mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-06 17:17:14 +08:00
CoolCola
@@ -118,4 +118,4 @@ tar -xf PaddleLite-generic-demo.tar.gz
|
||||
|
||||
3. A311D 上部署 YOLOv5 检测模型请参考：[YOLOv5 检测模型在 A311D 上的 C++ 部署示例](../../../examples/vision/detection/yolov5/a311d/README.md)
|
||||
|
||||
4. A311D 上部署 PP-LiteSeg 分割模型请参考：[PP-LiteSeg 分割模型在 A311D 上的 C++ 部署示例](../../../examples/vision/segmentation/paddleseg/a311d/README.md)
|
||||
4. A311D 上部署 PP-LiteSeg 分割模型请参考：[PP-LiteSeg 分割模型在 A311D 上的 C++ 部署示例](../../../examples/vision/segmentation/paddleseg/amlogic/a311d/README.md)
|
||||
|
||||
@@ -118,4 +118,4 @@ tar -xf PaddleLite-generic-demo.tar.gz
|
||||
|
||||
3. RV1126 上部署 YOLOv5 检测模型请参考：[YOLOv5 检测模型在 RV1126 上的 C++ 部署示例](../../../examples/vision/detection/yolov5/rv1126/README.md)
|
||||
|
||||
4. RV1126 上部署 PP-LiteSeg 分割模型请参考：[PP-LiteSeg 分割模型在 RV1126 上的 C++ 部署示例](../../../examples/vision/segmentation/paddleseg/rv1126/README.md)
|
||||
4. RV1126 上部署 PP-LiteSeg 分割模型请参考：[PP-LiteSeg 分割模型在 RV1126 上的 C++ 部署示例](../../../examples/vision/segmentation/paddleseg/rockchip/rv1126/README.md)
|
||||
|
||||
@@ -25,9 +25,9 @@ FastDeploy在RK3588s上进行了测试，测试环境如下:
|
||||
| Detection | [RKYOLOV5](../../../../examples/vision/detection/rkyolo/README.md) | YOLOV5-S-Relu(int8) | 是 | 57 |
|
||||
| Detection | [RKYOLOX](../../../../examples/vision/detection/rkyolo/README.md) | yolox-s | 是 | 130 |
|
||||
| Detection | [RKYOLOV7](../../../../examples/vision/detection/rkyolo/README.md) | yolov7-tiny | 是 | 58 |
|
||||
| Segmentation | [Unet](../../../../examples/vision/segmentation/paddleseg/rknpu2/README.md) | Unet-cityscapes | 否 | - |
|
||||
| Segmentation | [PP-HumanSegV2Lite](../../../../examples/vision/segmentation/paddleseg/rknpu2/README.md) | portrait(int8) | 是 | 43 |
|
||||
| Segmentation | [PP-HumanSegV2Lite](../../../../examples/vision/segmentation/paddleseg/rknpu2/README.md) | human(int8) | 是 | 43 |
|
||||
| Segmentation | [Unet](../../../../examples/vision/segmentation/paddleseg/rockchip/rknpu2/README.md) | Unet-cityscapes | 否 | - |
|
||||
| Segmentation | [PP-HumanSegV2Lite](../../../../examples/vision/segmentation/paddleseg/rockchip/rknpu2/README.md) | portrait(int8) | 是 | 43 |
|
||||
| Segmentation | [PP-HumanSegV2Lite](../../../../examples/vision/segmentation/paddleseg/rockchip/rknpu2/README.md) | human(int8) | 是 | 43 |
|
||||
| Face Detection | [SCRFD](../../../../examples/vision/facedet/scrfd/rknpu2/README.md) | SCRFD-2.5G-kps-640(int8) | 是 | 42 |
|
||||
| Face FaceRecognition | [InsightFace](../../../../examples/vision/faceid/insightface/rknpu2/README_CN.md) | ms1mv3_arcface_r18(int8) | 是 | 12 |
|
||||
|
||||
|
||||
@@ -105,4 +105,4 @@ For more details, please refer to: [Paddle Lite prepares the device environment]
|
||||
|
||||
3. For deploying YOLOv5 detection model on A311D, please refer to: [C++ Deployment Example of YOLOv5 Detection Model on A311D](../../../examples/vision/detection/yolov5/a311d/README.md)
|
||||
|
||||
