[Feature] Segformer backbone re-implementation (#594)

* [Feature]Segformer re-implementation

* Using act_cfg and norm_cfg to control activation and normalization

* Split this PR into several little PRs

* Fix lint error

* Remove SegFormerHead

* parameters init refactor

* 1. Refactor segformer backbone parameters init;

2. Remove rebundant functions and unit tests;

* Remove rebundant codes

* 1. Remove rebundant codes;

2. Modify module name;

* Refactor the backbone of segformer using mmcv.cnn.bricks.transformer.py

* Fix some code logic bugs.

* Add mit_convert.py to match pretrain keys of segformer.

* Resolve some comments.

* 1. Add some assert to ensure right params;

2. Support flexible peconv position;

* Add pe_index assert and fix unit test.

* 1. Add doc string for MixVisionTransformer;

2. Add some unit tests for MixVisionTransformer;

* Use hw_shape to pass shape of feature map.

* 1. Fix doc string of MixVisionTransformer;

2. Simplify MixFFN;

3. Modify H, W to hw_shape;

* Add more unit tests.

* Add doc string for shape convertion functions.

* Add some unit tests to improve code coverage.

* Fix Segformer backbone pretrain weights match bug.

* resolve the shape convertion functions doc string.

* Add pad_to_patch_size arg.

* Modify default value of pad_to_patch_size arg.

mmseg/models/backbones/__init__.py

@@ -1,6 +1,7 @@
 from .cgnet import CGNet
 from .fast_scnn import FastSCNN
 from .hrnet import HRNet
+from .mit import MixVisionTransformer
 from .mobilenet_v2 import MobileNetV2
 from .mobilenet_v3 import MobileNetV3
 from .resnest import ResNeSt
@@ -13,5 +14,5 @@
 __all__ = [
     'ResNet', 'ResNetV1c', 'ResNetV1d', 'ResNeXt', 'HRNet', 'FastSCNN',
     'ResNeSt', 'MobileNetV2', 'UNet', 'CGNet', 'MobileNetV3',
-    'VisionTransformer', 'SwinTransformer'
+    'VisionTransformer', 'SwinTransformer', 'MixVisionTransformer'
 ]