Skip to content

P
PaddleDetection

s920243400 / PaddleDetection
与 Fork 源项目一致

Fork自 PaddlePaddle / PaddleDetection

通知 2
Star 0
Fork 0
P
PaddleDetection

体验新版 GitCode，发现更多精彩内容 >>

未验证 提交 a09fe2c1 编写于 作者: F Feng Ni 提交者： GitHub
浏览文件
操作

[doc] Fix rcnn det coments (#2464)

上级 24f582fd
隐藏空白更改
内联 并排
Showing with 207 addition and 85 deletion
configs/cascade_rcnn/README.md
浏览文件 @ a09fe2c1
...@@ -4,8 +4,8 @@ ...@@ -4,8 +4,8 @@
| 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 | | 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 | Cascade Faster | 1 | 1x | ---- | 41.1 | - | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.yml) | | ResNet50-FPN | Cascade Faster | 1 | 1x | ---- | 41.1 | - | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.yml) |
| ResNet50-FPN | Cascade Mask | 1 | 1x | ---- | 41.8 | 36.3 | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.yml) | | ResNet50-FPN | Cascade Mask | 1 | 1x | ---- | 41.8 | 36.3 | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.yml) |
**注意：** Cascade R-CNN模型精度依赖Paddle develop分支修改，精度复现须使用[每日版本](https://www.paddlepaddle.org.cn/documentation/docs/zh/install/Tables.html#whl-dev)或2.0.1版本(将于2021.03发布)，使用Paddle 2.0.0版本会有少量精度损失。 **注意：** Cascade R-CNN模型精度依赖Paddle develop分支修改，精度复现须使用[每日版本](https://www.paddlepaddle.org.cn/documentation/docs/zh/install/Tables.html#whl-dev)或2.0.1版本(将于2021.03发布)，使用Paddle 2.0.0版本会有少量精度损失。
......
configs/dcn/README.md
浏览文件 @ a09fe2c1
...@@ -2,17 +2,17 @@ ...@@ -2,17 +2,17 @@
| 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 | | 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 | 1 | 1x | - | 42.1 | - | [下载链接](https://paddledet.bj.bcebos.com/models/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-FPN | Faster | c3-c5 | 1 | 1x | - | 42.1 | - | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/dcn/faster_rcnn_dcn_r50_fpn_1x_coco.yml) |
| ResNet50-vd-FPN | Faster | c3-c5 | 1 | 1x | - | 42.7 | - | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_dcn_r50_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_1x_coco.yml) | | ResNet50-vd-FPN | Faster | c3-c5 | 1 | 1x | - | 42.7 | - | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_dcn_r50_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_1x_coco.yml) |
| ResNet50-vd-FPN | Faster | c3-c5 | 1 | 2x | - | 43.7 | - | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_dcn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_2x_coco.yml) | | ResNet50-vd-FPN | Faster | c3-c5 | 1 | 2x | - | 43.7 | - | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_dcn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_2x_coco.yml) |
| ResNet101-vd-FPN | Faster | c3-c5 | 1 | 1x | - | 45.1 | - | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_dcn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_r101_vd_fpn_1x_coco.yml) | | ResNet101-vd-FPN | Faster | c3-c5 | 1 | 1x | - | 45.1 | - | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_dcn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/dcn/faster_rcnn_dcn_r101_vd_fpn_1x_coco.yml) |
| ResNeXt101-vd-FPN | Faster | c3-c5 | 1 | 1x | - | 46.5 | - | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.pdparams) |[配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml) | | ResNeXt101-vd-FPN | Faster | c3-c5 | 1 | 1x | - | 46.5 | - | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.pdparams) |[配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/dcn/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml) |
| ResNet50-FPN | Mask | c3-c5 | 1 | 1x | - | 42.7 | 38.4 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r50_fpn_1x_coco.yml) | | ResNet50-FPN | Mask | c3-c5 | 1 | 1x | - | 42.7 | 38.4 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/dcn/mask_rcnn_dcn_r50_fpn_1x_coco.yml) |
| ResNet50-vd-FPN | Mask | c3-c5 | 1 | 2x | - | 44.6 | 39.8 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r50_vd_fpn_2x_coco.yml) | | ResNet50-vd-FPN | Mask | c3-c5 | 1 | 2x | - | 44.6 | 39.8 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/dcn/mask_rcnn_dcn_r50_vd_fpn_2x_coco.yml) |
| ResNet101-vd-FPN | Mask | c3-c5 | 1 | 1x | - | 45.6 | 40.6 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r101_vd_fpn_1x_coco.yml) | | ResNet101-vd-FPN | Mask | c3-c5 | 1 | 1x | - | 45.6 | 40.6 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/dcn/mask_rcnn_dcn_r101_vd_fpn_1x_coco.yml) |
| ResNeXt101-vd-FPN | Mask | c3-c5 | 1 | 1x | - | 47.3 | 42.0 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml) | | ResNeXt101-vd-FPN | Mask | c3-c5 | 1 | 1x | - | 47.3 | 42.0 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/dcn/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml) |
| ResNet50-FPN | Cascade Faster | c3-c5 | 1 | 1x | - | 42.1 | - | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_rcnn_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/cascade_rcnn_dcn_r50_fpn_1x_coco.yml) | | ResNet50-FPN | Cascade Faster | c3-c5 | 1 | 1x | - | 42.1 | - | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_rcnn_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/dcn/cascade_rcnn_dcn_r50_fpn_1x_coco.yml) |
| ResNeXt101-vd-FPN | Cascade Faster | c3-c5 | 1 | 1x | - | 48.8 | - | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml) | | ResNeXt101-vd-FPN | Cascade Faster | c3-c5 | 1 | 1x | - | 48.8 | - | [下载链接](https://paddledet.bj.bcebos.com/models/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/dcn/cascade_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml) |
**注意事项:** **注意事项:**
......