4. For deploying PP-LiteSeg segmentation model on A311D, please refer to: [C++ Deployment Example of PP-LiteSeg Segmentation Model on A311D](../../../examples/vision/segmentation/paddleseg/a311d/README.md)
|
||||
4. For deploying PP-LiteSeg segmentation model on A311D, please refer to: [C++ Deployment Example of PP-LiteSeg Segmentation Model on A311D](../../../examples/vision/segmentation/paddleseg/amlogic/a311d/README.md)
|
||||
|
||||
@@ -105,4 +105,4 @@ For more details, please refer to: [Paddle Lite prepares the device environment]
|
||||
|
||||
3. For deploying YOLOv5 detection model on RV1126, please refer to: [C++ Deployment Example of YOLOv5 Detection Model on RV1126](../../../examples/vision/detection/yolov5/rv1126/README.md)
|
||||
|
||||
4. For deploying PP-LiteSeg segmentation model on RV1126, please refer to: [C++ Deployment Example of PP-LiteSeg Segmentation Model on RV1126](../../../examples/vision/segmentation/paddleseg/rv1126/README.md)
|
||||
4. For deploying PP-LiteSeg segmentation model on RV1126, please refer to: [C++ Deployment Example of PP-LiteSeg Segmentation Model on RV1126](../../../examples/vision/segmentation/paddleseg/rockchip/rv1126/README.md)
|
||||
|
||||
@@ -35,7 +35,7 @@ sudo ./infer_tinypose_demo ./PP_TinyPose_256x192_infer ./hrnet_demo.jpg
|
||||
</div>
|
||||
|
||||
以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
|
||||
- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
|
||||
- [如何在Windows中使用FastDeploy C++ SDK](../../../../../../docs/cn/faq/use_sdk_on_windows.md)
|
||||
|
||||
## PP-TinyPose C++接口
|
||||
|
||||
@@ -79,5 +79,5 @@ PPTinyPose模型加载和初始化，其中model_file为导出的Paddle模型格
|
||||
|
||||
- [模型介绍](../../../)
|
||||
- [Python部署](../../python)
|
||||
- [视觉模型预测结果](../../../../../../docs/api/vision_results/)
|
||||
- [视觉模型预测结果](../../../../../../../docs/api/vision_results/)
|
||||
- [如何切换模型推理后端引擎](../../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
|
||||
@@ -53,7 +53,7 @@ PP-TinyPose模型加载和初始化，其中model_file, params_file以及config_
|
||||
|
||||
> **返回**
|
||||
>
|
||||
> > 返回`fastdeploy.vision.KeyPointDetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
|
||||
> > 返回`fastdeploy.vision.KeyPointDetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../../docs/api/vision_results/)
|
||||
|
||||
### 类成员属性
|
||||
#### 后处理参数
|
||||
@@ -66,5 +66,5 @@ PP-TinyPose模型加载和初始化，其中model_file, params_file以及config_
|
||||
|
||||
- [PP-TinyPose 模型介绍](..)
|
||||
- [PP-TinyPose C++部署](../cpp)
|
||||
- [模型预测结果说明](../../../../../docs/api/vision_results/)
|
||||
- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
- [模型预测结果说明](../../../../../../docs/api/vision_results/)
|
||||
- [如何切换模型推理后端引擎](../../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
PaddleSeg Matting deployment examples, please refer to [document](../../segmentation/ppmatting/README_CN.md).
|
||||
PaddleSeg Matting deployment examples, please refer to [document](../../segmentation/ppmatting/README.md).
|
||||
|
||||
PaddleSeg Matting的部署示例，请参考[文档](../../segmentation/ppmatting/README_CN.md).
