apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 00:57:33 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Doc]Check and modify broken links in documents (#1207)

Browse Source 
* Update README_CN.md

之前的readme cn复制错了，导致存在死链

* Update README_CN.md

* Update README_CN.md

* Update README.md

* Update README.md

* Update README.md

* Update README_CN.md

* Update README_CN.md

* Update README.md

* Update README_CN.md

* Update README.md

* Update README_CN.md

* Update README.md

* Update RNN.md

* Update RNN_CN.md

* Update WebDemo.md

* Update WebDemo_CN.md

* Update install_rknn_toolkit2.md

* Update export.md

* Update use_cpp_sdk_on_android.md

* Update README.md

* Update README_Pу́сский_язы́к.md

* Update README_Pу́сский_язы́к.md

* Update README_Pу́сский_язы́к.md

* Update README_Pу́сский_язы́к.md

* Update README_हिन्दी.md

* Update README_日本語.md

* Update README_한국인.md

* Update README_日本語.md

* Update README_CN.md

* Update README_CN.md

* Update README.md

* Update README_CN.md

* Update README.md

* Update README.md

* Update README_CN.md

* Update README_CN.md

* Update README_CN.md

* Update README_CN.md
This commit is contained in:
charl-u
2023-02-01 15:49:23 +08:00
committed by GitHub
parent c36843d302
commit 29e93fa2dc
29 changed files with 245 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/cn/faq/rknpu2/export.md
View File

@@ -8,7 +8,7 @@ Fastdeploy已经简单的集成了onnx->rknn的转换过程。
本教程使用tools/rknpu2/export.py文件导出模型，在导出之前需要编写yaml配置文件。 本教程使用tools/rknpu2/export.py文件导出模型，在导出之前需要编写yaml配置文件。
## 环境要求 ## 环境要求
在进行转换前请根据[rknn_toolkit2安装文档](./install_rknn_toolkit2.md)检查环境是否已经安装成功。 在进行转换前请根据[rknn_toolkit2安装文档](./environment.md)检查环境是否已经安装成功。
## export.py 配置参数介绍 ## export.py 配置参数介绍