configs/faster_rcnn/README.md
浏览文件 @ a09fe2c1
...@@ -4,20 +4,20 @@ ...@@ -4,20 +4,20 @@
| 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 | 下载 | 配置文件 | | 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 | 下载 | 配置文件 |
| :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: | | :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: |
| ResNet50 | Faster | 1 | 1x | ---- | 36.7 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r50_1x_coco.yml) | | ResNet50 | Faster | 1 | 1x | ---- | 36.7 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_1x_coco.yml) |
| ResNet50-vd | Faster | 1 | 1x | ---- | 37.6 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r50_vd_1x_coco.yml) | | ResNet50-vd | Faster | 1 | 1x | ---- | 37.6 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_vd_1x_coco.yml) |
| ResNet101 | Faster | 1 | 1x | ---- | 39.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r101_1x_coco.yml) | | ResNet101 | Faster | 1 | 1x | ---- | 39.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r101_1x_coco.yml) |
| ResNet34-FPN | Faster | 1 | 1x | ---- | 37.8 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r34_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r34_fpn_1x_coco.yml) | | ResNet34-FPN | Faster | 1 | 1x | ---- | 37.8 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r34_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r34_fpn_1x_coco.yml) |
| ResNet34-vd-FPN | Faster | 1 | 1x | ---- | 38.5 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r34_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r34_vd_fpn_1x_coco.yml) | | ResNet34-vd-FPN | Faster | 1 | 1x | ---- | 38.5 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r34_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r34_vd_fpn_1x_coco.yml) |
| ResNet50-FPN | Faster | 1 | 1x | ---- | 38.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.yml) | | ResNet50-FPN | Faster | 1 | 1x | ---- | 38.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.yml) |
| ResNet50-FPN | Faster | 1 | 2x | ---- | 40.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r50_fpn_2x_coco.yml) | | ResNet50-FPN | Faster | 1 | 2x | ---- | 40.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_fpn_2x_coco.yml) |
| ResNet50-vd-FPN | Faster | 1 | 1x | ---- | 39.5 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r50_vd_fpn_1x_coco.yml) | | ResNet50-vd-FPN | Faster | 1 | 1x | ---- | 39.5 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_vd_fpn_1x_coco.yml) |
| ResNet50-vd-FPN | Faster | 1 | 2x | ---- | 40.8 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r50_vd_fpn_2x_coco.yml) | | ResNet50-vd-FPN | Faster | 1 | 2x | ---- | 40.8 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r50_vd_fpn_2x_coco.yml) |
| ResNet101-FPN | Faster | 1 | 2x | ---- | 41.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r101_fpn_2x_coco.yml) | | ResNet101-FPN | Faster | 1 | 2x | ---- | 41.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r101_fpn_2x_coco.yml) |
| ResNet101-vd-FPN | Faster | 1 | 1x | ---- | 42.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r101_vd_fpn_1x_coco.yml) | | ResNet101-vd-FPN | Faster | 1 | 1x | ---- | 42.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r101_vd_fpn_1x_coco.yml) |
| ResNet101-vd-FPN | Faster | 1 | 2x | ---- | 43.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r101_vd_fpn_2x_coco.yml) | | ResNet101-vd-FPN | Faster | 1 | 2x | ---- | 43.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_r101_vd_fpn_2x_coco.yml) |
| ResNeXt101-vd-FPN | Faster | 1 | 1x | ---- | 43.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_x101_vd_64x4d_fpn_1x_coco.yml) | | ResNeXt101-vd-FPN | Faster | 1 | 1x | ---- | 43.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_x101_vd_64x4d_fpn_1x_coco.yml) |
| ResNeXt101-vd-FPN | Faster | 1 | 2x | ---- | 44.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_x101_vd_64x4d_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_x101_vd_64x4d_fpn_2x_coco.yml) | | ResNeXt101-vd-FPN | Faster | 1 | 2x | ---- | 44.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_x101_vd_64x4d_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/faster_rcnn/faster_rcnn_x101_vd_64x4d_fpn_2x_coco.yml) |
**注意：** Faster R-CNN模型精度依赖Paddle develop分支修改，精度复现须使用[每日版本](https://www.paddlepaddle.org.cn/documentation/docs/zh/install/Tables.html#whl-dev)或2.0.1版本(将于2021.03发布)，使用Paddle 2.0.0版本会有少量精度损失。 **注意：** Faster R-CNN模型精度依赖Paddle develop分支修改，精度复现须使用[每日版本](https://www.paddlepaddle.org.cn/documentation/docs/zh/install/Tables.html#whl-dev)或2.0.1版本(将于2021.03发布)，使用Paddle 2.0.0版本会有少量精度损失。
......
