[Dygraph] add ResNet-vd, ResNet-34, ResNeXt-101 (PaddlePaddle#2071)

* add configs and modelzoo * remove trainreader of batchsize 2 * add vd r34 x101 * fix typo * add vd r34 x101 * add resnet dcn, clean code * fix x101 width in py2 * add faster mask rcnn dcn configs and modelzoo * fix dcn modelzoo * clean dcn configs code
heavengate · Jan 18, 2021 · ac358bf · ac358bf
1 parent 3d13ead
commit ac358bf
Show file tree

Hide file tree

Showing 30 changed files with 930 additions and 58 deletions.
diff --git a/dygraph/configs/dcn/README.md b/dygraph/configs/dcn/README.md
@@ -0,0 +1,33 @@
+### Deformable ConvNets v2
+
+| 骨架网络             | 网络类型           | 卷积    | 每张GPU图片个数 | 学习率策略 |推理时间(fps)| Box AP | Mask AP |                           下载                           | 配置文件 |
+| :------------------- | :------------- | :-----: |:--------: | :-----: | :-----------: |:----: | :-----: | :----------------------------------------------------------: | :----: |
+| ResNet50-FPN         | Faster         | c3-c5   |    2      |   1x    |    -     |  41.3  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_r50_fpn_1x_coco.yml) |
+| ResNet50-vd-FPN      | Faster         | c3-c5   |    2      |   2x    |    -     |  42.4  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_dcn_r50_vd_fpn_2x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_2x.yml) |
+| ResNet101-vd-FPN     | Faster         | c3-c5   |    2      |   1x    |    -     |  44.1  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_dcn_r101_vd_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_r101_vd_fpn_1x.yml) |
+| ResNeXt101-vd-FPN    | Faster         | c3-c5   |    1      |   1x    |    -     |  45.2  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x.pdparams) |[配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) |
+| ResNet50-FPN         | Mask           | c3-c5   |    1      |   1x    |    -     |  41.9  |  37.3   | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_dcn_r50_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r50_fpn_1x.yml) |
+| ResNet50-vd-FPN      | Mask           | c3-c5   |    1      |   2x    |    -     |  42.9  |  38.0   | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_dcn_r50_vd_fpn_2x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r50_vd_fpn_2x.yml) |
+| ResNet101-vd-FPN     | Mask           | c3-c5   |    1      |   1x    |    -     |  44.6  |  39.2   | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_dcn_r101_vd_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r101_vd_fpn_1x.yml) |
+| ResNeXt101-vd-FPN    | Mask           | c3-c5   |    1      |   1x    |     -    |  46.2  |  40.4   | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) |
+
+**注意事项:**  
+
+- Deformable卷积网络v2(dcn_v2)参考自论文[Deformable ConvNets v2](https://arxiv.org/abs/1811.11168).
+- `c3-c5`意思是在resnet模块的3到5阶段增加`dcn`.
+
+## Citations
+```
+@inproceedings{dai2017deformable,
+  title={Deformable Convolutional Networks},
+  author={Dai, Jifeng and Qi, Haozhi and Xiong, Yuwen and Li, Yi and Zhang, Guodong and Hu, Han and Wei, Yichen},
+  booktitle={Proceedings of the IEEE international conference on computer vision},
+  year={2017}
+}
+@article{zhu2018deformable,
+  title={Deformable ConvNets v2: More Deformable, Better Results},
+  author={Zhu, Xizhou and Hu, Han and Lin, Stephen and Dai, Jifeng},
+  journal={arXiv preprint arXiv:1811.11168},
+  year={2018}
+}
+```
diff --git a/dygraph/configs/dcn/faster_rcnn_dcn_r101_vd_fpn_1x_coco.yml b/dygraph/configs/dcn/faster_rcnn_dcn_r101_vd_fpn_1x_coco.yml
@@ -0,0 +1,29 @@
+_BASE_: [
+  'faster_rcnn_dcn_r50_fpn_1x_coco.yml',
+]
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar
+weights: output/faster_rcnn_dcn_r101_fpn_1x_coco/model_final
+
+ResNet:
+  # index 0 stands for res2
+  depth: 101
+  variant: d
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+  dcn_v2_stages: [1,2,3]
+
+epoch: 12
+LearningRate:
+  base_lr: 0.02
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+TrainReader:
+  batch_size: 2
diff --git a/dygraph/configs/dcn/faster_rcnn_dcn_r50_fpn_1x_coco.yml b/dygraph/configs/dcn/faster_rcnn_dcn_r50_fpn_1x_coco.yml
@@ -0,0 +1,30 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  '../faster_rcnn/_base_/optimizer_1x.yml',