2
docs/cn/faq/use_cpp_sdk_on_android.md
View File

@@ -73,7 +73,7 @@ Android Studio 生成 JNI 函数定义: 鼠标停留在Java中定义的native函
## 在C++层实现JNI函数 ## 在C++层实现JNI函数
<div id="CPP"></div> <div id="CPP"></div>
以下为PicoDet JNI层实现的示例，相关的辅助函数不在此处赘述，完整的C++代码请参考 [android/app/src/main/cpp](../../../examples/vision/detection/paddledetection/android/app/src/main/cpp/). 以下为PicoDet JNI层实现的示例，相关的辅助函数不在此处赘述，完整的C++代码请参考 [android/app/src/main/cpp](../../examples/vision/detection/paddledetection/android/app/src/main/cpp/).
```C++ ```C++
// Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved. // Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
// //

24
docs/docs_i18n/README_Pу́сский_язы́к.md
View File

@@ -29,17 +29,17 @@
<div align="center"> <div align="center">
[<img src='https://user-images.githubusercontent.com/54695910/200465949-da478e1b-21ce-43b8-9f3f-287460e786bd.png' height="80px" width="110px">](examples/vision/classification) [<img src='https://user-images.githubusercontent.com/54695910/200465949-da478e1b-21ce-43b8-9f3f-287460e786bd.png' height="80px" width="110px">](../../examples/vision/classification)
[<img src='https://user-images.githubusercontent.com/54695910/188054680-2f8d1952-c120-4b67-88fc-7d2d7d2378b4.gif' height="80px" width="110px">](examples/vision/detection) [<img src='https://user-images.githubusercontent.com/54695910/188054680-2f8d1952-c120-4b67-88fc-7d2d7d2378b4.gif' height="80px" width="110px">](../../examples/vision/detection)
[<img src='https://user-images.githubusercontent.com/54695910/188054711-6119f0e7-d741-43b1-b273-9493d103d49f.gif' height="80px" width="110px">](examples/vision/segmentation/paddleseg) [<img src='https://user-images.githubusercontent.com/54695910/188054711-6119f0e7-d741-43b1-b273-9493d103d49f.gif' height="80px" width="110px">](../../examples/vision/segmentation/paddleseg)
[<img src='https://user-images.githubusercontent.com/54695910/188054718-6395321c-8937-4fa0-881c-5b20deb92aaa.gif' height="80px" width="110px">](examples/vision/segmentation/paddleseg) [<img src='https://user-images.githubusercontent.com/54695910/188054718-6395321c-8937-4fa0-881c-5b20deb92aaa.gif' height="80px" width="110px">](../../examples/vision/segmentation/paddleseg)
[<img src='https://user-images.githubusercontent.com/54695910/188058231-a5fe1ce1-0a38-460f-9582-e0b881514908.gif' height="80px" width="110px">](examples/vision/matting) [<img src='https://user-images.githubusercontent.com/54695910/188058231-a5fe1ce1-0a38-460f-9582-e0b881514908.gif' height="80px" width="110px">](../../examples/vision/matting)
[<img src='https://user-images.githubusercontent.com/54695910/188054691-e4cb1a70-09fe-4691-bc62-5552d50bd853.gif' height="80px" width="110px">](examples/vision/matting) [<img src='https://user-images.githubusercontent.com/54695910/188054691-e4cb1a70-09fe-4691-bc62-5552d50bd853.gif' height="80px" width="110px">](../../examples/vision/matting)
[<img src='https://user-images.githubusercontent.com/54695910/188054669-a85996ba-f7f3-4646-ae1f-3b7e3e353e7d.gif' height="80px" width="110px">](examples/vision/ocr)<br> [<img src='https://user-images.githubusercontent.com/54695910/188054669-a85996ba-f7f3-4646-ae1f-3b7e3e353e7d.gif' height="80px" width="110px">](../../examples/vision/ocr)<br>
[<img src='https://user-images.githubusercontent.com/54695910/188059460-9845e717-c30a-4252-bd80-b7f6d4cf30cb.png' height="80px" width="110px">](examples/vision/facealign) [<img src='https://user-images.githubusercontent.com/54695910/188059460-9845e717-c30a-4252-bd80-b7f6d4cf30cb.png' height="80px" width="110px">](../../examples/vision/facealign)
[<img src='https://user-images.githubusercontent.com/54695910/188054671-394db8dd-537c-42b1-9d90-468d7ad1530e.gif' height="80px" width="110px">](examples/vision/keypointdetection) [<img src='https://user-images.githubusercontent.com/54695910/188054671-394db8dd-537c-42b1-9d90-468d7ad1530e.gif' height="80px" width="110px">](../../examples/vision/keypointdetection)
[<img src='https://user-images.githubusercontent.com/48054808/173034825-623e4f78-22a5-4f14-9b83-dc47aa868478.gif' height="80px" width="110px">](https://user-images.githubusercontent.com/54695910/200162475-f5d85d70-18fb-4930-8e7e-9ca065c1d618.gif) [<img src='https://user-images.githubusercontent.com/48054808/173034825-623e4f78-22a5-4f14-9b83-dc47aa868478.gif' height="80px" width="110px">](https://github.com/PaddlePaddle/FastDeploy/issues/6)
[<img src='https://user-images.githubusercontent.com/54695910/200162475-f5d85d70-18fb-4930-8e7e-9ca065c1d618.gif' height="80px" width="110px">](examples/text) [<img src='https://user-images.githubusercontent.com/54695910/200162475-f5d85d70-18fb-4930-8e7e-9ca065c1d618.gif' height="80px" width="110px">](../../examples/text)
[<img src='https://user-images.githubusercontent.com/54695910/212314909-77624bdd-1d12-4431-9cca-7a944ec705d3.png' height="80px" width="110px">](https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/001.wav) [<img src='https://user-images.githubusercontent.com/54695910/212314909-77624bdd-1d12-4431-9cca-7a944ec705d3.png' height="80px" width="110px">](https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/001.wav)
</div> </div>
@@ -270,7 +270,7 @@ int main(int argc, char* argv[]) {
| Сценарии миссий | Модели | Linux | Linux | Win | Win | Mac | Mac | Linux | Linux | Linux | Linux | Linux | | Сценарии миссий | Модели | Linux | Linux | Win | Win | Mac | Mac | Linux | Linux | Linux | Linux | Linux |
|:----------------------:|:--------------------------------------------------------------------------------------------:|:------------------------------------------------:|:----------:|:-------:|:----------:|:-------:|:-------:|:-----------:|:---------------:|:-------------:|:-------------:|:-------:| |:----------------------:|:--------------------------------------------------------------------------------------------:|:------------------------------------------------:|:----------:|:-------:|:----------:|:-------:|:-------:|:-----------:|:---------------:|:-------------:|:-------------:|:-------:|
| --- | --- | X86 CPU | NVIDIA GPU | X86 CPU | NVIDIA GPU | X86 CPU | Arm CPU | AArch64 CPU | Phytium D2000CPU | NVIDIA Jetson | Graphcore IPU | Serving | | --- | --- | X86 CPU | NVIDIA GPU | X86 CPU | NVIDIA GPU | X86 CPU | Arm CPU | AArch64 CPU | Phytium D2000CPU | NVIDIA Jetson | Graphcore IPU | Serving |
| Classification | [PaddleClas/ResNet50](./../../examples/vision/classification/paddleclas) | [✅](./examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | Classification | [PaddleClas/ResNet50](./../../examples/vision/classification/paddleclas) | [✅](./../../examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Classification | [TorchVison/ResNet](./../../examples/vision/classification/resnet) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | | Classification | [TorchVison/ResNet](./../../examples/vision/classification/resnet) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ |
| Classification | [ultralytics/YOLOv5Cls](./../../examples/vision/classification/yolov5cls) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ | | Classification | [ultralytics/YOLOv5Cls](./../../examples/vision/classification/yolov5cls) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❔ | ❔ |
