Yining Li

Sorry for the late reply. You may need to set `use_gt_bbox=True` in `data_cfg`.

Thank you very much for your help! For now, there are lint issues in the code. Could you please install pre-commit hooks (see our [docs](https://github.com/open-mmlab/mmpose/blob/master/.github/CONTRIBUTING.md)) and run ``pre-commit run --all-files``...

The unit test of ViTPose seems failed. For quick debugging, you can run unit tests locally by ``$pytest tests/``.

We will help check and fix the CI problem.

Yes, you can use timm for the backbone implementation. There is a tutorial in MMDetection on how to use timm backbones in MMDetection through an MMClassification wrapper, which should also...

@Tau-J Could you please add unit tests for multi-source sampler?

@Tau-J A few follow-ups: - Please double-check the FLOPs of all rtmpose models with the updated script. - There are mixed uses of 'rtmpose-tiny' and 'rtmpose-s/m/l' in the config names....

The error information indicates that the `cat` here is a string, which should be a dict. Could you please verify that your annotation files follow the standard COCO format? Or...

Hi, the reason seems to be that in your annotation file the 'categories' field is a dict, which should be a list of dict in COCO format. You can refer...

The script `tools/test.py` is for quantitatively evaluating the trained model in metrics like 'AP'. It's output `result_keypoints.json` are not for visualization. `demo/top_down_image_demo.py` can be used to visualize the inference results...