support transformer backbone (open-mmlab#465)

* vit backbone

* fix lint

* add docstrings and fix pretrained pos_embed dim not match prob

* add unittest for vit

* fix lint

* add vit based fcn configs

* fix import error

* support multiple resolution input images

* upsample pos_embed at init_weights

* support resize pos_embed at evaluation

* fix training errors

* add more unitest code for vit backbone

* unitest for uncovered code

* add norm_eval unittest

* refactor _pos_embeding

* minor change

* change var name

* rafactor init_weight

* load weights after resize

* ignore 'module' in pretrain checkpoint

* add with_cp

* add with_cp

Co-authored-by: Jiarui XU <[email protected]>

Author: 谢昕辰

mmseg/models/backbones/__init__.py

@@ -7,8 +7,10 @@
 from .resnet import ResNet, ResNetV1c, ResNetV1d
 from .resnext import ResNeXt
 from .unet import UNet
+from .vit import VisionTransformer
 
 __all__ = [
     'ResNet', 'ResNetV1c', 'ResNetV1d', 'ResNeXt', 'HRNet', 'FastSCNN',
-    'ResNeSt', 'MobileNetV2', 'UNet', 'CGNet', 'MobileNetV3'
+    'ResNeSt', 'MobileNetV2', 'UNet', 'CGNet', 'MobileNetV3',
+    'VisionTransformer'
 ]