mmsegmentation/mmseg
Ze Liu 214d083cce [WIP] Add Swin Transformer (#511)
* add Swin Transformer

* add Swin Transformer

* fixed import

* Add some swin training settings.

* Fix some filename error.

* Fix attribute name: pretrain -> pretrained

* Upload mmcls implementation of swin transformer.

* Refactor Swin Transformer to follow mmcls style.

* Refactor init_weigths of swin_transformer.py

* Fix lint

* Match inference precision

* Add some comments

* Add swin_convert to load official style ckpt

* Remove arg: auto_pad

* 1. Complete comments for each block;

2. Correct weight convert function;

3. Fix the pad of Patch Merging;

* Clean function args.

* Fix vit unit test.

* 1. Add swin transformer unit tests;

2. Fix some pad bug;

3. Modify config to adapt new swin implementation;

* Modify config arg

* Update readme.md of swin

* Fix config arg error and Add some swin benchmark msg.

* Add MeM and ms test content for readme.md of swin transformer.

* Fix doc string of swin module

* 1. Register swin transformer to model list;

2. Modify pth url which keep meta attribute;

* Update swin.py

* Merge config settings.

* Modify config style.

* Update README.md

Add ViT link

* Modify main readme.md

Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>
Co-authored-by: sennnnn <201730271412@mail.scut.edu.cn>
Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn>
2021-07-01 23:41:55 +08:00
..
apis infer batch size using len(result) in test function (#532) 2021-05-06 08:16:46 -07:00
core [feature]: Able to use save_best option (#575) 2021-06-02 16:25:26 -07:00
datasets [Feature] Support persistent_workers in DataLoader (PyTorch>=1.7.0) (#646) 2021-06-28 17:39:32 +08:00
models [WIP] Add Swin Transformer (#511) 2021-07-01 23:41:55 +08:00
ops add dynamic export and visualize to pytorch2onnx (#463) 2021-04-12 11:54:59 -07:00
utils [Enhance] Refactor inverted residual (#164) 2020-09-28 00:33:51 +08:00
__init__.py Use MMCV's EvalHook in MMSegmentation (#438) 2021-05-05 16:19:54 -07:00
version.py Bump to v0.14.1 (#604) 2021-06-16 21:49:56 -07:00