configs/hrnet/README.md
浏览文件 @ a09fe2c1
...@@ -30,5 +30,5 @@ ...@@ -30,5 +30,5 @@
| Backbone | Type | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs | | Backbone | Type | Image/gpu | Lr schd | Inf time (fps) | Box AP | Mask AP | Download | Configs |
| :---------------------- | :------------- | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :-----: | | :---------------------- | :------------- | :-------: | :-----: | :------------: | :----: | :-----: | :----------------------------------------------------------: | :-----: |
| HRNetV2p_W18 | Faster | 1 | 1x | - | 36.8 | - | [model](https://paddledet.bj.bcebos.com/models/faster_rcnn_hrnetv2p_w18_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/hrnet/faster_rcnn_hrnetv2p_w18_1x_coco.yml) | | HRNetV2p_W18 | Faster | 1 | 1x | - | 36.8 | - | [model](https://paddledet.bj.bcebos.com/models/faster_rcnn_hrnetv2p_w18_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/hrnet/faster_rcnn_hrnetv2p_w18_1x_coco.yml) |
| HRNetV2p_W18 | Faster | 1 | 2x | - | 39.0 | - | [model](https://paddledet.bj.bcebos.com/models/faster_rcnn_hrnetv2p_w18_2x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/hrnet/faster_rcnn_hrnetv2p_w18_2x_coco.yml) | | HRNetV2p_W18 | Faster | 1 | 2x | - | 39.0 | - | [model](https://paddledet.bj.bcebos.com/models/faster_rcnn_hrnetv2p_w18_2x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/hrnet/faster_rcnn_hrnetv2p_w18_2x_coco.yml) |
configs/mask_rcnn/README.md
浏览文件 @ a09fe2c1
...@@ -4,16 +4,16 @@ ...@@ -4,16 +4,16 @@
| 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 | | 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 | Mask | 1 | 1x | ---- | 37.4 | 32.8 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_1x_coco.yml) | | ResNet50 | Mask | 1 | 1x | ---- | 37.4 | 32.8 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_r50_1x_coco.yml) |
| ResNet50 | Mask | 1 | 2x | ---- | 39.7 | 34.5 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_2x_coco.yml) | | ResNet50 | Mask | 1 | 2x | ---- | 39.7 | 34.5 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_r50_2x_coco.yml) |
| ResNet50-FPN | Mask | 1 | 1x | ---- | 39.2 | 35.6 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.yml) | | ResNet50-FPN | Mask | 1 | 1x | ---- | 39.2 | 35.6 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.yml) |
| ResNet50-FPN | Mask | 1 | 2x | ---- | 40.5 | 36.7 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_fpn_2x_coco.yml) | | ResNet50-FPN | Mask | 1 | 2x | ---- | 40.5 | 36.7 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_r50_fpn_2x_coco.yml) |
| ResNet50-vd-FPN | Mask | 1 | 1x | ---- | 40.3 | 36.4 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_vd_fpn_1x_coco.yml) | | ResNet50-vd-FPN | Mask | 1 | 1x | ---- | 40.3 | 36.4 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_r50_vd_fpn_1x_coco.yml) |
| ResNet50-vd-FPN | Mask | 1 | 2x | ---- | 41.4 | 37.5 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_vd_fpn_2x_coco.yml) | | ResNet50-vd-FPN | Mask | 1 | 2x | ---- | 41.4 | 37.5 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_r50_vd_fpn_2x_coco.yml) |
| ResNet101-FPN | Mask | 1 | 1x | ---- | 40.6 | 36.6 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r101_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r101_fpn_1x_coco.yml) | | ResNet101-FPN | Mask | 1 | 1x | ---- | 40.6 | 36.6 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r101_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_r101_fpn_1x_coco.yml) |
| ResNet101-vd-FPN | Mask | 1 | 1x | ---- | 42.4 | 38.1 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r101_vd_fpn_1x_coco.yml) | | ResNet101-vd-FPN | Mask | 1 | 1x | ---- | 42.4 | 38.1 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_r101_vd_fpn_1x_coco.yml) |
| ResNeXt101-vd-FPN | Mask | 1 | 1x | ---- | 44.0 | 39.5 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_x101_vd_64x4d_fpn_1x_coco.yml) | | ResNeXt101-vd-FPN | Mask | 1 | 1x | ---- | 44.0 | 39.5 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_x101_vd_64x4d_fpn_1x_coco.yml) |
| ResNeXt101-vd-FPN | Mask | 1 | 2x | ---- | 44.6 | 39.8 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_x101_vd_64x4d_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_x101_vd_64x4d_fpn_2x_coco.yml) | | ResNeXt101-vd-FPN | Mask | 1 | 2x | ---- | 44.6 | 39.8 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_x101_vd_64x4d_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/mask_rcnn/mask_rcnn_x101_vd_64x4d_fpn_2x_coco.yml) |
**注意：** Mask R-CNN模型精度依赖Paddle develop分支修改，精度复现须使用[每日版本](https://www.paddlepaddle.org.cn/documentation/docs/zh/install/Tables.html#whl-dev)或2.0.1版本(将于2021.03发布)，使用Paddle 2.0.0版本会有少量精度损失。 **注意：** Mask R-CNN模型精度依赖Paddle develop分支修改，精度复现须使用[每日版本](https://www.paddlepaddle.org.cn/documentation/docs/zh/install/Tables.html#whl-dev)或2.0.1版本(将于2021.03发布)，使用Paddle 2.0.0版本会有少量精度损失。
......
ppdet/data/source/category.py
浏览文件 @ a09fe2c1
...@@ -32,6 +32,8 @@ def get_categories(metric_type, anno_file=None): ...@@ -32,6 +32,8 @@ def get_categories(metric_type, anno_file=None):
to category name map from annotation file. to category name map from annotation file.
Args: Args:
metric_type (str): metric type, currently support 'coco', 'voc', 'oid'
and 'widerface'.
anno_file (str): annotation file path anno_file (str): annotation file path
""" """
if metric_type.lower() == 'coco': if metric_type.lower() == 'coco':
......
ppdet/data/source/coco.py
浏览文件 @ a09fe2c1
...@@ -24,6 +24,17 @@ logger = setup_logger(__name__) ...@@ -24,6 +24,17 @@ logger = setup_logger(__name__)
@register @register
@serializable @serializable
class COCODataSet(DetDataset): class COCODataSet(DetDataset):
"""
Load dataset with COCO format.
Args:
dataset_dir (str): root directory for dataset.
image_dir (str): directory for images.
anno_path (str): coco annotation file path.
data_fields (list): key name of data dictionary, at least have 'image'.
sample_num (int): number of samples to load, -1 means all.
"""
def __init__(self, def __init__(self,
dataset_dir=None, dataset_dir=None,
image_dir=None, image_dir=None,
......
ppdet/data/source/dataset.py
浏览文件 @ a09fe2c1
...@@ -27,6 +27,18 @@ import copy ...@@ -27,6 +27,18 @@ import copy
@serializable @serializable
class DetDataset(Dataset): class DetDataset(Dataset):
"""
Load detection dataset.
Args:
dataset_dir (str): root directory for dataset.
image_dir (str): directory for images.
anno_path (str): annotation file path.
data_fields (list): key name of data dictionary, at least have 'image'.
sample_num (int): number of samples to load, -1 means all.
use_default_label (bool): whether to load default label list.