|
||||
PaddleSeg Matting的部署示例，请参考[文档](../../segmentation/ppmatting/README.md).
|
||||
|
||||
@@ -40,7 +40,7 @@ wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_
|
||||
```
|
||||
|
||||
The above command works for Linux or MacOS. For SDK in Windows, refer to:
|
||||
- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
|
||||
- [How to use FastDeploy C++ SDK in Windows](../../../../../../docs/cn/faq/use_sdk_on_windows.md)
|
||||
|
||||
The visualized result after running is as follows
|
||||
|
||||
|
||||
@@ -8,8 +8,8 @@
|
||||
软硬件环境满足要求，以及交叉编译环境的准备，请参考：[FastDeploy](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install#自行编译安装)
|
||||
|
||||
### 模型准备
|
||||
1. 用户可以直接使用由[FastDeploy 提供的量化模型](../README_CN.md#晶晨a311d支持的paddleseg模型)进行部署。
|
||||
2. 若FastDeploy没有提供满足要求的量化模型，用户可以参考[PaddleSeg动态图模型导出为A311D支持的INT8模型](../README_CN.md#paddleseg动态图模型导出为a311d支持的int8模型)自行导出或训练量化模型
|
||||
1. 用户可以直接使用由[FastDeploy 提供的量化模型](../README.md#晶晨a311d支持的paddleseg模型)进行部署。
|
||||
2. 若FastDeploy没有提供满足要求的量化模型，用户可以参考[PaddleSeg动态图模型导出为A311D支持的INT8模型](../README.md#paddleseg动态图模型导出为a311d支持的int8模型)自行导出或训练量化模型
|
||||
3. 若上述导出或训练的模型出现精度下降或者报错，则需要使用异构计算，使得模型算子部分跑在A311D的ARM CPU上进行调试以及精度验证，其中异构计算所需的文件是subgraph.txt。具体关于异构计算可参考：[异构计算](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/faq/heterogeneous_computing_on_timvx_npu.md)。
|
||||
|
||||
## 在 A311D 上部署量化后的 PP-LiteSeg 分割模型
|
||||
|
||||
@@ -5,8 +5,8 @@ This directory provides `infer.c` to finish the deployment of PaddleSeg on CPU/G
|
||||
|
||||
Before deployment, two steps require confirmation
|
||||
|
||||
- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/en/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/en/build_and_install/download_prebuilt_libraries.md)
|
||||
- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../../docs/en/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../../docs/en/build_and_install/download_prebuilt_libraries.md)
|
||||
|
||||
Taking inference on Linux as an example, the compilation test can be completed by executing the following command in this directory. FastDeploy version 1.0.4 or above (x.x.x>=1.0.4) is required to support this model.
|
||||
|
||||
@@ -32,7 +32,7 @@ wget https://paddleseg.bj.bcebos.com/dygraph/demo/cityscapes_demo.png
|
||||
```
|
||||
|
||||
The above command works for Linux or MacOS. For SDK in Windows, refer to:
|
||||
- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/en/faq/use_sdk_on_windows.md)
|
||||
- [How to use FastDeploy C++ SDK in Windows](../../../../../../docs/en/faq/use_sdk_on_windows.md)
|
||||
|
||||
The visualized result after running is as follows
|
||||
|
||||
@@ -154,7 +154,7 @@ FD_C_Bool FD_C_PaddleSegWrapperPredict(
|
||||
> **Params**
|
||||
> * **fd_c_ppseg_wrapper**(FD_C_PaddleSegWrapper*): Pointer to manipulate PaddleSeg object.