| Classification | [PaddleClas/PP-LCNet](./../../examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | Classification | [PaddleClas/PP-LCNet](./../../examples/vision/classification/paddleclas) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |

22
docs/docs_i18n/README_हिन्दी.md
View File

@@ -29,17 +29,17 @@
<div align="center"> <div align="center">
[<img src='https://user-images.githubusercontent.com/54695910/200465949-da478e1b-21ce-43b8-9f3f-287460e786bd.png' height="80px" width="110px">](examples/vision/classification) [<img src='https://user-images.githubusercontent.com/54695910/200465949-da478e1b-21ce-43b8-9f3f-287460e786bd.png' height="80px" width="110px">](../../examples/vision/classification)
[<img src='https://user-images.githubusercontent.com/54695910/188054680-2f8d1952-c120-4b67-88fc-7d2d7d2378b4.gif' height="80px" width="110px">](examples/vision/detection) [<img src='https://user-images.githubusercontent.com/54695910/188054680-2f8d1952-c120-4b67-88fc-7d2d7d2378b4.gif' height="80px" width="110px">](../../examples/vision/detection)
[<img src='https://user-images.githubusercontent.com/54695910/188054711-6119f0e7-d741-43b1-b273-9493d103d49f.gif' height="80px" width="110px">](examples/vision/segmentation/paddleseg) [<img src='https://user-images.githubusercontent.com/54695910/188054711-6119f0e7-d741-43b1-b273-9493d103d49f.gif' height="80px" width="110px">](../../examples/vision/segmentation/paddleseg)
[<img src='https://user-images.githubusercontent.com/54695910/188054718-6395321c-8937-4fa0-881c-5b20deb92aaa.gif' height="80px" width="110px">](examples/vision/segmentation/paddleseg) [<img src='https://user-images.githubusercontent.com/54695910/188054718-6395321c-8937-4fa0-881c-5b20deb92aaa.gif' height="80px" width="110px">](../../examples/vision/segmentation/paddleseg)
[<img src='https://user-images.githubusercontent.com/54695910/188058231-a5fe1ce1-0a38-460f-9582-e0b881514908.gif' height="80px" width="110px">](examples/vision/matting) [<img src='https://user-images.githubusercontent.com/54695910/188058231-a5fe1ce1-0a38-460f-9582-e0b881514908.gif' height="80px" width="110px">](../../examples/vision/matting)
[<img src='https://user-images.githubusercontent.com/54695910/188054691-e4cb1a70-09fe-4691-bc62-5552d50bd853.gif' height="80px" width="110px">](examples/vision/matting) [<img src='https://user-images.githubusercontent.com/54695910/188054691-e4cb1a70-09fe-4691-bc62-5552d50bd853.gif' height="80px" width="110px">](../../examples/vision/matting)
[<img src='https://user-images.githubusercontent.com/54695910/188054669-a85996ba-f7f3-4646-ae1f-3b7e3e353e7d.gif' height="80px" width="110px">](examples/vision/ocr)<br> [<img src='https://user-images.githubusercontent.com/54695910/188054669-a85996ba-f7f3-4646-ae1f-3b7e3e353e7d.gif' height="80px" width="110px">](../../examples/vision/ocr)<br>
[<img src='https://user-images.githubusercontent.com/54695910/188059460-9845e717-c30a-4252-bd80-b7f6d4cf30cb.png' height="80px" width="110px">](examples/vision/facealign) [<img src='https://user-images.githubusercontent.com/54695910/188059460-9845e717-c30a-4252-bd80-b7f6d4cf30cb.png' height="80px" width="110px">](../../examples/vision/facealign)
[<img src='https://user-images.githubusercontent.com/54695910/188054671-394db8dd-537c-42b1-9d90-468d7ad1530e.gif' height="80px" width="110px">](examples/vision/keypointdetection) [<img src='https://user-images.githubusercontent.com/54695910/188054671-394db8dd-537c-42b1-9d90-468d7ad1530e.gif' height="80px" width="110px">](../../examples/vision/keypointdetection)
[<img src='https://user-images.githubusercontent.com/48054808/173034825-623e4f78-22a5-4f14-9b83-dc47aa868478.gif' height="80px" width="110px">](https://user-images.githubusercontent.com/54695910/200162475-f5d85d70-18fb-4930-8e7e-9ca065c1d618.gif) [<img src='https://user-images.githubusercontent.com/48054808/173034825-623e4f78-22a5-4f14-9b83-dc47aa868478.gif' height="80px" width="110px">](https://github.com/PaddlePaddle/FastDeploy/issues/6)
[<img src='https://user-images.githubusercontent.com/54695910/200162475-f5d85d70-18fb-4930-8e7e-9ca065c1d618.gif' height="80px" width="110px">](examples/text) [<img src='https://user-images.githubusercontent.com/54695910/200162475-f5d85d70-18fb-4930-8e7e-9ca065c1d618.gif' height="80px" width="110px">](../../examples/text)
[<img src='https://user-images.githubusercontent.com/54695910/212314909-77624bdd-1d12-4431-9cca-7a944ec705d3.png' height="80px" width="110px">](https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/001.wav) [<img src='https://user-images.githubusercontent.com/54695910/212314909-77624bdd-1d12-4431-9cca-7a944ec705d3.png' height="80px" width="110px">](https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/001.wav)
</div> </div>

24
docs/docs_i18n/README_日本語.md
View File

@@ -29,17 +29,17 @@
<div align="center"> <div align="center">
[<img src='https://user-images.githubusercontent.com/54695910/200465949-da478e1b-21ce-43b8-9f3f-287460e786bd.png' height="80px" width="110px">](examples/vision/classification) [<img src='https://user-images.githubusercontent.com/54695910/200465949-da478e1b-21ce-43b8-9f3f-287460e786bd.png' height="80px" width="110px">](../../examples/vision/classification)
[<img src='https://user-images.githubusercontent.com/54695910/188054680-2f8d1952-c120-4b67-88fc-7d2d7d2378b4.gif' height="80px" width="110px">](examples/vision/detection) [<img src='https://user-images.githubusercontent.com/54695910/188054680-2f8d1952-c120-4b67-88fc-7d2d7d2378b4.gif' height="80px" width="110px">](../../examples/vision/detection)
[<img src='https://user-images.githubusercontent.com/54695910/188054711-6119f0e7-d741-43b1-b273-9493d103d49f.gif' height="80px" width="110px">](examples/vision/segmentation/paddleseg) [<img src='https://user-images.githubusercontent.com/54695910/188054711-6119f0e7-d741-43b1-b273-9493d103d49f.gif' height="80px" width="110px">](../../examples/vision/segmentation/paddleseg)
[<img src='https://user-images.githubusercontent.com/54695910/188054718-6395321c-8937-4fa0-881c-5b20deb92aaa.gif' height="80px" width="110px">](examples/vision/segmentation/paddleseg) [<img src='https://user-images.githubusercontent.com/54695910/188054718-6395321c-8937-4fa0-881c-5b20deb92aaa.gif' height="80px" width="110px">](../../examples/vision/segmentation/paddleseg)
[<img src='https://user-images.githubusercontent.com/54695910/188058231-a5fe1ce1-0a38-460f-9582-e0b881514908.gif' height="80px" width="110px">](examples/vision/matting) [<img src='https://user-images.githubusercontent.com/54695910/188058231-a5fe1ce1-0a38-460f-9582-e0b881514908.gif' height="80px" width="110px">](../../examples/vision/matting)
[<img src='https://user-images.githubusercontent.com/54695910/188054691-e4cb1a70-09fe-4691-bc62-5552d50bd853.gif' height="80px" width="110px">](examples/vision/matting) [<img src='https://user-images.githubusercontent.com/54695910/188054691-e4cb1a70-09fe-4691-bc62-5552d50bd853.gif' height="80px" width="110px">](../../examples/vision/matting)