"""
def __init__(self, def __init__(self,
dataset_dir=None, dataset_dir=None,
image_dir=None, image_dir=None,
......
ppdet/data/source/voc.py
浏览文件 @ a09fe2c1
...@@ -38,6 +38,7 @@ class VOCDataSet(DetDataset): ...@@ -38,6 +38,7 @@ class VOCDataSet(DetDataset):
dataset_dir (str): root directory for dataset. dataset_dir (str): root directory for dataset.
image_dir (str): directory for images. image_dir (str): directory for images.
anno_path (str): voc annotation file path. anno_path (str): voc annotation file path.
data_fields (list): key name of data dictionary, at least have 'image'.
sample_num (int): number of samples to load, -1 means all. sample_num (int): number of samples to load, -1 means all.
label_list (str): if use_default_label is False, will load label_list (str): if use_default_label is False, will load
mapping between category and class index. mapping between category and class index.
......
ppdet/data/source/widerface.py
浏览文件 @ a09fe2c1
...@@ -31,8 +31,10 @@ class WIDERFaceDataSet(DetDataset): ...@@ -31,8 +31,10 @@ class WIDERFaceDataSet(DetDataset):
Args: Args:
dataset_dir (str): root directory for dataset. dataset_dir (str): root directory for dataset.
image_dir (str): directory for images. image_dir (str): directory for images.
anno_path (str): root directory for voc annotation data anno_path (str): WiderFace annotation data.
sample_num (int): number of samples to load, -1 means all data_fields (list): key name of data dictionary, at least have 'image'.
sample_num (int): number of samples to load, -1 means all.
with_lmk (bool): whether to load face landmark keypoint labels.
""" """
def __init__(self, def __init__(self,
......
ppdet/metrics/coco_utils.py
浏览文件 @ a09fe2c1
...@@ -67,13 +67,13 @@ def cocoapi_eval(jsonfile, ...@@ -67,13 +67,13 @@ def cocoapi_eval(jsonfile,
classwise=False): classwise=False):
""" """
Args: Args:
jsonfile: Evaluation json file, eg: bbox.json, mask.json. jsonfile (str): Evaluation json file, eg: bbox.json, mask.json.
style: COCOeval style, can be `bbox` , `segm` and `proposal`. style (str): COCOeval style, can be `bbox` , `segm` and `proposal`.
coco_gt: Whether to load COCOAPI through anno_file, coco_gt (str): Whether to load COCOAPI through anno_file,
eg: coco_gt = COCO(anno_file) eg: coco_gt = COCO(anno_file)
anno_file: COCO annotations file. anno_file (str): COCO annotations file.
max_dets: COCO evaluation maxDets. max_dets (tuple): COCO evaluation maxDets.
classwise: whether per-category AP and draw P-R Curve or not. classwise (bool): Whether per-category AP and draw P-R Curve or not.
""" """
assert coco_gt != None or anno_file != None assert coco_gt != None or anno_file != None
from pycocotools.coco import COCO from pycocotools.coco import COCO
...@@ -142,9 +142,7 @@ def cocoapi_eval(jsonfile, ...@@ -142,9 +142,7 @@ def cocoapi_eval(jsonfile,
return coco_eval.stats return coco_eval.stats
def json_eval_results(metric: object, def json_eval_results(metric, json_directory, dataset):
json_directory: object=None,
dataset: object=None) -> object:
""" """
cocoapi eval with already exists proposal.json, bbox.json or mask.json cocoapi eval with already exists proposal.json, bbox.json or mask.json
""" """
......
ppdet/metrics/map_utils.py
浏览文件 @ a09fe2c1
...@@ -101,19 +101,20 @@ class DetectionMAP(object): ...@@ -101,19 +101,20 @@ class DetectionMAP(object):
Currently support two types: 11point and integral Currently support two types: 11point and integral
Args: Args:
class_num (int): the class number. class_num (int): The class number.
overlap_thresh (float): The threshold of overlap overlap_thresh (float): The threshold of overlap
ratio between prediction bounding box and ratio between prediction bounding box and
ground truth bounding box for deciding ground truth bounding box for deciding
true/false positive. Default 0.5. true/false positive. Default 0.5.
map_type (str): calculation method of mean average map_type (str): Calculation method of mean average
precision, currently support '11point' and precision, currently support '11point' and
'integral'. Default '11point'. 'integral'. Default '11point'.
is_bbox_normalized (bool): whther bounding boxes is_bbox_normalized (bool): Whether bounding boxes
is normalized to range[0, 1]. Default False. is normalized to range[0, 1]. Default False.
evaluate_difficult (bool): whether to evaluate evaluate_difficult (bool): Whether to evaluate
difficult bounding boxes. Default False. difficult bounding boxes. Default False.
classwise (bool): whether per-category AP and draw catid2name (dict): Mapping between category id and category name.
classwise (bool): Whether per-category AP and draw
P-R Curve or not. P-R Curve or not.
""" """
......
ppdet/modeling/architectures/cascade_rcnn.py
浏览文件 @ a09fe2c1
...@@ -25,6 +25,18 @@ __all__ = ['CascadeRCNN'] ...@@ -25,6 +25,18 @@ __all__ = ['CascadeRCNN']
@register @register
class CascadeRCNN(BaseArch): class CascadeRCNN(BaseArch):
"""
Cascade R-CNN network, see https://arxiv.org/abs/1712.00726
Args:
backbone (object): backbone instance
rpn_head (object): `RPNHead` instance
bbox_head (object): `BBoxHead` instance
bbox_post_process (object): `BBoxPostProcess` instance
neck (object): 'FPN' instance
mask_head (object): `MaskHead` instance
mask_post_process (object): `MaskPostProcess` instance
"""
__category__ = 'architecture' __category__ = 'architecture'
__inject__ = [ __inject__ = [
'bbox_post_process', 'bbox_post_process',
......