|
||||
> * **img**（FD_C_Mat）: pointer to cv::Mat object, which can be obained by FD_C_Imread interface
|
||||
> * **result**(FD_C_SegmentationResult*): Segmentation prediction results, Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for SegmentationResult
|
||||
> * **result**(FD_C_SegmentationResult*): Segmentation prediction results, Refer to [Vision Model Prediction Results](../../../../../../docs/api/vision_results/) for SegmentationResult
|
||||
|
||||
|
||||
#### Result
|
||||
@@ -180,5 +180,5 @@ FD_C_Mat FD_C_VisSegmentation(FD_C_Mat im,
|
||||
|
||||
- [PPSegmentation Model Description](../../)
|
||||
- [PaddleSeg Python Deployment](../python)
|
||||
- [Model Prediction Results](../../../../../docs/api/vision_results/)
|
||||
- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
- [Model Prediction Results](../../../../../../docs/api/vision_results/)
|
||||
- [How to switch the model inference backend engine](../../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
|
||||
@@ -5,8 +5,8 @@
|
||||
|
||||
在部署前，需确认以下两个步骤
|
||||
|
||||
- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
|
||||
以Linux上推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本1.0.4以上(x.x.x>=1.0.4)
|
||||
|
||||
@@ -32,10 +32,10 @@ wget https://paddleseg.bj.bcebos.com/dygraph/demo/cityscapes_demo.png
|
||||
```
|
||||
|
||||
以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
|
||||
- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
|
||||
- [如何在Windows中使用FastDeploy C++ SDK](../../../../../../docs/cn/faq/use_sdk_on_windows.md)
|
||||
|
||||
如果用户使用华为昇腾NPU部署, 请参考以下方式在部署前初始化部署环境:
|
||||
- [如何使用华为昇腾NPU部署](../../../../../docs/cn/faq/use_sdk_on_ascend.md)
|
||||
- [如何使用华为昇腾NPU部署](../../../../../../docs/cn/faq/use_sdk_on_ascend.md)
|
||||
|
||||
运行完成可视化结果如下图所示
|
||||
|
||||
@@ -155,7 +155,7 @@ FD_C_Bool FD_C_PaddleSegWrapperPredict(
|
||||
> **参数**
|
||||
> * **fd_c_ppseg_wrapper**(FD_C_PaddleSegWrapper*): 指向PaddleSeg模型的指针
|
||||
> * **img**（FD_C_Mat）: 输入图像的指针，指向cv::Mat对象，可以调用FD_C_Imread读取图像获取
|
||||
> * **result**FD_C_SegmentationResult*): Segmentation检测结果，SegmentationResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
|
||||
> * **result**FD_C_SegmentationResult*): Segmentation检测结果，SegmentationResult说明参考[视觉模型预测结果](../../../../../../docs/api/vision_results/)
|
||||
|
||||
|
||||
#### Predict结果
|
||||
@@ -181,5 +181,5 @@ FD_C_Mat FD_C_VisSegmentation(FD_C_Mat im,
|
||||
|
||||
- [PPSegmentation 系列模型介绍](../../)
|
||||
- [PaddleSeg Python部署](../python)
|
||||
- [模型预测结果说明](../../../../../docs/api/vision_results/)
|
||||
- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
- [模型预测结果说明](../../../../../../docs/api/vision_results/)
|
||||
- [如何切换模型推理后端引擎](../../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
|
||||
@@ -5,8 +5,8 @@ This directory provides `infer.cs` to finish the deployment of PaddleSeg on CPU/
|
||||
|
||||
Before deployment, two steps require confirmation
|
||||
|
||||
- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/en/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/en/build_and_install/download_prebuilt_libraries.md)
|
||||
- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../../docs/en/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../../docs/en/build_and_install/download_prebuilt_libraries.md)
|
||||
|
||||
Please follow below instructions to compile and test in Windows. FastDeploy version 1.0.4 or above (x.x.x>=1.0.4) is required to support this model.