+  '../faster_rcnn/_base_/faster_rcnn_r50_fpn.yml',
+  '../faster_rcnn/_base_/faster_fpn_reader.yml',
+]
+weights: output/faster_rcnn_dcn_r50_fpn_1x_coco/model_final
+
+ResNet:
+  depth: 50
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+  dcn_v2_stages: [1,2,3]
+
+epoch: 12
+LearningRate:
+  base_lr: 0.02
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+TrainReader:
+  batch_size: 2
diff --git a/dygraph/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_2x_coco.yml b/dygraph/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_2x_coco.yml
@@ -0,0 +1,29 @@
+_BASE_: [
+  'faster_rcnn_dcn_r50_fpn_1x_coco.yml',
+]
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar
+weights: output/faster_rcnn_dcn_r50_vd_fpn_2x_coco/model_final
+
+ResNet:
+  # index 0 stands for res2
+  depth: 50
+  variant: d
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+  dcn_v2_stages: [1,2,3]
+
+epoch: 24
+LearningRate:
+  base_lr: 0.02
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [16, 22]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
+
+TrainReader:
+  batch_size: 2
diff --git a/dygraph/configs/dcn/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml b/dygraph/configs/dcn/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml
@@ -0,0 +1,29 @@
+_BASE_: [
+  'faster_rcnn_dcn_r50_fpn_1x_coco.yml',
+]
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar
+weights: output/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco/model_final.pdparams
+
+ResNet:
+  # for ResNeXt: groups, base_width, base_channels
+  depth: 101
+  groups: 64
+  base_width: 4
+  base_channels: 64
+  variant: d
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+  dcn_v2_stages: [1,2,3]
+
+epoch: 12
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
diff --git a/dygraph/configs/dcn/mask_rcnn_dcn_r101_vd_fpn_1x_coco.yml b/dygraph/configs/dcn/mask_rcnn_dcn_r101_vd_fpn_1x_coco.yml
@@ -0,0 +1,26 @@
+_BASE_: [
+  'mask_rcnn_dcn_r50_fpn_1x_coco.yml',
+]
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar
+weights: output/mask_rcnn_dcn_r101_fpn_1x_coco/model_final.pdparams
+
+ResNet:
+  # index 0 stands for res2
+  depth: 101
+  variant: d
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+  dcn_v2_stages: [1,2,3]
+
+epoch: 12
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
diff --git a/dygraph/configs/dcn/mask_rcnn_dcn_r50_fpn_1x_coco.yml b/dygraph/configs/dcn/mask_rcnn_dcn_r50_fpn_1x_coco.yml
@@ -0,0 +1,27 @@
+_BASE_: [
+  '../datasets/coco_instance.yml',
+  '../runtime.yml',
+  '../mask_rcnn/_base_/optimizer_1x.yml',
+  '../mask_rcnn/_base_/mask_rcnn_r50_fpn.yml',
+  '../mask_rcnn/_base_/mask_fpn_reader.yml',
+]
+weights: output/mask_rcnn_dcn_r50_fpn_1x_coco/model_final
+
+ResNet:
+  depth: 50
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+  dcn_v2_stages: [1,2,3]
+
+epoch: 12
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
diff --git a/dygraph/configs/dcn/mask_rcnn_dcn_r50_vd_fpn_2x_coco.yml b/dygraph/configs/dcn/mask_rcnn_dcn_r50_vd_fpn_2x_coco.yml
@@ -0,0 +1,26 @@
+_BASE_: [
+  'mask_rcnn_dcn_r50_fpn_1x_coco.yml',
+]
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar
+weights: output/mask_rcnn_dcn_r50_vd_fpn_2x_coco/model_final
+
+ResNet:
+  # index 0 stands for res2
+  depth: 50
+  variant: d
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+  dcn_v2_stages: [1,2,3]
+
+epoch: 24
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [16, 22]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
diff --git a/dygraph/configs/dcn/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml b/dygraph/configs/dcn/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml
@@ -0,0 +1,29 @@
+_BASE_: [
+  'mask_rcnn_dcn_r50_fpn_1x_coco.yml',
+]
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar
+weights: output/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco/model_final.pdparams
+
+ResNet:
+  # for ResNeXt: groups, base_width, base_channels
+  depth: 101
+  variant: d
+  groups: 64
+  base_width: 4
+  base_channels: 64
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+  dcn_v2_stages: [1,2,3]
+
+epoch: 12
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000
diff --git a/dygraph/configs/faster_rcnn/README.md b/dygraph/configs/faster_rcnn/README.md
@@ -4,8 +4,11 @@
 
