dbf3df21a3
[Refactor] Use `out_type` to specify ViT-like backbone output. ( #1408 )
...
* [Refactor] Use to specify ViT-like backbone output.
* Fix ClsBatchNormNeck
* Update mmpretrain/models/necks/mae_neck.py
---------
Co-authored-by: Yixiao Fang <36138628+fangyixiao18@users.noreply.github.com>
2023-03-09 11:02:58 +08:00
0979e78573
Rename the package name to `mmpretrain`.
2023-02-17 15:20:55 +08:00
b7d0d521eb
[Refactor] Use `mmengine` instead of `mmcv` and refactor some transforms. ( #986 )
...
* [Refactor] Refactor the rest data transforms and fix some docstring.
* Use `mmengine` instead of `mmcv`
* Refactor KFold dataset tools
* Fix docstring according to comments
2022-08-24 15:59:02 +08:00
b5193a9029
[Fix] Reduce unit test memory usage of T2T-ViT
2022-05-16 17:01:30 +08:00
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
fffa30dd48
[Feature] Add Tokens-to-Token ViT backbone and converted checkpoints. ( #467 )
...
* add t2t backbone
* register t2t_vit
* add t2t_vit config
* [Temp] Align posterize transform with timm.
* Fix lint
* Refactor t2t-vit
* Add config for t2t-vit
* Add metafile and README for t2t-vit
* Add unit tests
* configs
* Update metafile and README
* Improve docstring
* Fix batch size which should be 8x64 instead of 8x128
* Fix typo
* Update model zoo
* Update training augments config.
* Move some arguments of T2TModule to T2TViT
* Update docs.
* Update unit test
Co-authored-by: HIT-cwh <2892770585@qq.com>
2021-10-29 10:37:16 +08:00
Ma Zerun