Commit Graph

18 Commits (15cd34bbef84b103970360c6a35fd6070445c201)

Author SHA1 Message Date
Ma Zerun 076ee10cac
[Feature] Add swin-transformer model. (#271)
* Add swin transformer archs S, B and L.

* Add SwinTransformer configs

* Add train config files of swin.

* Align init method with original code

* Use nn.Unfold to merge patch

* Change all ConfigDict to dict

* Add init_cfg for all subclasses of BaseModule.

* Use mmcv version init function

* Add Swin README

* Use safer cfg copy method

* Improve docstring and variable name.

* Fix some difference in randaug

Fix BGR bug, align scheduler config.

Fix label smoothing parameter difference.

* Fix missing droppath in attn

* Fix bug of relative posititon table if window width is not equal to
height.

* Make `PatchMerging` more general, support kernel, stride, padding and
dilation.

* Rename `residual` to `identity` in attention and FFN.

* Add `auto_pad` option to auto pad feature map

* Improve docstring.

* Fix bug in ShiftWMSA padding.

* Remove unused `key` and `value` in ShiftWMSA

* Move `PatchMerging` into utils and use common `PatchEmbed`.

* Use latest `LinearClsHead`, train augments and label smooth settings.
And remove original `SwinLinearClsHead`.

* Mark some configs as "Evalution Only".

* Remove useless comment in config

* 1. Move ShiftWindowMSA and WindowMSA to `utils/attention.py`
2. Add docstrings of each module.
3. Fix some variables' names.
4. Other small improvement.

* Add unit tests of swin-transformer and patchmerging.

* Fix some bugs in unit tests.

* Fix bug of rel_position_index if window is not square.

* Make WindowMSA implicit, and add unit tests.

* Add metafile.yml, update readme and model_zoo.
2021-07-01 09:30:42 +08:00
LXXXXR 27a49a9646
bump version to v0.12.0 (#287) 2021-06-03 11:42:34 +08:00
LXXXXR dac090162d
Bump version to v0.11.1 (#256)
* bump version to v0.11.1

* minor fix

* minor fix

* minor fix

* minor fix
2021-05-21 16:36:08 +08:00
LXXXXR 37167158e7
bump version to v0.11.0 (#233) 2021-05-01 22:26:39 +08:00
mzr1996 3d87474c71
Add Chinese Readme and docs (#221)
* Add Citation in README

Add Citation and mmgeneration in README

* Merge inference and test section in getting_start.md and other small chagne.

* Fix code type in install.md

* Add Chinese Readme

* README and docs improvement.
2021-04-26 13:58:18 +08:00
LXXXXR 7d618e6606
[Fix] Fix version (#209)
* fix version

* add projects in openmmlab

* minor fix

* empty

* add mmocr

* empty

* empty

* fix linting
2021-04-16 19:07:17 +08:00
mzr1996 b7b520881f
Update CONTRIBUTING.md according to mmcv (#210)
* Update CONTRIBUTING.md according to mmcv

* Docstring formatting by docformatter

* Update openmmlab website.
2021-04-14 21:22:37 +08:00
LXXXXR 1f6549eeee
bump version to 0.10.0 (#194) 2021-04-01 10:39:18 +08:00
LXXXXR 7ca0ca271f
Bump version to 0.9.0 (#166)
* update docs for version 0.9.0

* add missing #153
2021-03-01 20:14:53 +08:00
LXXXXR 7f49632d7c
Bump version to 0.8.0 (#156)
* update docs to bump version

* minor change

* revise acording to comments
2021-01-31 17:50:40 +08:00
LXXXXR d835cd005a
Bump version to 0.7.0 (#129)
* add change log and unable MD024 in pre-commit hook

* fix readme and modify version

* Revised according to comments
2020-12-31 16:41:45 +08:00
LXXXXR 400074c321
Add markdown lint in pre-commit hook (#106)
* add mdlint

* remove duplicate check

* modify md files to pass linting check

* change mmcv download url

* remove torch1.4.0 version check

* remove torch1.4.0 version check
2020-12-02 19:42:45 +08:00
Lei Yang 360ae80591
rename detectors to classifiers (#19) 2020-08-05 00:43:13 +08:00
Lei Yang 8e1ef6af26
rm bibtex and contact (#15) 2020-07-27 22:18:05 +08:00
LiJiezhi 8247704afc
Update README.md (#7) 2020-07-21 19:28:50 +08:00
Kai Chen 0fb9b2f140
Update readme (#3)
* add badges and license

* minor format
2020-07-13 12:55:34 +08:00
yanglei 53f5568119 Add README 2020-07-12 00:06:54 +08:00
chenkai a99e6eb10d init commit 2020-05-21 21:21:43 +08:00