|
||||
|
||||
@@ -35,7 +35,7 @@ msbuild infer_demo.sln /m:4 /p:Configuration=Release /p:Platform=x64
|
||||
```
|
||||
|
||||
For more information about how to use FastDeploy SDK to compile a project with Visual Studio 2019. Please refer to
|
||||
- [Using the FastDeploy C++ SDK on Windows Platform](../../../../../docs/en/faq/use_sdk_on_windows.md)
|
||||
- [Using the FastDeploy C++ SDK on Windows Platform](../../../../../../docs/en/faq/use_sdk_on_windows.md)
|
||||
|
||||
## 4. Execute compiled program
|
||||
|
||||
@@ -93,12 +93,12 @@ fastdeploy.SegmentationResult Predict(OpenCvSharp.Mat im)
|
||||
>>
|
||||
> **Return**
|
||||
>
|
||||
>> * **result**: Segmentation prediction results, refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for SegmentationResult
|
||||
>> * **result**: Segmentation prediction results, refer to [Vision Model Prediction Results](../../../../../../docs/api/vision_results/) for SegmentationResult
|
||||
|
||||
|
||||
## Other Documents
|
||||
|
||||
- [PPSegmentation Model Description](../../)
|
||||
- [PaddleSeg Python Deployment](../python)
|
||||
- [Model Prediction Results](../../../../../docs/api/vision_results/)
|
||||
- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
- [Model Prediction Results](../../../../../../docs/api/vision_results/)
|
||||
- [How to switch the model inference backend engine](../../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
|
||||
@@ -5,8 +5,8 @@
|
||||
|
||||
在部署前，需确认以下两个步骤
|
||||
|
||||
- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
|
||||
在本目录执行如下命令即可在Windows完成编译测试，支持此模型需保证FastDeploy版本1.0.4以上(x.x.x>=1.0.4)
|
||||
|
||||
@@ -35,8 +35,8 @@ msbuild infer_demo.sln /m:4 /p:Configuration=Release /p:Platform=x64
|
||||
```
|
||||
|
||||
关于使用Visual Studio 2019创建sln工程，或者CMake工程等方式编译的更详细信息，可参考如下文档
|
||||
- [在 Windows 使用 FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
|
||||
- [FastDeploy C++库在Windows上的多种使用方式](../../../../../docs/cn/faq/use_sdk_on_windows_build.md)
|
||||
- [在 Windows 使用 FastDeploy C++ SDK](../../../../../../docs/cn/faq/use_sdk_on_windows.md)
|
||||
- [FastDeploy C++库在Windows上的多种使用方式](../../../../../../docs/cn/faq/use_sdk_on_windows_build.md)
|
||||
|
||||
## 4. 运行可执行程序
|
||||
|
||||
@@ -98,5 +98,5 @@ fastdeploy.SegmentationResult Predict(OpenCvSharp.Mat im)
|
||||
|
||||
- [模型介绍](../../)
|
||||
- [Python部署](../python)
|
||||
- [视觉模型预测结果](../../../../../docs/api/vision_results/)
|
||||
- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
- [视觉模型预测结果](../../../../../../docs/api/vision_results/)
|
||||
- [如何切换模型推理后端引擎](../../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
|
||||
@@ -28,7 +28,7 @@ PaddleSeg支持利用FastDeploy在昆仑芯片上部署Segmentation模型
|
||||
- [DeepLabV3系列模型](https://github.com/PaddlePaddle/PaddleSeg/blob/develop/configs/deeplabv3/README.md)
|
||||
- [SegFormer系列模型](https://github.com/PaddlePaddle/PaddleSeg/blob/develop/configs/segformer/README.md)
|
||||
|
||||
>>**注意** 若需要在华为昇腾上部署**PP-Matting**、**PP-HumanMatting**请从[Matting模型部署](../../ppmating/)下载对应模型，部署过程与此文档一致
|
||||
>>**注意** 若需要在华为昇腾上部署**PP-Matting**、**PP-HumanMatting**请从[Matting模型部署](../../../ppmating/)下载对应模型，部署过程与此文档一致
|
||||
|
||||
## 准备PaddleSeg部署模型
|
||||
