未验证 提交 c1f5c6d7 编写于 作者: Y YixinKristy 提交者: GitHub

Merge branch 'PaddlePaddle:develop' into develop

...@@ -37,16 +37,16 @@ PP-TinyPose是PaddleDetecion针对移动端设备优化的实时关键点检测 ...@@ -37,16 +37,16 @@ PP-TinyPose是PaddleDetecion针对移动端设备优化的实时关键点检测
### 关键点检测模型 ### 关键点检测模型
| 模型 | 输入尺寸 | AP (COCO Val) | 单人推理耗时 (FP32) | 单人推理耗时(FP16) | 配置文件 | 模型权重 | 预测部署模型 | Paddle-Lite部署模型(FP32) | Paddle-Lite部署模型(FP16) | | 模型 | 输入尺寸 | AP (COCO Val) | 单人推理耗时 (FP32) | 单人推理耗时(FP16) | 配置文件 | 模型权重 | 预测部署模型 | Paddle-Lite部署模型(FP32) | Paddle-Lite部署模型(FP16) |
| :---------- | :------: | :-----------: | :-----------------: | :-----------------: | :------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | | :---------- | :------: | :-----------: | :-----------------: | :-----------------: | :------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
| PP-TinyPose | 128*96 | 58.1 | 4.57ms | 3.27ms | [Config](./tinypose_128x96.yml) | [Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96.pdparams) | [预测部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96.tar) | [Lite部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96.tar) | [Lite部署模型(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96_fp16.tar) | | PP-TinyPose | 128*96 | 58.1 | 4.57ms | 3.27ms | [Config](./tinypose_128x96.yml) | [Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96.pdparams) | [预测部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96.tar) | [Lite部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96_lite.tar) | [Lite部署模型(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96_fp16_lite.tar) |
| PP-TinyPose | 256*192 | 68.8 | 14.07ms | 8.33ms | [Config](./tinypose_256x192.yml) | [Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192.pdparams) | [预测部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192.tar) | [Lite部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192.tar) | [Lite部署模型(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192_fp16.tar) | | PP-TinyPose | 256*192 | 68.8 | 14.07ms | 8.33ms | [Config](./tinypose_256x192.yml) | [Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192.pdparams) | [预测部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192.tar) | [Lite部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192_lite.tar) | [Lite部署模型(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192_fp16_lite.tar) |
### 行人检测模型 ### 行人检测模型
| 模型 | 输入尺寸 | mAP (COCO Val) | 平均推理耗时 (FP32) | 平均推理耗时 (FP16) | 配置文件 | 模型权重 | 预测部署模型 | Paddle-Lite部署模型(FP32) | Paddle-Lite部署模型(FP16) | | 模型 | 输入尺寸 | mAP (COCO Val) | 平均推理耗时 (FP32) | 平均推理耗时 (FP16) | 配置文件 | 模型权重 | 预测部署模型 | Paddle-Lite部署模型(FP32) | Paddle-Lite部署模型(FP16) |
| :------------------- | :------: | :------------: | :-----------------: | :-----------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | | :------------------- | :------: | :------------: | :-----------------: | :-----------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
| PicoDet-S-Pedestrian | 192*192 | 29.0 | 4.30ms | 2.37ms | [Config](../../picodet/application/pedestrian_detection/picodet_s_192_pedestrian.yml) | [Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian.pdparams) | [预测部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian.tar) | [Lite部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian.tar) | [Lite部署模型(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian_fp16.tar) | | PicoDet-S-Pedestrian | 192*192 | 29.0 | 4.30ms | 2.37ms | [Config](../../picodet/application/pedestrian_detection/picodet_s_192_pedestrian.yml) | [Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian.pdparams) | [预测部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian.tar) | [Lite部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian_lite.tar) | [Lite部署模型(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian_fp16_lite.tar) |
| PicoDet-S-Pedestrian | 320*320 | 38.5 | 10.26ms | 6.30ms | [Config](../../picodet/application/pedestrian_detection/picodet_s_320_pedestrian.yml) | [Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian.pdparams) | [预测部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian.tar) | [Lite部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian.tar) | [Lite部署模型(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian_fp16.tar) | | PicoDet-S-Pedestrian | 320*320 | 38.5 | 10.26ms | 6.30ms | [Config](../../picodet/application/pedestrian_detection/picodet_s_320_pedestrian.yml) | [Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian.pdparams) | [预测部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian.tar) | [Lite部署模型](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian_lite.tar) | [Lite部署模型(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian_fp16_lite.tar) |
......