ppdet/modeling/architectures/faster_rcnn.py
浏览文件 @ a09fe2c1
...@@ -25,6 +25,16 @@ __all__ = ['FasterRCNN'] ...@@ -25,6 +25,16 @@ __all__ = ['FasterRCNN']
@register @register
class FasterRCNN(BaseArch): class FasterRCNN(BaseArch):
"""
Faster R-CNN network, see https://arxiv.org/abs/1506.01497
Args:
backbone (object): backbone instance
rpn_head (object): `RPNHead` instance
bbox_head (object): `BBoxHead` instance
bbox_post_process (object): `BBoxPostProcess` instance
neck (object): 'FPN' instance
"""
__category__ = 'architecture' __category__ = 'architecture'
__inject__ = ['bbox_post_process'] __inject__ = ['bbox_post_process']
...@@ -34,13 +44,6 @@ class FasterRCNN(BaseArch): ...@@ -34,13 +44,6 @@ class FasterRCNN(BaseArch):
bbox_head, bbox_head,
bbox_post_process, bbox_post_process,
neck=None): neck=None):
"""
backbone (nn.Layer): backbone instance.
rpn_head (nn.Layer): generates proposals using backbone features.
bbox_head (nn.Layer): a head that performs per-region computation.
mask_head (nn.Layer): generates mask from bbox and backbone features.
"""
super(FasterRCNN, self).__init__() super(FasterRCNN, self).__init__()
self.backbone = backbone self.backbone = backbone
self.neck = neck self.neck = neck
......
ppdet/modeling/architectures/mask_rcnn.py
浏览文件 @ a09fe2c1
...@@ -25,6 +25,19 @@ __all__ = ['MaskRCNN'] ...@@ -25,6 +25,19 @@ __all__ = ['MaskRCNN']
@register @register
class MaskRCNN(BaseArch): class MaskRCNN(BaseArch):
"""
Mask R-CNN network, see https://arxiv.org/abs/1703.06870
Args:
backbone (object): backbone instance
rpn_head (object): `RPNHead` instance
bbox_head (object): `BBoxHead` instance
mask_head (object): `MaskHead` instance
bbox_post_process (object): `BBoxPostProcess` instance
mask_post_process (object): `MaskPostProcess` instance
neck (object): 'FPN' instance
"""
__category__ = 'architecture' __category__ = 'architecture'
__inject__ = [ __inject__ = [
'bbox_post_process', 'bbox_post_process',
...@@ -39,12 +52,6 @@ class MaskRCNN(BaseArch): ...@@ -39,12 +52,6 @@ class MaskRCNN(BaseArch):
bbox_post_process, bbox_post_process,
mask_post_process, mask_post_process,
neck=None): neck=None):
"""
backbone (nn.Layer): backbone instance.
rpn_head (nn.Layer): generates proposals using backbone features.
bbox_head (nn.Layer): a head that performs per-region computation.
mask_head (nn.Layer): generates mask from bbox and backbone features.
"""
super(MaskRCNN, self).__init__() super(MaskRCNN, self).__init__()
self.backbone = backbone self.backbone = backbone
self.neck = neck self.neck = neck
......
ppdet/modeling/backbones/hrnet.py
浏览文件 @ a09fe2c1
...@@ -97,7 +97,12 @@ class ConvNormLayer(nn.Layer): ...@@ -97,7 +97,12 @@ class ConvNormLayer(nn.Layer):
class Layer1(nn.Layer): class Layer1(nn.Layer):
def __init__(self, num_channels, has_se=False, freeze_norm=True, name=None): def __init__(self,
num_channels,
has_se=False,
norm_decay=0.,
freeze_norm=True,
name=None):
super(Layer1, self).__init__() super(Layer1, self).__init__()
self.bottleneck_block_list = [] self.bottleneck_block_list = []
...@@ -111,6 +116,7 @@ class Layer1(nn.Layer): ...@@ -111,6 +116,7 @@ class Layer1(nn.Layer):
has_se=has_se, has_se=has_se,
stride=1, stride=1,
downsample=True if i == 0 else False, downsample=True if i == 0 else False,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
name=name + '_' + str(i + 1))) name=name + '_' + str(i + 1)))
self.bottleneck_block_list.append(bottleneck_block) self.bottleneck_block_list.append(bottleneck_block)
...@@ -123,7 +129,12 @@ class Layer1(nn.Layer): ...@@ -123,7 +129,12 @@ class Layer1(nn.Layer):
class TransitionLayer(nn.Layer): class TransitionLayer(nn.Layer):
def __init__(self, in_channels, out_channels, freeze_norm=True, name=None): def __init__(self,
in_channels,
out_channels,
norm_decay=0.,
freeze_norm=True,
name=None):
super(TransitionLayer, self).__init__() super(TransitionLayer, self).__init__()
num_in = len(in_channels) num_in = len(in_channels)
...@@ -140,6 +151,7 @@ class TransitionLayer(nn.Layer): ...@@ -140,6 +151,7 @@ class TransitionLayer(nn.Layer):
ch_in=in_channels[i], ch_in=in_channels[i],
ch_out=out_channels[i], ch_out=out_channels[i],
filter_size=3, filter_size=3,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
act='relu', act='relu',
name=name + '_layer_' + str(i + 1))) name=name + '_layer_' + str(i + 1)))
...@@ -151,6 +163,7 @@ class TransitionLayer(nn.Layer): ...@@ -151,6 +163,7 @@ class TransitionLayer(nn.Layer):
ch_out=out_channels[i], ch_out=out_channels[i],
filter_size=3, filter_size=3,
stride=2, stride=2,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
act='relu', act='relu',
name=name + '_layer_' + str(i + 1))) name=name + '_layer_' + str(i + 1)))
...@@ -175,6 +188,7 @@ class Branches(nn.Layer): ...@@ -175,6 +188,7 @@ class Branches(nn.Layer):
in_channels, in_channels,
out_channels, out_channels,
has_se=False, has_se=False,
norm_decay=0.,
freeze_norm=True, freeze_norm=True,
name=None): name=None):
super(Branches, self).__init__() super(Branches, self).__init__()
...@@ -190,6 +204,7 @@ class Branches(nn.Layer): ...@@ -190,6 +204,7 @@ class Branches(nn.Layer):
num_channels=in_ch, num_channels=in_ch,
num_filters=out_channels[i], num_filters=out_channels[i],
has_se=has_se, has_se=has_se,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
