Yifan Lareina WU

[Feature] Support ViTPose

1

## Motivation Add implementation of ViTPose on MMPose 1.0 ## Modification - Add six config files - Add layer decay optimizer - In `HeatmapHead`, add parameter `upsample`, default to zero...

Vit-huge patch size mismatch with mae

1

Hi, I noticed that in [mae repo](https://github.com/facebookresearch/mae/blob/efb2a8062c206524e35e47d04501ed4f544c0ae8/models_mae.py#L239), the patch size for the huge model is 14, but in your config, the patch size is 16. This causes warnings during pretrained...

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

error on distances.cpp

1

When I tried to make the project, the terminal says "error: type 'igl::opengl::ViewerCore' does not provide a call operator v.core().background_color.setConstant(0.8);"