[<img src='https://user-images.githubusercontent.com/54695910/188054669-a85996ba-f7f3-4646-ae1f-3b7e3e353e7d.gif' height="80px" width="110px">](examples/vision/ocr)<br> [<img src='https://user-images.githubusercontent.com/54695910/188054669-a85996ba-f7f3-4646-ae1f-3b7e3e353e7d.gif' height="80px" width="110px">](../../examples/vision/ocr)<br>
[<img src='https://user-images.githubusercontent.com/54695910/188059460-9845e717-c30a-4252-bd80-b7f6d4cf30cb.png' height="80px" width="110px">](examples/vision/facealign) [<img src='https://user-images.githubusercontent.com/54695910/188059460-9845e717-c30a-4252-bd80-b7f6d4cf30cb.png' height="80px" width="110px">](../../examples/vision/facealign)
[<img src='https://user-images.githubusercontent.com/54695910/188054671-394db8dd-537c-42b1-9d90-468d7ad1530e.gif' height="80px" width="110px">](examples/vision/keypointdetection) [<img src='https://user-images.githubusercontent.com/54695910/188054671-394db8dd-537c-42b1-9d90-468d7ad1530e.gif' height="80px" width="110px">](../../examples/vision/keypointdetection)
[<img src='https://user-images.githubusercontent.com/48054808/173034825-623e4f78-22a5-4f14-9b83-dc47aa868478.gif' height="80px" width="110px">](https://user-images.githubusercontent.com/54695910/200162475-f5d85d70-18fb-4930-8e7e-9ca065c1d618.gif) [<img src='https://user-images.githubusercontent.com/48054808/173034825-623e4f78-22a5-4f14-9b83-dc47aa868478.gif' height="80px" width="110px">](https://github.com/PaddlePaddle/FastDeploy/issues/6)
[<img src='https://user-images.githubusercontent.com/54695910/200162475-f5d85d70-18fb-4930-8e7e-9ca065c1d618.gif' height="80px" width="110px">](examples/text) [<img src='https://user-images.githubusercontent.com/54695910/200162475-f5d85d70-18fb-4930-8e7e-9ca065c1d618.gif' height="80px" width="110px">](../../examples/text)
[<img src='https://user-images.githubusercontent.com/54695910/212314909-77624bdd-1d12-4431-9cca-7a944ec705d3.png' height="80px" width="110px">](https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/001.wav) [<img src='https://user-images.githubusercontent.com/54695910/212314909-77624bdd-1d12-4431-9cca-7a944ec705d3.png' height="80px" width="110px">](https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/001.wav)
</div> </div>
@@ -132,7 +132,7 @@
- **よくある質問** - **よくある質問**
- [1. Windows上C++ SDK の場合使用方法](./../../docs/en/faq/use_sdk_on_windows.md) - [1. Windows上C++ SDK の場合使用方法](./../../docs/en/faq/use_sdk_on_windows.md)
- [2. FastDeploy C++ SDKをAndroidで使用する方法](./../../docs/en/faq/use_cpp_sdk_on_android.md) - [2. FastDeploy C++ SDKをAndroidで使用する方法](./../../docs/en/faq/use_cpp_sdk_on_android.md)
- [3. TensorRT 使い方のコツ](./../../doc/en/faq/tensorrt_tricks.md) - [3. TensorRT 使い方のコツ](./../../docs/en/faq/tensorrt_tricks.md)
- **続きを読むFastDeployモジュールのデプロイメント** - **続きを読むFastDeployモジュールのデプロイメント**
- [Benchmark テスト](./../../benchmark) - [Benchmark テスト](./../../benchmark)
- **モデル対応表** - **モデル対応表**

24
docs/docs_i18n/README_한국인.md
View File

@@ -29,17 +29,17 @@
<div align="center"> <div align="center">
[<img src='https://user-images.githubusercontent.com/54695910/200465949-da478e1b-21ce-43b8-9f3f-287460e786bd.png' height="80px" width="110px">](examples/vision/classification) [<img src='https://user-images.githubusercontent.com/54695910/200465949-da478e1b-21ce-43b8-9f3f-287460e786bd.png' height="80px" width="110px">](../../examples/vision/classification)
[<img src='https://user-images.githubusercontent.com/54695910/188054680-2f8d1952-c120-4b67-88fc-7d2d7d2378b4.gif' height="80px" width="110px">](examples/vision/detection) [<img src='https://user-images.githubusercontent.com/54695910/188054680-2f8d1952-c120-4b67-88fc-7d2d7d2378b4.gif' height="80px" width="110px">](../../examples/vision/detection)
[<img src='https://user-images.githubusercontent.com/54695910/188054711-6119f0e7-d741-43b1-b273-9493d103d49f.gif' height="80px" width="110px">](examples/vision/segmentation/paddleseg) [<img src='https://user-images.githubusercontent.com/54695910/188054711-6119f0e7-d741-43b1-b273-9493d103d49f.gif' height="80px" width="110px">](../../examples/vision/segmentation/paddleseg)
[<img src='https://user-images.githubusercontent.com/54695910/188054718-6395321c-8937-4fa0-881c-5b20deb92aaa.gif' height="80px" width="110px">](examples/vision/segmentation/paddleseg) [<img src='https://user-images.githubusercontent.com/54695910/188054718-6395321c-8937-4fa0-881c-5b20deb92aaa.gif' height="80px" width="110px">](../../examples/vision/segmentation/paddleseg)
[<img src='https://user-images.githubusercontent.com/54695910/188058231-a5fe1ce1-0a38-460f-9582-e0b881514908.gif' height="80px" width="110px">](examples/vision/matting) [<img src='https://user-images.githubusercontent.com/54695910/188058231-a5fe1ce1-0a38-460f-9582-e0b881514908.gif' height="80px" width="110px">](../../examples/vision/matting)
[<img src='https://user-images.githubusercontent.com/54695910/188054691-e4cb1a70-09fe-4691-bc62-5552d50bd853.gif' height="80px" width="110px">](examples/vision/matting) [<img src='https://user-images.githubusercontent.com/54695910/188054691-e4cb1a70-09fe-4691-bc62-5552d50bd853.gif' height="80px" width="110px">](../../examples/vision/matting)
[<img src='https://user-images.githubusercontent.com/54695910/188054669-a85996ba-f7f3-4646-ae1f-3b7e3e353e7d.gif' height="80px" width="110px">](examples/vision/ocr)<br> [<img src='https://user-images.githubusercontent.com/54695910/188054669-a85996ba-f7f3-4646-ae1f-3b7e3e353e7d.gif' height="80px" width="110px">](../../examples/vision/ocr)<br>
[<img src='https://user-images.githubusercontent.com/54695910/188059460-9845e717-c30a-4252-bd80-b7f6d4cf30cb.png' height="80px" width="110px">](examples/vision/facealign) [<img src='https://user-images.githubusercontent.com/54695910/188059460-9845e717-c30a-4252-bd80-b7f6d4cf30cb.png' height="80px" width="110px">](../../examples/vision/facealign)
[<img src='https://user-images.githubusercontent.com/54695910/188054671-394db8dd-537c-42b1-9d90-468d7ad1530e.gif' height="80px" width="110px">](examples/vision/keypointdetection) [<img src='https://user-images.githubusercontent.com/54695910/188054671-394db8dd-537c-42b1-9d90-468d7ad1530e.gif' height="80px" width="110px">](../../examples/vision/keypointdetection)
[<img src='https://user-images.githubusercontent.com/48054808/173034825-623e4f78-22a5-4f14-9b83-dc47aa868478.gif' height="80px" width="110px">](https://user-images.githubusercontent.com/54695910/200162475-f5d85d70-18fb-4930-8e7e-9ca065c1d618.gif) [<img src='https://user-images.githubusercontent.com/48054808/173034825-623e4f78-22a5-4f14-9b83-dc47aa868478.gif' height="80px" width="110px">](https://github.com/PaddlePaddle/FastDeploy/issues/6)
[<img src='https://user-images.githubusercontent.com/54695910/200162475-f5d85d70-18fb-4930-8e7e-9ca065c1d618.gif' height="80px" width="110px">](examples/text) [<img src='https://user-images.githubusercontent.com/54695910/200162475-f5d85d70-18fb-4930-8e7e-9ca065c1d618.gif' height="80px" width="110px">](../../examples/text)
