Yufei Xu

Hi, we modify the FPN file with an extra option `use_residual=False` to disable the residual connection in the FPN module, which only serves for feature dimension change, as described in...

Hi, It seems that you have modified the backbone structures with convolution and batch normalization in the FFN part.

According to the error information, it should be fine by adding contiguous in Line 103 in single_level_roi_extractor.py, e.g., ```python roi_feats_t = self.roi_layers[i](feats[i].contiguous(), rois_) ``` However, since there have been some...

Thanks for your instruction. The code is checked now. How can I upload the pre-trained weights and logs for the ViTPose variants? Can I provide the links using OneDrive or...

Thanks a lot for your help! The files and configs have been updated now. The pre-trained models and logs are available at [Onedrive](https://1drv.ms/u/s!AimBgYV7JjTlgccv_ney00z-K9TAGQ?e=fQIIAB). The uncovered codes by the unit test...

We also fixed some bugs caused by the updated NumPy version in the dataset files. Please check the recent commits. By the way, it seems that the current failed build...

Hi @ly015, would you mind restarting the failed checks? I just checked the logs, and it seems that the pip installation caused the error. Thanks a lot.

It seems that the current failure information is related to the docker version... Should I open a new PR for the dev-1.x branch and close this PR instead? Thanks a...

Hi @ly015, it seems that the current failure case is in loading the video in ```test_inference.py```, where no frames are detected after the [command](https://github.com/open-mmlab/mmpose/actions/runs/4122842964/jobs/7120120416#step:12:352). To this end, is there anything...

Hi, is there anything we can do to help fix the CI problem? Besides, could we open a new PR based on the dev-1.x branch to merge the ViTPose variants...