py", line 448, in build_extensions self._build_extensions_serial() File "/opt/conda/lib/python3.6/distutils/command/build_ext.py", line 473, in _build_extensions_serial self.build_extension(ext) File "/opt/conda/lib/python3.6/site-packages/setuptools/command/build_ext.py", line 196, in build_extension _build_ext.build_extension(self, ext) File "/opt/conda/lib/python3.6/distutils/command/build_ext.py", line 533, in build_extension depends=ext.depends) File "/opt/conda/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 538, in unix_wrap_ninja_compile with_cuda=with_cuda) File "/opt/conda/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1359, in _write_ninja_file_and_compile_objects error_prefix='Error compiling objects for extension') File "/opt/conda/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 1683, in _run_ninja_build raise RuntimeError(message) from e RuntimeError: Error compiling objects for extension `

src/deform_conv_cuda.cpp:559:3: error: ‘AT_CHECK’ was not declared in this scope; did you mean ‘DCHECK’?

  559 |   AT_CHECK(input.is_contiguous(), "input tensor has to be contiguous");
      |   ^~~~~~~~
      |   DCHECK

error: command '/usr/bin/gcc' failed with exit code 1

Hi，I saw you said "train our model for a batch size of 32 for 20 epochs with 2 Nvidia GeForce Titan X GPUs" in the paper. Can I know the sepcific training time you will cost in this situation? Thanks

Thank you very much for your work. I am in China now and I cannot download the posetrack2017 and posetrack2018 dataset. Could you please share it with me? Or can I train directly with the COCO dataset? What should I do?（Do I need to change the format in COCO？） Looking forward to your reply ！ Thanks！！

Hello,The Posetrack official website is down and I'm unable to access the dataset. I could see that many have faced the same issue.It would be great if you could resolve the website issue or send us the data personally.Thank you so much for your time.

Why not let the model directly output 15 joints corresponding to Posetrack dataset, but output 17 joints corresponding to COCO dataset, and then convert to posetrack?

I ran training new model on posetrack17 and test it on validation dataset for three times. I only got 80.9mAP for three times where there are large gap. 2 * 2080 and other config is not changed. I used 0, 1000, 8000 random seed for different initialization. So where's the problem.

The below error occurs:

022-04-23 06:32:46 [posetimation.zoo.DcPose.dcpose_rsn] ERROR: => please download pre-trained models first! Traceback (most recent call last): File "run.py", line 33, in main() File "run.py", line 29, in main runner.launch() File "/home/awanish/DCPose-main/engine/defaults/runner.py", line 52, in launch trainer = DefaultTrainer(self.cfg, self.output_path_dict, PE_Name=self.args.PE_Name) File "/home/awanish/DCPose-main/engine/defaults/trainer.py", line 32, in init self.model = build_model(cfg, phase='train') File "/home/awanish/DCPose-main/posetimation/zoo/build.py", line 17, in build_model model_instance.init_weights() File "/home/awanish/DCPose-main/posetimation/zoo/DcPose/dcpose_rsn.py", line 285, in init_weights raise ValueError('{} is not exist!'.format(self.pretrained)) ValueError: /home/awanish/DCPose-main/DcPose_supp_files/pretrained_models/pretrained_.pth is not exist!

there is no file with the name pretrained_.pth given in supp files folder