[<img src='https://user-images.githubusercontent.com/54695910/212314909-77624bdd-1d12-4431-9cca-7a944ec705d3.png' height="80px" width="110px">](https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/001.wav) [<img src='https://user-images.githubusercontent.com/54695910/212314909-77624bdd-1d12-4431-9cca-7a944ec705d3.png' height="80px" width="110px">](https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/001.wav)
</div> </div>
@@ -131,7 +131,7 @@
- **늘 보는 질문** - **늘 보는 질문**
- [1. Windows C++ SDK 어떻게 사용하는가](./../../docs/cn/faq/use_sdk_on_windows.md) - [1. Windows C++ SDK 어떻게 사용하는가](./../../docs/cn/faq/use_sdk_on_windows.md)
- [2. Android 어떻게 사용하는가 FastDeploy C++ SDK](./../../docs/cn/faq/use_cpp_sdk_on_android.md) - [2. Android 어떻게 사용하는가 FastDeploy C++ SDK](./../../docs/cn/faq/use_cpp_sdk_on_android.md)
- [3. TensorRT 몇 가지 기술들이 있습니다](./../../docs/cn/faq/tensorrt_tricks.md) - [3. TensorRT 몇 가지 기술들이 있습니다](./../../docs/en/faq/tensorrt_tricks.md)
- **더 많은FastDeploy 배포 모듈** - **더 많은FastDeploy 배포 모듈**
- [Benchmark 테스트](./../../benchmark) - [Benchmark 테스트](./../../benchmark)
- **모델 지원 목록** - **모델 지원 목록**

2
docs/en/build_and_install/README.md
View File

@@ -17,7 +17,7 @@ English | [中文](../../cn/build_and_install/README.md)
- [Build and Install on A311D Platform](a311d.md) - [Build and Install on A311D Platform](a311d.md)
- [Build and Install on KunlunXin XPU Platform](kunlunxin.md) - [Build and Install on KunlunXin XPU Platform](kunlunxin.md)
- [Build and Install on Huawei Ascend Platform](huawei_ascend.md) - [Build and Install on Huawei Ascend Platform](huawei_ascend.md)
- [Build and Install on SOPHGO Platform](sophgo.md.md) - [Build and Install on SOPHGO Platform](sophgo.md)
## Build options ## Build options

2
docs/en/faq/rknpu2/install_rknn_toolkit2.md
View File

@@ -1,4 +1,4 @@
English | [中文](../../../cn/faq/rknpu2/install_rknn_toolkit2.md) English | [中文](../../cn/faq/rknpu2/install_rknn_toolkit2.md)
# RKNN-Toolkit2 Installation # RKNN-Toolkit2 Installation
## Download ## Download

2
examples/application/js/WebDemo.md
View File

@@ -149,7 +149,7 @@ const postConfig = {thresh: 0.5};
await model.predict(Config); await model.predict(Config);
```` ````
Take the OCR text detection demo as an example, modify the parameters of the text detection post-processing to achieve the effect of expanding the text detection frame, and modify the OCR web demo to execute the [model prediction code](https://github.com/PaddlePaddle/FastDeploy/tree/develop/examples/application/web_demo/src/pages/cv/ocr/TextRecognition/TextRecognition.vue#L99), ie: Take the OCR text detection demo as an example, modify the parameters of the text detection post-processing to achieve the effect of expanding the text detection frame, and modify the OCR web demo to execute the [model prediction code](https://github.com/PaddlePaddle/FastDeploy/tree/develop/examples/application/js/web_demo/src/pages/cv/ocr/TextRecognition/TextRecognition.vue#L99), ie:
```` ````
const res = await ocr.recognize(img, { canvas: canvas.value }); const res = await ocr.recognize(img, { canvas: canvas.value });

2
examples/application/js/WebDemo_CN.md
View File

@@ -148,7 +148,7 @@ const postConfig = {thresh: 0.5};
await model.predict(Config); await model.predict(Config);
``` ```
以OCR文本检测 demo为例，修改文本检测后处理的参数实现扩大文本检测框的效果，修改OCR web demo中执行[模型预测代码](https://github.com/PaddlePaddle/FastDeploy/tree/develop/examples/application/web_demo/src/pages/cv/ocr/TextRecognition/TextRecognition.vue#L99)，即： 以OCR文本检测 demo为例，修改文本检测后处理的参数实现扩大文本检测框的效果，修改OCR web demo中执行[模型预测代码](https://github.com/PaddlePaddle/FastDeploy/tree/develop/examples/application/js/web_demo/src/pages/cv/ocr/TextRecognition/TextRecognition.vue#L99)，即：
``` ```
const res = await ocr.recognize(img, { canvas: canvas.value }); const res = await ocr.recognize(img, { canvas: canvas.value });

4
examples/application/js/converter/RNN.md
View File

@@ -70,11 +70,11 @@ Formula: rnn_matmul = rnn_origin + Matmul( $ S_{t-1} $, WeightList_hh)
3) rnn_cell 3) rnn_cell
Method: Split the rnn_matmul op output into 4 copies, each copy performs a different activation function calculation, and finally outputs lstm_x_y.tmp_c[1, 1, 48]. x∈[0, 3], y∈[0, 24]. Method: Split the rnn_matmul op output into 4 copies, each copy performs a different activation function calculation, and finally outputs lstm_x_y.tmp_c[1, 1, 48]. x∈[0, 3], y∈[0, 24].
For details, please refer to [rnn_cell](../paddlejs-backend-webgl/src/ops/shader/rnn/rnn_cell.ts). For details, please refer to [rnn_cell](https://github.com/PaddlePaddle/Paddle.js/blob/release/v2.2.5/packages/paddlejs-backend-webgl/src/ops/shader/rnn/rnn_cell.ts).
4) rnn_hidden 4) rnn_hidden
Split the rnn_matmul op output into 4 copies, each copy performs a different activation function calculation, and finally outputs lstm_x_y.tmp_h[1, 1, 48]. x∈[0, 3], y∈[0, 24]. Split the rnn_matmul op output into 4 copies, each copy performs a different activation function calculation, and finally outputs lstm_x_y.tmp_h[1, 1, 48]. x∈[0, 3], y∈[0, 24].
For details, please refer to [rnn_hidden](../paddlejs-backend-webgl/src/ops/shader/rnn/rnn_hidden.ts). For details, please refer to [rnn_hidden](https://github.com/PaddlePaddle/Paddle.js/blob/release/v2.2.5/packages/paddlejs-backend-webgl/src/ops/shader/rnn/rnn_hidden.ts).

4
examples/application/js/converter/RNN_CN.md
View File

@@ -73,11 +73,11 @@ paddle源码实现：https://github.com/PaddlePaddle/Paddle/blob/develop/paddle/
3）rnn_cell 3）rnn_cell
计算方式：将rnn_matmul op输出结果分割成4份，每份执行不同激活函数计算，最后输出lstm_x_y.tmp_c[1, 1, 48]。x∈[0, 3]，y∈[0, 24]。 计算方式：将rnn_matmul op输出结果分割成4份，每份执行不同激活函数计算，最后输出lstm_x_y.tmp_c[1, 1, 48]。x∈[0, 3]，y∈[0, 24]。
详见算子实现：[rnn_cell](../paddlejs-backend-webgl/src/ops/shader/rnn/rnn_cell.ts) 详见算子实现：[rnn_cell](https://github.com/PaddlePaddle/Paddle.js/blob/release/v2.2.5/packages/paddlejs-backend-webgl/src/ops/shader/rnn/rnn_cell.ts)
4）rnn_hidden 4）rnn_hidden
计算方式：将rnn_matmul op输出结果分割成4份，每份执行不同激活函数计算，最后输出lstm_x_y.tmp_h[1, 1, 48]。x∈[0, 3]，y∈[0, 24]。 计算方式：将rnn_matmul op输出结果分割成4份，每份执行不同激活函数计算，最后输出lstm_x_y.tmp_h[1, 1, 48]。x∈[0, 3]，y∈[0, 24]。
详见算子实现：[rnn_hidden](../paddlejs-backend-webgl/src/ops/shader/rnn/rnn_hidden.ts) 详见算子实现：[rnn_hidden](https://github.com/PaddlePaddle/Paddle.js/blob/release/v2.2.5/packages/paddlejs-backend-webgl/src/ops/shader/rnn/rnn_hidden.ts)

2
examples/vision/classification/paddleclas/serving/README.md
View File

@@ -80,7 +80,7 @@ The current default configuration runs the TensorRT engine on GPU. If you want t
## Use VisualDL for serving deployment visualization ## Use VisualDL for serving deployment visualization
You can use VisualDL for [serving deployment visualization](../../../../serving/docs/EN/vdl_management-en.md) , the above model preparation, deployment, configuration modification and client request operations can all be performed based on VisualDL. You can use VisualDL for [serving deployment visualization](../../../../../serving/docs/EN/vdl_management-en.md) , the above model preparation, deployment, configuration modification and client request operations can all be performed based on VisualDL.
The serving deployment of PaddleClas by VisualDL only needs the following three steps: The serving deployment of PaddleClas by VisualDL only needs the following three steps:
```text ```text

