mmclassification/tests
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
..
data
test_backbones [Feature] Add swin-transformer model. (#271) 2021-07-01 09:30:42 +08:00
test_pipelines Fix magnitude_std bug in RandAugment, and update unit tests. (#309) 2021-06-21 11:25:11 +08:00
test_classifiers.py [Feature]Add augments to models/utils (#278) 2021-06-20 09:44:51 +08:00
test_dataset.py
test_eval_hook.py [Fix] Use MMCV's EvalHook in MMClassification (#182) 2021-03-25 17:38:51 +08:00
test_heads.py Fix Mobilenetv3 structure and add pretrained model (#291) 2021-06-27 23:19:36 +08:00
test_losses.py Refactor LabelSmoothLoss (#285) 2021-06-12 21:32:18 +08:00
test_metrics.py
test_neck.py GlabelAveragePooling support 1d, 2d and 3d by param, and add neck test (#236) 2021-05-10 15:00:50 +08:00