Ma Zerun c708770b42
[Enhance] Support dynamic input shape for ViT-based algorithms. (#706)
* Move `resize_pos_embed` to `mmcls.models.utils`

* Refactor Vision Transformer

* Refactor DeiT

* Refactor MLP-Mixer

* Refactor Swin-Transformer

* Remove `indexing` arg

* Support dynamic inputs for t2t_vit

* Add copyright

* Fix bugs in swin transformer

* Add `pad_small_maps` option

* Update swin transformer

* Handle `attn_mask` in checkpoints of swin

* Imporve by comments
2022-03-03 13:10:12 +08:00
..
2022-02-23 11:36:33 +08:00
2022-01-28 10:36:45 +08:00
2022-02-23 11:36:33 +08:00