2
examples/vision/detection/fastestdet/README_CN.md
View File

@@ -11,7 +11,7 @@
为了方便开发者的测试，下面提供了FastestDet导出的模型，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） 为了方便开发者的测试，下面提供了FastestDet导出的模型，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 | 备注 | | 模型 | 大小 | 精度 | 备注 |
|:---------------------------------------------------------------- |:----- |:----- |:---- | |:---------------------------------------------------------------- |:----- |:----- |:---- |
| [FastestDet](https://bj.bcebos.com/paddlehub/fastdeploy/FastestDetn.onnx) | 969KB | 25.3% | 此模型文件来源于[FastestDet](https://github.com/dog-qiuqiu/FastestDet.git)，BSD-3-Clause license | | [FastestDet](https://bj.bcebos.com/paddlehub/fastdeploy/FastestDet.onnx) | 969KB | 25.3% | 此模型文件来源于[FastestDet](https://github.com/dog-qiuqiu/FastestDet.git)，BSD-3-Clause license |
## 详细部署文档 ## 详细部署文档

2
examples/vision/detection/paddledetection/sophgo/README.md
View File

@@ -5,7 +5,7 @@
目前SOPHGO支持如下模型的部署 目前SOPHGO支持如下模型的部署
- [PP-YOLOE系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyoloe) - [PP-YOLOE系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/ppyoloe)
- [PicoDet系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/picodet) - [PicoDet系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4/configs/picodet)
- [YOLOV8系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/) - [YOLOV8系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.4)
## 准备PP-YOLOE YOLOV8或者PicoDet部署模型以及转换模型 ## 准备PP-YOLOE YOLOV8或者PicoDet部署模型以及转换模型

4
examples/vision/detection/rkyolo/cpp/README.md
View File

@@ -35,7 +35,7 @@ mkdir thirdpartys
### Compile and copy SDK to the thirdpartys folder ### Compile and copy SDK to the thirdpartys folder
Refer to [RK2 generation NPU deployment repository compilation](../../../../../../docs/cn/build_and_install/rknpu2.md). It will generate fastdeploy-0.0.3 directory in the build directory after compilation. Move it to the thirdpartys directory. Refer to [RK2 generation NPU deployment repository compilation](../../../../../docs/cn/build_and_install/rknpu2.md). It will generate fastdeploy-0.0.3 directory in the build directory after compilation. Move it to the thirdpartys directory.
### Copy model files and configuration files to the model folder ### Copy model files and configuration files to the model folder
In the process of Paddle dynamic graph model -> Paddle static graph model -> ONNX model, the ONNX file and the corresponding yaml configuration file will be generated. Please save the configuration file in the model folder. In the process of Paddle dynamic graph model -> Paddle static graph model -> ONNX model, the ONNX file and the corresponding yaml configuration file will be generated. Please save the configuration file in the model folder.
@@ -66,4 +66,4 @@ cd ./build/install
- [Model Description](../../) - [Model Description](../../)
- [Python Deployment](../python) - [Python Deployment](../python)
- [Vision Model Prediction Results](../../../../../../docs/api/vision_results/) - [Vision Model Prediction Results](../../../../../docs/api/vision_results/)

4
examples/vision/detection/rkyolo/cpp/README_CN.md
View File

@@ -35,7 +35,7 @@ mkdir thirdpartys
### 编译并拷贝SDK到thirdpartys文件夹 ### 编译并拷贝SDK到thirdpartys文件夹
请参考[RK2代NPU部署库编译](../../../../../../docs/cn/build_and_install/rknpu2.md)仓库编译SDK，编译完成后，将在build目录下生成 请参考[RK2代NPU部署库编译](../../../../../docs/cn/build_and_install/rknpu2.md)仓库编译SDK，编译完成后，将在build目录下生成
fastdeploy-0.0.3目录，请移动它至thirdpartys目录下. fastdeploy-0.0.3目录，请移动它至thirdpartys目录下.
### 拷贝模型文件，以及配置文件至model文件夹 ### 拷贝模型文件，以及配置文件至model文件夹
@@ -67,4 +67,4 @@ cd ./build/install
- [模型介绍](../../) - [模型介绍](../../)
- [Python部署](../python) - [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/)

4
examples/vision/detection/rkyolo/python/README.md
View File

@@ -3,7 +3,7 @@ English | [简体中文](README_CN.md)
Two steps before deployment Two steps before deployment
- 1. Software and hardware should meet the requirements. Refer to [FastDeploy Environment Requirements](../../../../../../docs/cn/build_and_install/rknpu2.md) - 1. Software and hardware should meet the requirements. Refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/rknpu2.md)
This directory provides examples that `infer.py` fast finishes the deployment of Picodet on RKNPU. The script is as follows This directory provides examples that `infer.py` fast finishes the deployment of Picodet on RKNPU. The script is as follows
@@ -31,5 +31,5 @@ The model needs to be in NHWC format on RKNPU. The normalized image will be embe
- [PaddleDetection Model Description](..) - [PaddleDetection Model Description](..)
- [PaddleDetection C++ Deployment](../cpp) - [PaddleDetection C++ Deployment](../cpp)
- [model prediction Results](../../../../../../docs/api/vision_results/) - [model prediction Results](../../../../../docs/api/vision_results/)
- [Convert PaddleDetection RKNN Model Files](../README.md) - [Convert PaddleDetection RKNN Model Files](../README.md)

4
examples/vision/detection/rkyolo/python/README_CN.md
View File

@@ -3,7 +3,7 @@
在部署前，需确认以下两个步骤 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/rknpu2.md) - 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/rknpu2.md)
本目录下提供`infer.py`快速完成Picodet在RKNPU上部署的示例。执行如下脚本即可完成 本目录下提供`infer.py`快速完成Picodet在RKNPU上部署的示例。执行如下脚本即可完成
@@ -31,5 +31,5 @@ RKNPU上对模型的输入要求是使用NHWC格式，且图片归一化操作
- [PaddleDetection 模型介绍](..) - [PaddleDetection 模型介绍](..)
- [PaddleDetection C++部署](../cpp) - [PaddleDetection C++部署](../cpp)
- [模型预测结果说明](../../../../../../docs/api/vision_results/) - [模型预测结果说明](../../../../../docs/api/vision_results/)
- [转换PaddleDetection RKNN模型文档](../README.md) - [转换PaddleDetection RKNN模型文档](../README.md)

