Ma Zerun 2932f9d8a3 [Refactor] Refator ViT (Continue #295) (#395) ... * [Squash] Refator ViT (from #295) * Use base variable to simplify auto_aug setting * Use common PatchEmbed, remove HybridEmbed and refactor ViT init structure. * Add `output_cls_token` option and change the output format of ViT and input format of ViT head. * Update unit tests and add test for `output_cls_token`. * Support out_indices. * Standardize config files * Support resize position embedding. * Add readme file of vit * Rename config file * Improve docs about ViT. * Update docstring * Use local version `MultiheadAttention` instead of mmcv version. * Fix MultiheadAttention * Support `qk_scale` argument in `MultiheadAttention` * Improve docs and change `layer_cfg` to `layer_cfgs` and support sequence. * Use init_cfg to init Linear layer in VisionTransformerHead * update metafile * Update checkpoints and configs * Imporve docstring. * Update README * Revert GAP modification.		2021-10-18 16:07:00 +08:00
..
augment	[Docs] Add Copyright information. (#413)	2021-08-17 19:52:42 +08:00
__init__.py	[Refactor] Refator ViT (Continue #295) (#395)	2021-10-18 16:07:00 +08:00
attention.py	[Refactor] Refator ViT (Continue #295) (#395)	2021-10-18 16:07:00 +08:00
channel_shuffle.py	[Docs] Add Copyright information. (#413)	2021-08-17 19:52:42 +08:00
embed.py	[Docs] Add Copyright information. (#413)	2021-08-17 19:52:42 +08:00
helpers.py	[Docs] Add Copyright information. (#413)	2021-08-17 19:52:42 +08:00
inverted_residual.py	[Docs] Add code-spell pre-commit hook and fix a large mount of typos. (#470)	2021-10-13 14:33:07 +08:00
make_divisible.py	[Docs] Add Copyright information. (#413)	2021-08-17 19:52:42 +08:00
se_layer.py	[Enhance] Enhence SE layer to support custom squeeze channels. (#417)	2021-08-20 13:31:44 +08:00