name=name + '_branch_layer_' + str(i + 1) + '_' + name=name + '_branch_layer_' + str(i + 1) + '_' +
str(j + 1))) str(j + 1)))
...@@ -213,6 +228,7 @@ class BottleneckBlock(nn.Layer): ...@@ -213,6 +228,7 @@ class BottleneckBlock(nn.Layer):
has_se, has_se,
stride=1, stride=1,
downsample=False, downsample=False,
norm_decay=0.,
freeze_norm=True, freeze_norm=True,
name=None): name=None):
super(BottleneckBlock, self).__init__() super(BottleneckBlock, self).__init__()
...@@ -224,6 +240,7 @@ class BottleneckBlock(nn.Layer): ...@@ -224,6 +240,7 @@ class BottleneckBlock(nn.Layer):
ch_in=num_channels, ch_in=num_channels,
ch_out=num_filters, ch_out=num_filters,
filter_size=1, filter_size=1,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
act="relu", act="relu",
name=name + "_conv1") name=name + "_conv1")
...@@ -232,6 +249,7 @@ class BottleneckBlock(nn.Layer): ...@@ -232,6 +249,7 @@ class BottleneckBlock(nn.Layer):
ch_out=num_filters, ch_out=num_filters,
filter_size=3, filter_size=3,
stride=stride, stride=stride,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
act="relu", act="relu",
name=name + "_conv2") name=name + "_conv2")
...@@ -239,6 +257,7 @@ class BottleneckBlock(nn.Layer): ...@@ -239,6 +257,7 @@ class BottleneckBlock(nn.Layer):
ch_in=num_filters, ch_in=num_filters,
ch_out=num_filters * 4, ch_out=num_filters * 4,
filter_size=1, filter_size=1,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
act=None, act=None,
name=name + "_conv3") name=name + "_conv3")
...@@ -248,6 +267,7 @@ class BottleneckBlock(nn.Layer): ...@@ -248,6 +267,7 @@ class BottleneckBlock(nn.Layer):
ch_in=num_channels, ch_in=num_channels,
ch_out=num_filters * 4, ch_out=num_filters * 4,
filter_size=1, filter_size=1,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
act=None, act=None,
name=name + "_downsample") name=name + "_downsample")
...@@ -283,6 +303,7 @@ class BasicBlock(nn.Layer): ...@@ -283,6 +303,7 @@ class BasicBlock(nn.Layer):
stride=1, stride=1,
has_se=False, has_se=False,
downsample=False, downsample=False,
norm_decay=0.,
freeze_norm=True, freeze_norm=True,
name=None): name=None):
super(BasicBlock, self).__init__() super(BasicBlock, self).__init__()
...@@ -293,6 +314,7 @@ class BasicBlock(nn.Layer): ...@@ -293,6 +314,7 @@ class BasicBlock(nn.Layer):
ch_in=num_channels, ch_in=num_channels,
ch_out=num_filters, ch_out=num_filters,
filter_size=3, filter_size=3,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
stride=stride, stride=stride,
act="relu", act="relu",
...@@ -301,6 +323,7 @@ class BasicBlock(nn.Layer): ...@@ -301,6 +323,7 @@ class BasicBlock(nn.Layer):
ch_in=num_filters, ch_in=num_filters,
ch_out=num_filters, ch_out=num_filters,
filter_size=3, filter_size=3,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
stride=1, stride=1,
act=None, act=None,
...@@ -311,6 +334,7 @@ class BasicBlock(nn.Layer): ...@@ -311,6 +334,7 @@ class BasicBlock(nn.Layer):
ch_in=num_channels, ch_in=num_channels,
ch_out=num_filters * 4, ch_out=num_filters * 4,
filter_size=1, filter_size=1,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
act=None, act=None,
name=name + "_downsample") name=name + "_downsample")
...@@ -381,6 +405,7 @@ class Stage(nn.Layer): ...@@ -381,6 +405,7 @@ class Stage(nn.Layer):
num_modules, num_modules,
num_filters, num_filters,
has_se=False, has_se=False,
norm_decay=0.,
freeze_norm=True, freeze_norm=True,
multi_scale_output=True, multi_scale_output=True,
name=None): name=None):
...@@ -396,6 +421,7 @@ class Stage(nn.Layer): ...@@ -396,6 +421,7 @@ class Stage(nn.Layer):
num_channels=num_channels, num_channels=num_channels,
num_filters=num_filters, num_filters=num_filters,
has_se=has_se, has_se=has_se,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
multi_scale_output=False, multi_scale_output=False,
name=name + '_' + str(i + 1))) name=name + '_' + str(i + 1)))
...@@ -406,6 +432,7 @@ class Stage(nn.Layer): ...@@ -406,6 +432,7 @@ class Stage(nn.Layer):
num_channels=num_channels, num_channels=num_channels,
num_filters=num_filters, num_filters=num_filters,
has_se=has_se, has_se=has_se,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
name=name + '_' + str(i + 1))) name=name + '_' + str(i + 1)))
...@@ -424,6 +451,7 @@ class HighResolutionModule(nn.Layer): ...@@ -424,6 +451,7 @@ class HighResolutionModule(nn.Layer):
num_filters, num_filters,
has_se=False, has_se=False,
multi_scale_output=True, multi_scale_output=True,
norm_decay=0.,
freeze_norm=True, freeze_norm=True,
name=None): name=None):
super(HighResolutionModule, self).__init__() super(HighResolutionModule, self).__init__()
...@@ -432,6 +460,7 @@ class HighResolutionModule(nn.Layer): ...@@ -432,6 +460,7 @@ class HighResolutionModule(nn.Layer):
in_channels=num_channels, in_channels=num_channels,
out_channels=num_filters, out_channels=num_filters,
has_se=has_se, has_se=has_se,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
name=name) name=name)
...@@ -439,6 +468,7 @@ class HighResolutionModule(nn.Layer): ...@@ -439,6 +468,7 @@ class HighResolutionModule(nn.Layer):
in_channels=num_filters, in_channels=num_filters,
out_channels=num_filters, out_channels=num_filters,
multi_scale_output=multi_scale_output, multi_scale_output=multi_scale_output,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