144
examples/vision/faceid/adaface/python/README_CN.md
View File

@@ -1,33 +1,125 @@
[English](README.md) | 简体中文 # AdaFace Python部署示例
# AdaFace准备部署模型 本目录下提供infer_xxx.py快速完成AdaFace模型在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
- [PaddleClas](https://github.com/PaddlePaddle/PaddleClas/) 在部署前，需确认以下两个步骤
- [官方库](https://github.com/PaddlePaddle/PaddleClas/)中训练过后的Paddle模型导出Paddle静态图模型操作后，可进行部署；
## 简介 - 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)
一直以来，低质量图像的人脸识别都具有挑战性，因为低质量图像的人脸属性是模糊和退化的。将这样的图片输入模型时，将不能很好的实现分类。 - 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
而在人脸识别任务中，我们经常会利用opencv的仿射变换来矫正人脸数据，这时数据会出现低质量退化的现象。如何解决低质量图片的分类问题成为了模型落地时的痛点问题。
在AdaFace这项工作中，作者在损失函数中引入了另一个因素，即图像质量。作者认为，强调错误分类样本的策略应根据其图像质量进行调整。 以AdaFace为例子, 提供`infer.py`快速完成AdaFace在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
具体来说，简单或困难样本的相对重要性应该基于样本的图像质量来给定。据此作者提出了一种新的损失函数来通过图像质量强调不同的困难样本的重要性。
由上，AdaFace缓解了低质量图片在输入网络后输出结果精度变低的情况，更加适合在人脸识别任务落地中使用。 ```bash
#下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vision/faceid/adaface/python/
#下载AdaFace模型文件和测试图片
#下载测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/rknpu2/face_demo.zip
unzip face_demo.zip
# 如果为Paddle模型，运行以下代码
wget https://bj.bcebos.com/paddlehub/fastdeploy/mobilefacenet_adaface.tgz
tar zxvf mobilefacenet_adaface.tgz -C ./
# CPU推理
python infer.py --model mobilefacenet_adaface/mobilefacenet_adaface.pdmodel \
--params_file mobilefacenet_adaface/mobilefacenet_adaface.pdiparams \
--face face_0.jpg \
--face_positive face_1.jpg \
--face_negative face_2.jpg \
--device cpu
# GPU推理
python infer.py --model mobilefacenet_adaface/mobilefacenet_adaface.pdmodel \
--params_file mobilefacenet_adaface/mobilefacenet_adaface.pdiparams \
--face face_0.jpg \
--face_positive face_1.jpg \
--face_negative face_2.jpg \
--device gpu
# GPU上使用TensorRT推理
python infer.py --model mobilefacenet_adaface/mobilefacenet_adaface.pdmodel \
--params_file mobilefacenet_adaface/mobilefacenet_adaface.pdiparams \
--face face_0.jpg \
--face_positive face_1.jpg \
--face_negative face_2.jpg \
--device gpu \
--use_trt True
# 昆仑芯XPU推理
python infer.py --model mobilefacenet_adaface/mobilefacenet_adaface.pdmodel \
--params_file mobilefacenet_adaface/mobilefacenet_adaface.pdiparams \
--face test_lite_focal_arcface_0.JPG \
--face_positive test_lite_focal_arcface_1.JPG \
--face_negative test_lite_focal_arcface_2.JPG \
--device kunlunxin
```
运行完成可视化结果如下图所示
<div width="700">
<img width="220" float="left" src="https://user-images.githubusercontent.com/67993288/184321537-860bf857-0101-4e92-a74c-48e8658d838c.JPG">
<img width="220" float="left" src="https://user-images.githubusercontent.com/67993288/184322004-a551e6e4-6f47-454e-95d6-f8ba2f47b516.JPG">
<img width="220" float="left" src="https://user-images.githubusercontent.com/67993288/184321622-d9a494c3-72f3-47f1-97c5-8a2372de491f.JPG">
</div>
```bash
FaceRecognitionResult: [Dim(512), Min(-0.133213), Max(0.148838), Mean(0.000293)]
FaceRecognitionResult: [Dim(512), Min(-0.102777), Max(0.120130), Mean(0.000615)]
FaceRecognitionResult: [Dim(512), Min(-0.116685), Max(0.142919), Mean(0.001595)]
Cosine 01: 0.7483505506964364
Cosine 02: -0.09605773855893639
```
## AdaFace Python接口
```python
fastdeploy.vision.faceid.AdaFace(model_file, params_file=None, runtime_option=None, model_format=ModelFormat.PADDLE)
```
AdaFace模型加载和初始化，其中model_file为导出的ONNX模型格式或PADDLE静态图格式
**参数**
> * **model_file**(str): 模型文件路径
> * **params_file**(str): 参数文件路径，当模型格式为ONNX格式时，此参数无需设定
> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
> * **model_format**(ModelFormat): 模型格式，默认为PADDLE
### predict函数
> ```python
> AdaFace.predict(image_data)
> ```
>
> 模型预测结口，输入图像直接输出检测结果。
>
> **参数**
>
> > * **image_data**(np.ndarray): 输入数据，注意需为HWC，BGR格式
> **返回**
>
> > 返回`fastdeploy.vision.FaceRecognitionResult`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
#### 预处理参数
用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
#### AdaFacePreprocessor的成员变量
以下变量为AdaFacePreprocessor的成员变量
> > * **size**(list[int]): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[112, 112]
> > * **alpha**(list[float]): 预处理归一化的alpha值，计算公式为`x'=x*alpha+beta`，alpha默认为[1. / 127.5, 1.f / 127.5, 1. / 127.5]
> > * **beta**(list[float]): 预处理归一化的beta值，计算公式为`x'=x*alpha+beta`，beta默认为[-1.f, -1.f, -1.f]
> > * **swap_rb**(bool): 预处理是否将BGR转换成RGB，默认True
#### AdaFacePostprocessor的成员变量
以下变量为AdaFacePostprocessor的成员变量
> > * **l2_normalize**(bool): 输出人脸向量之前是否执行l2归一化，默认False
## 导出Paddle静态图模型 ## 其它文档
以AdaFace为例:
训练和导出代码，请参考[AIStudio](https://aistudio.baidu.com/aistudio/projectdetail/4479879?contributionType=1)
- [AdaFace 模型介绍](..)
## 下载预训练Paddle静态图模型 - [AdaFace C++部署](../cpp)
- [模型预测结果说明](../../../../../docs/api/vision_results/)
为了方便开发者的测试，下面提供了我转换过的各系列模型，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）其中精度指标来源于AIStudio中对各模型的介绍。 - [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
| 模型 | 大小 | 精度 (AgeDB_30) |
|:----------------------------------------------------------------------------------------------|:------|:--------------|
| [AdaFace-MobileFacenet](https://bj.bcebos.com/paddlehub/fastdeploy/mobilefacenet_adaface.tgz) | 3.2MB | 95.5 |
## 详细部署文档
- [Python部署](python)
- [C++部署](cpp)

4
examples/vision/faceid/insightface/rknpu2/cpp/README.md
View File

@@ -44,7 +44,7 @@ unzip face_demo.zip
</div> </div>
以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考: 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)