PaddleSeg模型导出，请参考其文档说明[模型导出](https://github.com/PaddlePaddle/PaddleSeg/blob/develop/docs/model_export_cn.md)
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
## 昆仑芯XPU编译FastDeploy环境准备
|
||||
在部署前，需自行编译基于昆仑芯XPU的预测库，参考文档[昆仑芯XPU部署环境编译安装](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install#自行编译安装)
|
||||
|
||||
>>**注意** **PP-Matting**、**PP-HumanMatting**的模型，请从[Matting模型部署](../../../matting)下载
|
||||
>>**注意** **PP-Matting**、**PP-HumanMatting**的模型，请从[Matting模型部署](../../../../matting)下载
|
||||
|
||||
```bash
|
||||
#下载部署示例代码
|
||||
|
||||
@@ -22,6 +22,6 @@ FastDeploy 量化模型部署的过程大致都与FP32模型类似，只是模
|
||||
|
||||
| 硬件支持列表 | | | |
|
||||
|:----- | :-- | :-- | :-- |
|
||||
| [NVIDIA GPU](cpu-gpu) | [X86 CPU](cpu-gpu)| [飞腾CPU](cpu-gpu) | [ARM CPU](cpu-gpu) |
|
||||
| [Intel GPU(独立显卡/集成显卡)](cpu-gpu) | [昆仑](kunlun) | [昇腾](ascend) | [瑞芯微](rockchip) |
|
||||
| [晶晨](amlogic) | [算能](sophgo) |
|
||||
| [NVIDIA GPU](../cpu-gpu) | [X86 CPU](../cpu-gpu)| [飞腾CPU](../cpu-gpu) | [ARM CPU](../cpu-gpu) |
|
||||
| [Intel GPU(独立显卡/集成显卡)](../cpu-gpu) | [昆仑](../kunlun) | [昇腾](../ascend) | [瑞芯微](../rockchip) |
|
||||
| [晶晨](../amlogic) | [算能](../sophgo) |
|
||||
|
||||
@@ -12,11 +12,11 @@
|
||||
|
||||
## 转换模型
|
||||
|
||||
模型转换代码请参考[模型转换文档](../README_CN.md)
|
||||
模型转换代码请参考[模型转换文档](../README.md)
|
||||
|
||||
## 编译SDK
|
||||
|
||||
请参考[RK2代NPU部署库编译](../../../../../../docs/cn/faq/rknpu2/build.md)编译SDK.
|
||||
请参考[RK2代NPU部署库编译](../../../../../../../docs/cn/faq/rknpu2/build.md)编译SDK.
|
||||
|
||||
### 编译example
|
||||
|
||||
|
||||
@@ -32,7 +32,7 @@ RKNPU上对模型的输入要求是使用NHWC格式，且图片归一化操作
|
||||
|
||||
- [FastDeploy部署PaddleSeg模型概览](..)
|
||||
- [PaddleSeg C++部署](../cpp)
|
||||
- [转换PaddleSeg模型至RKNN模型文档](../README_CN.md#准备paddleseg部署模型以及转换模型)
|
||||
- [转换PaddleSeg模型至RKNN模型文档](../README.md#准备paddleseg部署模型以及转换模型)
|
||||
|
||||
## 常见问题
|
||||
- [如何将模型预测结果SegmentationResult转为numpy格式](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/faq/vision_result_related_problems.md)
|
||||
|
||||
@@ -8,8 +8,8 @@
|
||||
软硬件环境满足要求，以及交叉编译环境的准备，请参考：[瑞芯微RV1126部署环境](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install#自行编译安装)
|
||||
|
||||
### 模型准备
|
||||
1. 用户可以直接使用由[FastDeploy 提供的量化模型](../README_CN.md#瑞芯微-rv1126-支持的paddleseg模型)进行部署。
|
||||
2. 若FastDeploy没有提供满足要求的量化模型，用户可以参考[PaddleSeg动态图模型导出为RV1126支持的INT8模型](../README_CN.md#paddleseg动态图模型导出为rv1126支持的int8模型)自行导出或训练量化模型
|
||||
1. 用户可以直接使用由[FastDeploy 提供的量化模型](../README.md#瑞芯微-rv1126-支持的paddleseg模型)进行部署。
|
||||
2. 若FastDeploy没有提供满足要求的量化模型，用户可以参考[PaddleSeg动态图模型导出为RV1126支持的INT8模型](../README.md#paddleseg动态图模型导出为rv1126支持的int8模型)自行导出或训练量化模型
|
||||
3. 若上述导出或训练的模型出现精度下降或者报错，则需要使用异构计算，使得模型算子部分跑在RV1126的ARM CPU上进行调试以及精度验证，其中异构计算所需的文件是subgraph.txt。具体关于异构计算可参考：[异构计算](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/faq/heterogeneous_computing_on_timvx_npu.md)。
|
||||
|
||||
## 在 RV1126 上部署量化后的 PP-LiteSeg 分割模型
|
||||
|
||||
@@ -65,4 +65,4 @@ When the request is sent successfully, the results are returned in json format a
|
||||
|
||||
|
||||
|
||||
The default is to run ONNXRuntime on CPU. If developers need to run it on GPU or other inference engines, please see the [Configs File](../../../../../serving/docs/EN/model_configuration-en.md) to modify the configs in `models/runtime/config.pbtxt`.