name=name) name=name)
...@@ -453,6 +483,7 @@ class FuseLayers(nn.Layer): ...@@ -453,6 +483,7 @@ class FuseLayers(nn.Layer):
in_channels, in_channels,
out_channels, out_channels,
multi_scale_output=True, multi_scale_output=True,
norm_decay=0.,
freeze_norm=True, freeze_norm=True,
name=None): name=None):
super(FuseLayers, self).__init__() super(FuseLayers, self).__init__()
...@@ -473,6 +504,7 @@ class FuseLayers(nn.Layer): ...@@ -473,6 +504,7 @@ class FuseLayers(nn.Layer):
filter_size=1, filter_size=1,
stride=1, stride=1,
act=None, act=None,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
name=name + '_layer_' + str(i + 1) + '_' + name=name + '_layer_' + str(i + 1) + '_' +
str(j + 1))) str(j + 1)))
...@@ -489,6 +521,7 @@ class FuseLayers(nn.Layer): ...@@ -489,6 +521,7 @@ class FuseLayers(nn.Layer):
ch_out=out_channels[i], ch_out=out_channels[i],
filter_size=3, filter_size=3,
stride=2, stride=2,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
act=None, act=None,
name=name + '_layer_' + str(i + 1) + '_' + name=name + '_layer_' + str(i + 1) + '_' +
...@@ -503,6 +536,7 @@ class FuseLayers(nn.Layer): ...@@ -503,6 +536,7 @@ class FuseLayers(nn.Layer):
ch_out=out_channels[j], ch_out=out_channels[j],
filter_size=3, filter_size=3,
stride=2, stride=2,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
act="relu", act="relu",
name=name + '_layer_' + str(i + 1) + '_' + name=name + '_layer_' + str(i + 1) + '_' +
...@@ -544,6 +578,7 @@ class HRNet(nn.Layer): ...@@ -544,6 +578,7 @@ class HRNet(nn.Layer):
has_se (bool): whether to add SE block for each stage has_se (bool): whether to add SE block for each stage
freeze_at (int): the stage to freeze freeze_at (int): the stage to freeze
freeze_norm (bool): whether to freeze norm in HRNet freeze_norm (bool): whether to freeze norm in HRNet
norm_decay (float): weight decay for normalization layer weights
return_idx (List): the stage to return return_idx (List): the stage to return
""" """
...@@ -586,6 +621,7 @@ class HRNet(nn.Layer): ...@@ -586,6 +621,7 @@ class HRNet(nn.Layer):
ch_out=64, ch_out=64,
filter_size=3, filter_size=3,
stride=2, stride=2,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
act='relu', act='relu',
name="layer1_1") name="layer1_1")
...@@ -595,6 +631,7 @@ class HRNet(nn.Layer): ...@@ -595,6 +631,7 @@ class HRNet(nn.Layer):
ch_out=64, ch_out=64,
filter_size=3, filter_size=3,
stride=2, stride=2,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
act='relu', act='relu',
name="layer1_2") name="layer1_2")
...@@ -602,12 +639,14 @@ class HRNet(nn.Layer): ...@@ -602,12 +639,14 @@ class HRNet(nn.Layer):
self.la1 = Layer1( self.la1 = Layer1(
num_channels=64, num_channels=64,
has_se=has_se, has_se=has_se,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
name="layer2") name="layer2")
self.tr1 = TransitionLayer( self.tr1 = TransitionLayer(
in_channels=[256], in_channels=[256],
out_channels=channels_2, out_channels=channels_2,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
name="tr1") name="tr1")
...@@ -616,12 +655,14 @@ class HRNet(nn.Layer): ...@@ -616,12 +655,14 @@ class HRNet(nn.Layer):
num_modules=num_modules_2, num_modules=num_modules_2,
num_filters=channels_2, num_filters=channels_2,
has_se=self.has_se, has_se=self.has_se,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
name="st2") name="st2")
self.tr2 = TransitionLayer( self.tr2 = TransitionLayer(
in_channels=channels_2, in_channels=channels_2,
out_channels=channels_3, out_channels=channels_3,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
name="tr2") name="tr2")
...@@ -630,12 +671,14 @@ class HRNet(nn.Layer): ...@@ -630,12 +671,14 @@ class HRNet(nn.Layer):
num_modules=num_modules_3, num_modules=num_modules_3,
num_filters=channels_3, num_filters=channels_3,
has_se=self.has_se, has_se=self.has_se,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
name="st3") name="st3")
self.tr3 = TransitionLayer( self.tr3 = TransitionLayer(
in_channels=channels_3, in_channels=channels_3,
out_channels=channels_4, out_channels=channels_4,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
name="tr3") name="tr3")
self.st4 = Stage( self.st4 = Stage(
...@@ -643,6 +686,7 @@ class HRNet(nn.Layer): ...@@ -643,6 +686,7 @@ class HRNet(nn.Layer):
num_modules=num_modules_4, num_modules=num_modules_4,
num_filters=channels_4, num_filters=channels_4,
has_se=self.has_se, has_se=self.has_se,
norm_decay=norm_decay,
freeze_norm=freeze_norm, freeze_norm=freeze_norm,
name="st4") name="st4")
......
ppdet/modeling/necks/hrfpn.py
浏览文件 @ a09fe2c1
...@@ -30,8 +30,8 @@ class HRFPN(nn.Layer): ...@@ -30,8 +30,8 @@ class HRFPN(nn.Layer):
in_channels (list): number of input feature channels from backbone in_channels (list): number of input feature channels from backbone
out_channel (int): number of output feature channels out_channel (int): number of output feature channels
share_conv (bool): whether to share conv for different layers' reduction share_conv (bool): whether to share conv for different layers' reduction
spatial_scales (list): feature map scaling factor
extra_stage (int): add extra stage for returning HRFPN fpn_feats extra_stage (int): add extra stage for returning HRFPN fpn_feats
spatial_scales (list): feature map scaling factor
""" """
def __init__(self, def __init__(self,
......