 | 骨架网络             | 网络类型       | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP |                           下载                          | 配置文件 |
 | :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----: | :-----------------------------------------------------: | :-----: |
-| ResNet50             | Faster         |    1    |   1x    |     ----     |  35.1  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn_r50_1x_coco.yml) |
-| ResNet50-FPN         | Faster         |    1    |   1x    |     ----     |  37.0  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn_r50_fpn_1x_coco.yml) |
+| ResNet50             | Faster         |    1    |   1x    |     ----     |  35.1  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn/faster_rcnn_r50_1x_coco.yml) |
+| ResNet50-FPN         | Faster         |    1    |   1x    |     ----     |  37.0  |    -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.yml) |
+| ResNet34-FPN         | Faster         |    2    |   1x    |     ----     |  36.7  |   -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r34_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn/faster_rcnn_r34_fpn_1x_coco.yml) |
+| ResNet101            | Faster         |    1    |   1x    |     ----     |  38.3  |   -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r101_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn/faster_rcnn_r101_1x_coco.yml) |
+| ResNet101-FPN        | Faster         |    1    |   1x    |     ----     |  38.7  |   -    | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r101_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn/faster_rcnn_r101_fpn_1x_coco.yml) |
 
 ## Citations
 ```

diff --git a/dygraph/configs/faster_rcnn/faster_rcnn_r101_1x_coco.yml b/dygraph/configs/faster_rcnn/faster_rcnn_r101_1x_coco.yml
@@ -0,0 +1,14 @@
+_BASE_: [
+  'faster_rcnn_r50_1x_coco.yml',
+]
+
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar
+weights: output/faster_rcnn_r101_1x_coco/model_final
+
+ResNet:
+  # index 0 stands for res2
+  depth: 101
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
diff --git a/dygraph/configs/faster_rcnn/faster_rcnn_r101_fpn_1x_coco.yml b/dygraph/configs/faster_rcnn/faster_rcnn_r101_fpn_1x_coco.yml
@@ -0,0 +1,14 @@
+_BASE_: [
+  'faster_rcnn_r50_fpn_1x_coco.yml',
+]
+
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar
+weights: output/faster_rcnn_r101_fpn_1x_coco/model_final
+
+ResNet:
+  # index 0 stands for res2
+  depth: 101
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
diff --git a/dygraph/configs/faster_rcnn/faster_rcnn_r101_fpn_2x_coco.yml b/dygraph/configs/faster_rcnn/faster_rcnn_r101_fpn_2x_coco.yml
@@ -0,0 +1,25 @@
+_BASE_: [
+  'faster_rcnn_r50_fpn_1x_coco.yml',
+]
+
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar
+weights: output/faster_rcnn_r101_fpn_2x_coco/model_final
+
+ResNet:
+  # index 0 stands for res2
+  depth: 101
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+
+epoch: 24
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [16, 22]
+  - !LinearWarmup
+    start_factor: 0.3333333333333333
+    steps: 500
diff --git a/dygraph/configs/faster_rcnn/faster_rcnn_r101_vd_1x_coco.yml b/dygraph/configs/faster_rcnn/faster_rcnn_r101_vd_1x_coco.yml
@@ -0,0 +1,26 @@
+_BASE_: [
+  'faster_rcnn_r50_1x_coco.yml',
+]
+
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_vd_pretrained.tar
+weights: output/faster_rcnn_r101_vd_1x_coco/model_final
+
+ResNet:
+  # index 0 stands for res2
+  depth: 101
+  variant: d
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+
+epoch: 12
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.3333333333333333
+    steps: 1000
diff --git a/dygraph/configs/faster_rcnn/faster_rcnn_r101_vd_fpn_1x_coco.yml b/dygraph/configs/faster_rcnn/faster_rcnn_r101_vd_fpn_1x_coco.yml
@@ -0,0 +1,25 @@
+_BASE_: [
+  'faster_rcnn_r50_fpn_1x_coco.yml',
+]
+pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_vd_pretrained.tar
+weights: output/faster_rcnn_r101_vd_fpn_1x_coco/model_final.pdparams
+
+ResNet:
+  # index 0 stands for res2
+  depth: 101
+  variant: d
+  norm_type: bn
+  freeze_at: 0
+  return_idx: [0,1,2,3]
+  num_stages: 4
+
+epoch: 12
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [8, 11]
+  - !LinearWarmup
+    start_factor: 0.3333333333333333
+    steps: 1000