pytorch-image-models icon indicating copy to clipboard operation
pytorch-image-models copied to clipboard
verified publisher icon huggingface

Add FocalNet arch, refactor Swin V1/V2 for better feature extraction and HF hub multi-weight support

Open rwightman opened this issue 2 years ago • 1 comments

Since FocalNet and Swin related (and both need refactoring for better feat extraction support), combining

  • Introduction of FocalNet arch
  • Refactor Swin V1/V2, possibly other similar arch that could see improved features_only support
  • Add multi-weight support and push weights to HF hub when done (checkpoints need remap)

rwightman avatar Jan 10 '23 00:01 rwightman

The documentation is not available anymore as the PR was closed or merged.

HuggingFaceDocBuilderDev avatar Jan 10 '23 00:01 HuggingFaceDocBuilderDev