|
||||
The default is to run ONNXRuntime on CPU. If developers need to run it on GPU or other inference engines, please see the [Configs File](../../../../../../serving/docs/EN/model_configuration-en.md) to modify the configs in `models/runtime/config.pbtxt`.
|
||||
|
||||
@@ -25,7 +25,7 @@
|
||||
请参考[SOPHGO部署库编译](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install/sophgo.md)编译SDK，编译完成后，将在build目录下生成fastdeploy-sophgo目录。拷贝fastdeploy-sophgo至当前目录
|
||||
|
||||
### 拷贝模型文件，以及配置文件至model文件夹
|
||||
将Paddle模型转换为SOPHGO bmodel模型，转换步骤参考[文档](../README_CN.md#将paddleseg推理模型转换为bmodel模型步骤)
|
||||
将Paddle模型转换为SOPHGO bmodel模型，转换步骤参考[文档](../README.md#将paddleseg推理模型转换为bmodel模型步骤)
|
||||
|
||||
将转换后的SOPHGO bmodel模型文件拷贝至model中
|
||||
|
||||
@@ -53,4 +53,4 @@ make
|
||||
- [PaddleSeg C++ API文档](https://www.paddlepaddle.org.cn/fastdeploy-api-doc/cpp/html/namespacefastdeploy_1_1vision_1_1segmentation.html)
|
||||
- [FastDeploy部署PaddleSeg模型概览](../../)
|
||||
- [Python部署](../python)
|
||||
- [模型转换](../README_CN.md#将paddleseg推理模型转换为bmodel模型步骤)
|
||||
- [模型转换](../README.md#将paddleseg推理模型转换为bmodel模型步骤)
|
||||
|
||||
@@ -27,7 +27,7 @@ python3 infer.py --model_file ./bmodel/pp_liteseg_1684x_f32.bmodel --config_file
|
||||
|
||||
## 快速链接
|
||||
- [pp_liteseg C++部署](../cpp)
|
||||
- [转换 pp_liteseg SOPHGO模型文档](../README_CN.md#导出bmodel模型)
|
||||
- [转换 pp_liteseg SOPHGO模型文档](../README.md#导出bmodel模型)
|
||||
|
||||
## 常见问题
|
||||
- [如何将模型预测结果SegmentationResult转为numpy格式](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/faq/vision_result_related_problems.md)
|
||||
|
||||
@@ -45,7 +45,7 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_bgr.jpg
|
||||
</div>
|
||||
|
||||
以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
|
||||
- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
|
||||
- [如何在Windows中使用FastDeploy C++ SDK](../../../../../../docs/cn/faq/use_sdk_on_windows.md)
|
||||
|
||||
## 快速链接
|
||||
- [PaddleSeg C++ API文档](https://www.paddlepaddle.org.cn/fastdeploy-api-doc/cpp/html/namespacefastdeploy_1_1vision_1_1segmentation.html)
|
||||
|
||||
Reference in New Issue
Block a user