add vit-adapter and align backbone forward

configs/vit_adapter/README.md

@@ -0,0 +1,15 @@
+# Semantic Flow for Fast and Accurate Scene Parsing
+
+## Reference
+
+> Xiangtai Li, Ansheng You, Zhen Zhu, Houlong Zhao, Maoke Yang, Kuiyuan Yang, Shaohua Tan, Yunhai Tong:
+Semantic Flow for Fast and Accurate Scene Parsing. ECCV (1) 2020: 775-793 .
+
+## Performance
+
+### Cityscapes
+
+| Model | Backbone | Resolution | Training Iters | mIoU | mIoU (flip) | mIoU (ms+flip) | Links |
+|-|-|-|-|-|-|-|-|
+|SFNet|ResNet18_OS8|1024x1024|80000|78.72%|79.11%|79.28%|[model](https://bj.bcebos.com/paddleseg/dygraph/cityscapes/sfnet_resnet18_os8_cityscapes_1024x1024_80k/model.pdparams) \| [log](https://bj.bcebos.com/paddleseg/dygraph/cityscapes/sfnet_resnet18_os8_cityscapes_1024x1024_80k/train.log) \| [vdl](https://www.paddlepaddle.org.cn/paddle/visualdl/service/app/scalar?id=0d790ad96282048b136342fcebb08d14)|
+|SFNet|ResNet50_OS8|1024x1024|80000|81.49%|81.63%|81.85%|[model](https://bj.bcebos.com/paddleseg/dygraph/cityscapes/sfnet_resnet50_os8_cityscapes_1024x1024_80k/model.pdparams) \| [log](https://bj.bcebos.com/paddleseg/dygraph/cityscapes/sfnet_resnet50_os8_cityscapes_1024x1024_80k/train.log) \| [vdl](https://paddlepaddle.org.cn/paddle/visualdl/service/app?id=d458349ec63ea8ccd6fae84afa8ea981)|

configs/vit_adapter/upernet_deit_adapter_tiny_512_160k_ade20k.yml

@@ -0,0 +1,77 @@
+_base_: '../_base_/ade20k.yml'
+
+batch_size: 4  # total batch size is 16
+iters: 160000
+
+train_dataset:
+  transforms:
+    - type: ResizeStepScaling
+      min_scale_factor: 0.5
+      max_scale_factor: 2.0
+      scale_step_size: 0.25
+    - type: RandomPaddingCrop
+      crop_size: [512, 512]
+    - type: RandomHorizontalFlip
+    - type: RandomDistort
+      brightness_range: 0.4
+      contrast_range: 0.4
+      saturation_range: 0.4
+    - type: Normalize
+      mean: [0.485, 0.456, 0.406]
+      std: [0.229, 0.224, 0.225]
+
+val_dataset:
+  transforms:
+    - type: Resize
+      target_size: [2048, 512]
+      keep_ratio: True
+      size_divisor: 32
+    - type: Normalize
+      mean: [0.485, 0.456, 0.406]
+      std: [0.229, 0.224, 0.225]
+
+export:
+  transforms:
+    - type: Resize
+      target_size: [2048, 512]
+      keep_ratio: True
+      size_divisor: 32
+    - type: Normalize
+      mean: [0.485, 0.456, 0.406]
+      std: [0.229, 0.224, 0.225]
+
+optimizer:
+  _inherited_: False
+  type: AdamW
+  weight_decay: 0.01
+
+lr_scheduler:
+  type: PolynomialDecay
+  learning_rate: 0.0012
+  end_lr: 0
+  power: 1.0
+  warmup_iters: 1500
+  warmup_start_lr: 1.0e-6
+
+loss:
+  types:
+    - type: CrossEntropyLoss
+  coef: [1]
+
+model:
+  type: TopFormer
+  backbone:
+    type: ViTAdapter
+    num_heads: 3
+    patch_size: 16
+    embed_dim: 192
+    depth: 12
+    mlp_ratio: 4
+    drop_path_rate: 0.1
+    conv_inplane: 64
+    n_points: 4
+    deform_num_heads: 6
+    cffn_ratio: 0.25
+    deform_ratio: 1.0
+    interaction_indexes: [[0, 2], [3, 5], [6, 8], [9, 11]]
+  pretrained: pretrained_model/upernet_deit_adapter_tiny_512_160_ade20k_from_torch.pdparams

paddleseg/models/backbones/__init__.py

@@ -26,3 +26,4 @@
 from .ghostnet import *
 from .top_transformer import *
 from .uhrnet import *
+from .vit_adapter import *