apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-11-03 11:02:01 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

[Doc]Fix doc error (#539)

Browse Source 
* 修正RKPicodet文档

* 修正yolov5文档模型大小的错误
This commit is contained in:
Zheng_Bicheng
2022-11-09 13:57:02 +08:00
committed by GitHub
parent a37c043979
commit ad04a4377c
2 changed files with 13 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
examples/vision/detection/paddledetection/rknpu2/README.md
View File

@@ -15,23 +15,23 @@ RKNPU部署模型前需要将Paddle模型转换成RKNN模型，具体步骤如
## 模型转换example
下面以Picodet-npu为例子,教大家如何转换PaddleDetection模型到RKNN模型。
```bash
## 下载Paddle静态图模型并解压
wget https://bj.bcebos.com/fastdeploy/models/rknn2/picodet_s_416_coco_npu.zip
unzip -qo picodet_s_416_coco_npu.zip
# 下载Paddle静态图模型并解压
wget https://paddledet.bj.bcebos.com/deploy/Inference/picodet_s_416_coco_lcnet.tar
tar xvf picodet_s_416_coco_lcnet.zip
# 静态图转ONNX模型，注意，这里的save_file请和压缩包名对齐
paddle2onnx --model_dir picodet_s_416_coco_npu \
paddle2onnx --model_dir picodet_s_416_coco_lcnet \
--model_filename model.pdmodel \
--params_filename model.pdiparams \
--save_file picodet_s_416_coco_npu/picodet_s_416_coco_npu.onnx \
--save_file picodet_s_416_coco_lcnet/picodet_s_416_coco_lcnet.onnx \
--enable_dev_version True
python -m paddle2onnx.optimize --input_model picodet_s_416_coco_npu/picodet_s_416_coco_npu.onnx \
--output_model picodet_s_416_coco_npu/picodet_s_416_coco_npu.onnx \
python -m paddle2onnx.optimize --input_model picodet_s_416_coco_lcnet/picodet_s_416_coco_lcnet.onnx \
--output_model picodet_s_416_coco_lcnet/picodet_s_416_coco_lcnet.onnx \
--input_shape_dict "{'image':[1,3,416,416]}"
# ONNX模型转RKNN模型
# 转换模型,模型将生成在picodet_s_320_coco_lcnet_non_postprocess目录下
python tools/rknpu2/export.py --config_path tools/rknpu2/config/RK3588/picodet_s_416_coco_npu.yaml
python tools/rknpu2/export.py --config_path tools/rknpu2/config/RK3588/picodet_s_416_coco_lcnet.yaml
```
- [Python部署](./python)

10
examples/vision/detection/yolov5/README.md
View File

@@ -10,11 +10,11 @@
为了方便开发者的测试，下面提供了YOLOv5导出的各系列模型，开发者可直接下载使用。（下表中模型的精度来源于源官方库）
| 模型 | 大小 | 精度 |
|:---------------------------------------------------------------- |:----- |:----- |
| [YOLOv5n](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5n.onnx) | 1.9MB | 28.4% |
| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s.onnx) | 7.2MB | 37.2% |
| [YOLOv5m](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5m.onnx) | 21.2MB | 45.2% |
| [YOLOv5l](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5l.onnx) | 46.5MB | 48.8% |
| [YOLOv5x](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5x.onnx) | 86.7MB | 50.7% |
| [YOLOv5n](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5n.onnx) | 7.5MB | 28.4% |
| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s.onnx) | 28.9MB | 37.2% |
| [YOLOv5m](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5m.onnx) | 84.7MB | 45.2% |
| [YOLOv5l](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5l.onnx) | 186.2MB | 48.8% |
| [YOLOv5x](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5x.onnx) | 346.9MB | 50.7% |