ppdet/modeling/post_process.py
浏览文件 @ a09fe2c1
...@@ -24,6 +24,8 @@ try: ...@@ -24,6 +24,8 @@ try:
except Exception: except Exception:
from collections import Sequence from collections import Sequence
__all__ = ['BBoxPostProcess', 'MaskPostProcess', 'FCOSPostProcess']
@register @register
class BBoxPostProcess(object): class BBoxPostProcess(object):
...@@ -40,13 +42,17 @@ class BBoxPostProcess(object): ...@@ -40,13 +42,17 @@ class BBoxPostProcess(object):
""" """
Decode the bbox and do NMS if needed. Decode the bbox and do NMS if needed.
Args:
head_out (tuple): bbox_pred and cls_prob of bbox_head output.
rois (tuple): roi and rois_num of rpn_head output.
im_shape (Tensor): The shape of the input image.
scale_factor (Tensor): The scale factor of the input image.
Returns: Returns:
bbox_pred(Tensor): The output is the prediction with shape [N, 6] bbox_pred (Tensor): The output prediction with shape [N, 6], including
including labels, scores and bboxes. The size of labels, scores and bboxes. The size of bboxes are corresponding
bboxes are corresponding to the input image and to the input image, the bboxes may be used in other branch.
the bboxes may be used in other brunch. bbox_num (Tensor): The number of prediction boxes of each batch with
bbox_num(Tensor): The number of prediction of each batch with shape shape [1], and is N.
[N, 6].
""" """
if self.nms is not None: if self.nms is not None:
bboxes, score = self.decode(head_out, rois, im_shape, scale_factor) bboxes, score = self.decode(head_out, rois, im_shape, scale_factor)
...@@ -54,6 +60,9 @@ class BBoxPostProcess(object): ...@@ -54,6 +60,9 @@ class BBoxPostProcess(object):
else: else:
bbox_pred, bbox_num = self.decode(head_out, rois, im_shape, bbox_pred, bbox_num = self.decode(head_out, rois, im_shape,
scale_factor) scale_factor)
# Prevent empty bbox_pred from decode or NMS.
# Bboxes and score before NMS may be empty due to the score threshold.
if bbox_pred.shape[0] == 0: if bbox_pred.shape[0] == 0:
bbox_pred = paddle.to_tensor( bbox_pred = paddle.to_tensor(
np.array( np.array(
...@@ -64,16 +73,22 @@ class BBoxPostProcess(object): ...@@ -64,16 +73,22 @@ class BBoxPostProcess(object):
def get_pred(self, bboxes, bbox_num, im_shape, scale_factor): def get_pred(self, bboxes, bbox_num, im_shape, scale_factor):
""" """
Rescale, clip and filter the bbox from the output of NMS to Rescale, clip and filter the bbox from the output of NMS to
get final prediction. get final prediction.
Notes:
Currently only support bs = 1.
Args: Args:
bboxes(Tensor): The output of __call__ with shape [N, 6] bbox_pred (Tensor): The output bboxes with shape [N, 6] after decode
and NMS, including labels, scores and bboxes.
bbox_num (Tensor): The number of prediction boxes of each batch with
shape [1], and is N.
im_shape (Tensor): The shape of the input image.
scale_factor (Tensor): The scale factor of the input image.
Returns: Returns:
bbox_pred(Tensor): The output is the prediction with shape [N, 6] pred_result (Tensor): The final prediction results with shape [N, 6]
including labels, scores and bboxes. The size of including labels, scores and bboxes.
bboxes are corresponding to the original image.
""" """
origin_shape = paddle.floor(im_shape / scale_factor + 0.5) origin_shape = paddle.floor(im_shape / scale_factor + 0.5)
origin_shape_list = [] origin_shape_list = []
...@@ -125,7 +140,9 @@ class MaskPostProcess(object): ...@@ -125,7 +140,9 @@ class MaskPostProcess(object):
self.binary_thresh = binary_thresh self.binary_thresh = binary_thresh
def paste_mask(self, masks, boxes, im_h, im_w): def paste_mask(self, masks, boxes, im_h, im_w):
# paste each mask on image """
Paste the mask prediction to the original image.
"""
x0, y0, x1, y1 = paddle.split(boxes, 4, axis=1) x0, y0, x1, y1 = paddle.split(boxes, 4, axis=1)
masks = paddle.unsqueeze(masks, [0, 1]) masks = paddle.unsqueeze(masks, [0, 1])
img_y = paddle.arange(0, im_h, dtype='float32') + 0.5 img_y = paddle.arange(0, im_h, dtype='float32') + 0.5
...@@ -148,7 +165,19 @@ class MaskPostProcess(object): ...@@ -148,7 +165,19 @@ class MaskPostProcess(object):
def __call__(self, mask_out, bboxes, bbox_num, origin_shape): def __call__(self, mask_out, bboxes, bbox_num, origin_shape):
""" """
Paste the mask prediction to the original image. Decode the mask_out and paste the mask to the origin image.
Args:
mask_out (Tensor): mask_head output with shape [N, 28, 28].
bbox_pred (Tensor): The output bboxes with shape [N, 6] after decode
and NMS, including labels, scores and bboxes.
bbox_num (Tensor): The number of prediction boxes of each batch with
shape [1], and is N.
origin_shape (Tensor): The origin shape of the input image, the tensor
shape is [N, 2], and each row is [h, w].
Returns:
pred_result (Tensor): The final prediction mask results with shape
[N, h, w] in binary mask style.
""" """
num_mask = mask_out.shape[0] num_mask = mask_out.shape[0]
origin_shape = paddle.cast(origin_shape, 'int32') origin_shape = paddle.cast(origin_shape, 'int32')
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或