...@@ -37,14 +37,14 @@ If you want to deploy it on the mobile devives, you also need: ...@@ -37,14 +37,14 @@ If you want to deploy it on the mobile devives, you also need:
### Keypoint Detection Model ### Keypoint Detection Model
| Model | Input Size | AP (COCO Val) | Inference Time for Single Person (FP32)| Inference Time for Single Person(FP16) | Config | Model Weights | Deployment Model | Paddle-Lite Model(FP32) | Paddle-Lite Model(FP16)| | Model | Input Size | AP (COCO Val) | Inference Time for Single Person (FP32)| Inference Time for Single Person(FP16) | Config | Model Weights | Deployment Model | Paddle-Lite Model(FP32) | Paddle-Lite Model(FP16)|
| :------------------------ | :-------: | :------: | :------: |:---: | :---: | :---: | :---: | :---: | :---: | | :------------------------ | :-------: | :------: | :------: |:---: | :---: | :---: | :---: | :---: | :---: |
| PP-TinyPose | 128*96 | 58.1 | 4.57ms | 3.27ms | [Config](./tinypose_128x96.yml) |[Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96.pdparams) | [Deployment Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96.tar) | [Lite Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96.tar) | [Lite Model(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96_fp16.tar) | | PP-TinyPose | 128*96 | 58.1 | 4.57ms | 3.27ms | [Config](./tinypose_128x96.yml) |[Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96.pdparams) | [Deployment Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96.tar) | [Lite Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96_lite.tar) | [Lite Model(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96_fp16_lite.tar) |
| PP-TinyPose | 256*192 | 68.8 | 14.07ms | 8.33ms | [Config](./tinypose_256x192.yml) | [Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192.pdparams) | [Deployment Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192.tar) | [Lite Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192.tar) | [Lite Model(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192_fp16.tar) | | PP-TinyPose | 256*192 | 68.8 | 14.07ms | 8.33ms | [Config](./tinypose_256x192.yml) | [Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192.pdparams) | [Deployment Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192.tar) | [Lite Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192_lite.tar) | [Lite Model(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_256x192_fp16_lite.tar) |
### Pedestrian Detection Model ### Pedestrian Detection Model
| Model | Input Size | mAP (COCO Val) | Average Inference Time (FP32)| Average Inference Time (FP16) | Config | Model Weights | Deployment Model | Paddle-Lite Model(FP32) | Paddle-Lite Model(FP16)| | Model | Input Size | mAP (COCO Val) | Average Inference Time (FP32)| Average Inference Time (FP16) | Config | Model Weights | Deployment Model | Paddle-Lite Model(FP32) | Paddle-Lite Model(FP16)|
| :------------------------ | :-------: | :------: | :------: | :---: | :---: | :---: | :---: | :---: | :---: | | :------------------------ | :-------: | :------: | :------: | :---: | :---: | :---: | :---: | :---: | :---: |
| PicoDet-S-Pedestrian | 192*192 | 29.0 | 4.30ms | 2.37ms | [Config](../../picodet/application/pedestrian_detection/picodet_s_192_pedestrian.yml) |[Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian.pdparams) | [Deployment Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian.tar) | [Lite Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian.tar) | [Lite Model(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian_fp16.tar) | | PicoDet-S-Pedestrian | 192*192 | 29.0 | 4.30ms | 2.37ms | [Config](../../picodet/application/pedestrian_detection/picodet_s_192_pedestrian.yml) |[Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian.pdparams) | [Deployment Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian.tar) | [Lite Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian_lite.tar) | [Lite Model(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_192_pedestrian_fp16_lite.tar) |
| PicoDet-S-Pedestrian | 320*320 | 38.5 | 10.26ms | 6.30ms | [Config](../../picodet/application/pedestrian_detection/picodet_s_320_pedestrian.yml) | [Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian.pdparams) | [Deployment Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian.tar) | [Lite Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian.tar) | [Lite Model(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian_fp16.tar) | | PicoDet-S-Pedestrian | 320*320 | 38.5 | 10.26ms | 6.30ms | [Config](../../picodet/application/pedestrian_detection/picodet_s_320_pedestrian.yml) | [Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian.pdparams) | [Deployment Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian.tar) | [Lite Model](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian_lite.tar) | [Lite Model(FP16)](https://bj.bcebos.com/v1/paddledet/models/keypoint/picodet_s_320_pedestrian_fp16_lite.tar) |
**Tips** **Tips**
......
