更换文档检测模型

paddle_detection/configs/gn/README.md

@@ -0,0 +1,23 @@
+# Group Normalization
+
+## Model Zoo
+
+| 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-FPN   | Faster         |    1          |   2x     |    -       |  41.9  |    -    | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_fpn_gn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/gn/faster_rcnn_r50_fpn_gn_2x_coco.yml) |
+| ResNet50-FPN   | Mask           |    1          |   2x     |    -       |  42.3   |  38.4  | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_fpn_gn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/gn/mask_rcnn_r50_fpn_gn_2x_coco.yml) |
+| ResNet50-FPN   | Cascade Faster    |    1          |   2x     |    -       |  44.6   |  -  | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_rcnn_r50_fpn_gn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/gn/cascade_rcnn_r50_fpn_gn_2x_coco.yml) |
+| ResNet50-FPN   | Cacade Mask      |    1          |   2x     |    -       |  45.0   |  39.3  | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_mask_rcnn_r50_fpn_gn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/gn/cascade_mask_rcnn_r50_fpn_gn_2x_coco.yml) |
+
+
+**注意：** Faster R-CNN baseline仅使用 `2fc` head，而此处使用[`4conv1fc` head](https://arxiv.org/abs/1803.08494)（4层conv之间使用GN），并且FPN也使用GN，而对于Mask R-CNN是在mask head的4层conv之间也使用GN。
+
+## Citations
+```
+@inproceedings{wu2018group,
+  title={Group Normalization},
+  author={Wu, Yuxin and He, Kaiming},
+  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
+  year={2018}
+}
+```

paddle_detection/configs/gn/cascade_mask_rcnn_r50_fpn_gn_2x_coco.yml

@@ -0,0 +1,61 @@
+_BASE_: [
+  '../datasets/coco_instance.yml',
+  '../runtime.yml',
+  '../cascade_rcnn/_base_/optimizer_1x.yml',
+  '../cascade_rcnn/_base_/cascade_mask_rcnn_r50_fpn.yml',
+  '../cascade_rcnn/_base_/cascade_mask_fpn_reader.yml',
+]
+weights: output/cascade_mask_rcnn_r50_fpn_gn_2x_coco/model_final
+
+CascadeRCNN:
+  backbone: ResNet
+  neck: FPN
+  rpn_head: RPNHead
+  bbox_head: CascadeHead
+  mask_head: MaskHead
+  # post process
+  bbox_post_process: BBoxPostProcess
+  mask_post_process: MaskPostProcess
+
+FPN:
+  out_channel: 256
+  norm_type: gn
+
+CascadeHead:
+  head: CascadeXConvNormHead
+  roi_extractor:
+    resolution: 7
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+
+CascadeXConvNormHead:
+  num_convs: 4
+  out_channel: 1024
+  norm_type: gn
+
+MaskHead:
+  head: MaskFeat
+  roi_extractor:
+    resolution: 14
+    sampling_ratio: 0
+    aligned: True
+  mask_assigner: MaskAssigner
+  share_bbox_feat: False
+
+MaskFeat:
+  num_convs: 4
+  out_channel: 256
+  norm_type: gn
+
+
+epoch: 24
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [16, 22]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000

paddle_detection/configs/gn/cascade_rcnn_r50_fpn_gn_2x_coco.yml

@@ -0,0 +1,37 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  '../cascade_rcnn/_base_/optimizer_1x.yml',
+  '../cascade_rcnn/_base_/cascade_rcnn_r50_fpn.yml',
+  '../cascade_rcnn/_base_/cascade_fpn_reader.yml',
+]
+weights: output/cascade_rcnn_r50_fpn_gn_2x_coco/model_final
+
+FPN:
+  out_channel: 256
+  norm_type: gn
+
+CascadeHead:
+  head: CascadeXConvNormHead
+  roi_extractor:
+    resolution: 7
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+
+CascadeXConvNormHead:
+  num_convs: 4
+  out_channel: 1024
+  norm_type: gn
+
+
+epoch: 24
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [16, 22]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000

paddle_detection/configs/gn/faster_rcnn_r50_fpn_gn_2x_coco.yml

@@ -0,0 +1,45 @@
+_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_r50_fpn_gn_2x_coco/model_final
+
+FasterRCNN:
+  backbone: ResNet
+  neck: FPN
+  rpn_head: RPNHead
+  bbox_head: BBoxHead
+  # post process
+  bbox_post_process: BBoxPostProcess
+
+FPN:
+  out_channel: 256
+  norm_type: gn
+
+BBoxHead:
+  head: XConvNormHead
+  roi_extractor:
+    resolution: 7
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+
+XConvNormHead:
+  num_convs: 4
+  out_channel: 1024
+  norm_type: gn
+
+
+epoch: 24
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [16, 22]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000

paddle_detection/configs/gn/mask_rcnn_r50_fpn_gn_2x_coco.yml

@@ -0,0 +1,61 @@
+_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_r50_fpn_gn_2x_coco/model_final
+
+MaskRCNN:
+  backbone: ResNet
+  neck: FPN
+  rpn_head: RPNHead
+  bbox_head: BBoxHead
+  mask_head: MaskHead
+  # post process
+  bbox_post_process: BBoxPostProcess
+  mask_post_process: MaskPostProcess
+
+FPN:
+  out_channel: 256
+  norm_type: gn
+
+BBoxHead:
+  head: XConvNormHead
+  roi_extractor:
+    resolution: 7
+    sampling_ratio: 0
+    aligned: True
+  bbox_assigner: BBoxAssigner
+
+XConvNormHead:
+  num_convs: 4
+  out_channel: 1024
+  norm_type: gn
+
+MaskHead:
+  head: MaskFeat
+  roi_extractor:
+    resolution: 14
+    sampling_ratio: 0
+    aligned: True
+  mask_assigner: MaskAssigner
+  share_bbox_feat: False
+
+MaskFeat:
+  num_convs: 4
+  out_channel: 256
+  norm_type: gn
+
+
+epoch: 24
+LearningRate:
+  base_lr: 0.01
+  schedulers:
+  - !PiecewiseDecay
+    gamma: 0.1
+    milestones: [16, 22]
+  - !LinearWarmup
+    start_factor: 0.1
+    steps: 1000