...@@ -75,7 +75,7 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyoloe/ppyoloe_crn_l_30 ...@@ -75,7 +75,7 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyoloe/ppyoloe_crn_l_30
### 4. Deployment ### 4. Deployment
- PaddleInference [Python](../../deploy/python) & [C++](../../deploy/cpp) - Paddle Inference [Python](../../deploy/python) & [C++](../../deploy/cpp)
- [Paddle-TensorRT](../../deploy/TENSOR_RT.md) - [Paddle-TensorRT](../../deploy/TENSOR_RT.md)
- [Paddle2ONNX](https://github.com/PaddlePaddle/Paddle2ONNX) - [Paddle2ONNX](https://github.com/PaddlePaddle/Paddle2ONNX)
- [PaddleServing](https://github.com/PaddlePaddle/Serving) - [PaddleServing](https://github.com/PaddlePaddle/Serving)
...@@ -86,16 +86,16 @@ For deployment on GPU or benchmarked, model should be first exported to inferenc ...@@ -86,16 +86,16 @@ For deployment on GPU or benchmarked, model should be first exported to inferenc
Exporting PP-YOLOE for Paddle Inference **without TensorRT**, use following command. Exporting PP-YOLOE for Paddle Inference **without TensorRT**, use following command.
```bash ```bash
python tools/export_model.py configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams
``` ```
Exporting PP-YOLOE for Paddle Inference **with TensorRT** for better performance, use following command with extra `-o trt=True` setting. Exporting PP-YOLOE for Paddle Inference **with TensorRT** for better performance, use following command with extra `-o trt=True` setting.
```bash ```bash
python tools/export_model.py configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams trt=True python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams trt=True
``` ```
`deploy/python/infer.py` is used to load exported paddle inference model above for inference and benchmark through PaddleInference. `deploy/python/infer.py` is used to load exported paddle inference model above for inference and benchmark through Paddle Inference.
```bash ```bash
# inference single image # inference single image
......
...@@ -76,7 +76,7 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyoloe/ppyoloe_crn_l_30 ...@@ -76,7 +76,7 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyoloe/ppyoloe_crn_l_30
### 4. 部署 ### 4. 部署
- PaddleInference [Python](../../deploy/python) & [C++](../../deploy/cpp) - Paddle Inference [Python](../../deploy/python) & [C++](../../deploy/cpp)
- [Paddle-TensorRT](../../deploy/TENSOR_RT.md) - [Paddle-TensorRT](../../deploy/TENSOR_RT.md)
- [Paddle2ONNX](https://github.com/PaddlePaddle/Paddle2ONNX) - [Paddle2ONNX](https://github.com/PaddlePaddle/Paddle2ONNX)
- [PaddleServing](https://github.com/PaddlePaddle/Serving) - [PaddleServing](https://github.com/PaddlePaddle/Serving)
...@@ -84,19 +84,19 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyoloe/ppyoloe_crn_l_30 ...@@ -84,19 +84,19 @@ CUDA_VISIBLE_DEVICES=0 python tools/infer.py -c configs/ppyoloe/ppyoloe_crn_l_30
PP-YOLOE在GPU上部署或者推理benchmark需要通过`tools/export_model.py`导出模型。 PP-YOLOE在GPU上部署或者推理benchmark需要通过`tools/export_model.py`导出模型。
当你使用PaddleInferenced但不使用TensorRT时,运行以下的命令进行导出 当你使用Paddle Inference但不使用TensorRT时,运行以下的命令进行导出
```bash ```bash
python tools/export_model.py configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams
``` ```
当你使用PaddleInference的TensorRT时,需要指定`-o trt=True`进行导出 当你使用Paddle Inference的TensorRT时,需要指定`-o trt=True`进行导出
```bash ```bash
python tools/export_model.py configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams trt=True python tools/export_model.py -c configs/ppyoloe/ppyoloe_crn_l_300e_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/ppyoloe_crn_l_300e_coco.pdparams trt=True
``` ```
`deploy/python/infer.py`使用上述导出后的PaddleInference模型用于推理和benchnark. `deploy/python/infer.py`使用上述导出后的Paddle Inference模型用于推理和benchnark.
```bash ```bash
# 推理单张图片 # 推理单张图片
......
Markdown is supported
0% .
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