## InsightFace C++接口 ## InsightFace C++接口
@@ -113,7 +113,7 @@ VPL模型加载和初始化，其中model_file为导出的ONNX模型格式。
> **参数** > **参数**
> >
> > * **im**: 输入图像，注意需为HWC，BGR格式 > > * **im**: 输入图像，注意需为HWC，BGR格式
> > * **result**: 检测结果，包括检测框，各个框的置信度, FaceRecognitionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/) > > * **result**: 检测结果，包括检测框，各个框的置信度, FaceRecognitionResult说明参考[视觉模型预测结果](../../../../../../docs/api/vision_results/)
### 修改预处理以及后处理的参数 ### 修改预处理以及后处理的参数
预处理和后处理的参数的需要通过修改InsightFaceRecognitionPostprocessor，InsightFaceRecognitionPreprocessor的成员变量来进行修改。 预处理和后处理的参数的需要通过修改InsightFaceRecognitionPostprocessor，InsightFaceRecognitionPreprocessor的成员变量来进行修改。

6
examples/vision/faceid/insightface/rknpu2/python/README_CN.md
View File

@@ -83,7 +83,7 @@ ArcFace模型加载和初始化，其中model_file为导出的ONNX模型格式
> **返回** > **返回**
> >
> > 返回`fastdeploy.vision.FaceRecognitionResult`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.FaceRecognitionResult`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 ### 类成员属性
#### 预处理参数 #### 预处理参数
@@ -104,5 +104,5 @@ ArcFace模型加载和初始化，其中model_file为导出的ONNX模型格式
- [InsightFace 模型介绍](..) - [InsightFace 模型介绍](..)
- [InsightFace C++部署](../cpp) - [InsightFace C++部署](../cpp)
- [模型预测结果说明](../../../../../docs/api/vision_results/) - [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) - [如何切换模型推理后端引擎](../../../../../../docs/cn/faq/how_to_change_backend.md)

65
examples/vision/segmentation/paddleseg/README_CN.md
View File

@@ -1,34 +1,47 @@
[English](README.md) | 简体中文 # PaddleSeg 模型部署
# 视觉模型部署
本目录下提供了各类视觉模型的部署，主要涵盖以下任务类型 ## 模型版本说明
| 任务类型 | 说明 | 预测结果结构体 | - [PaddleSeg develop](https://github.com/PaddlePaddle/PaddleSeg/tree/develop)
|:-------------- |:----------------------------------- |:-------------------------------------------------------------------------------- |
| Detection | 目标检测，输入图像，检测图像中物体位置，并返回检测框坐标及类别和置信度 | [DetectionResult](../../docs/api/vision_results/detection_result.md) |
| Segmentation | 语义分割，输入图像，给出图像中每个像素的分类及置信度 | [SegmentationResult](../../docs/api/vision_results/segmentation_result.md) |
| Classification | 图像分类，输入图像，给出图像的分类结果和置信度 | [ClassifyResult](../../docs/api/vision_results/classification_result.md) |
| FaceDetection | 人脸检测，输入图像，检测图像中人脸位置，并返回检测框坐标及人脸关键点 | [FaceDetectionResult](../../docs/api/vision_results/face_detection_result.md) |
| FaceAlignment | 人脸对齐(人脸关键点检测)，输入图像，返回人脸关键点 | [FaceAlignmentResult](../../docs/api/vision_results/face_alignment_result.md) |
| KeypointDetection | 关键点检测，输入图像，返回图像中人物行为的各个关键点坐标和置信度 | [KeyPointDetectionResult](../../docs/api/vision_results/keypointdetection_result.md) |
| FaceRecognition | 人脸识别，输入图像，返回可用于相似度计算的人脸特征的embedding | [FaceRecognitionResult](../../docs/api/vision_results/face_recognition_result.md) |
| Matting | 抠图，输入图像，返回图片的前景每个像素点的Alpha值 | [MattingResult](../../docs/api/vision_results/matting_result.md) |
| OCR | 文本框检测，分类，文本框内容识别，输入图像，返回文本框坐标，文本框的方向类别以及框内的文本内容 | [OCRResult](../../docs/api/vision_results/ocr_result.md) |
| MOT | 多目标跟踪，输入图像，检测图像中物体位置，并返回检测框坐标，对象id及类别置信度 | [MOTResult](../../docs/api/vision_results/mot_result.md) |
| HeadPose | 头部姿态估计，返回头部欧拉角 | [HeadPoseResult](../../docs/api/vision_results/headpose_result.md) |
## FastDeploy API设计 目前FastDeploy支持如下模型的部署
视觉模型具有较有统一任务范式，在设计API时（包括C++/Python），FastDeploy将视觉模型的部署拆分为四个步骤 - [U-Net系列模型](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/unet/README.md)
- [PP-LiteSeg系列模型](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/pp_liteseg/README.md)
- [PP-HumanSeg系列模型](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/contrib/PP-HumanSeg/README.md)
- [FCN系列模型](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/fcn/README.md)
- [DeepLabV3系列模型](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/configs/deeplabv3/README.md)
- 模型加载 【注意】如你部署的为**PP-Matting**、**PP-HumanMatting**以及**ModNet**请参考[Matting模型部署](../../matting)
- 图像预处理
- 模型推理
- 推理结果后处理
FastDeploy针对飞桨的视觉套件，以及外部热门模型，提供端到端的部署服务，用户只需准备模型，按以下步骤即可完成整个模型的部署 ## 准备PaddleSeg部署模型
- 加载模型 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)
- 调用`predict`接口
FastDeploy在各视觉模型部署时，也支持一键切换后端推理引擎，详情参阅[如何切换模型推理引擎](../../docs/cn/faq/how_to_change_backend.md)。 **注意**
- PaddleSeg导出的模型包含`model.pdmodel`、`model.pdiparams`和`deploy.yaml`三个文件，FastDeploy会从yaml文件中获取模型在推理时需要的预处理信息
## 下载预训练模型
为了方便开发者的测试，下面提供了PaddleSeg导出的部分模型
- without-argmax导出方式为：**不指定**`--input_shape`，**指定**`--output_op none`
- with-argmax导出方式为：**不指定**`--input_shape`，**指定**`--output_op argmax`
开发者可直接下载使用。
| 模型 | 参数文件大小 |输入Shape | mIoU | mIoU (flip) | mIoU (ms+flip) |
|:---------------------------------------------------------------- |:----- |:----- | :----- | :----- | :----- |
| [Unet-cityscapes-with-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/Unet_cityscapes_with_argmax_infer.tgz) \| [Unet-cityscapes-without-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/Unet_cityscapes_without_argmax_infer.tgz) | 52MB | 1024x512 | 65.00% | 66.02% | 66.89% |
| [PP-LiteSeg-B(STDC2)-cityscapes-with-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/PP_LiteSeg_B_STDC2_cityscapes_with_argmax_infer.tgz) \| [PP-LiteSeg-B(STDC2)-cityscapes-without-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/PP_LiteSeg_B_STDC2_cityscapes_without_argmax_infer.tgz) | 31MB | 1024x512 | 79.04% | 79.52% | 79.85% |
|[PP-HumanSegV1-Lite-with-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/Portrait_PP_HumanSegV1_Lite_with_argmax_infer.tgz) \| [PP-HumanSegV1-Lite-without-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV1_Lite_infer.tgz) | 543KB | 192x192 | 86.2% | - | - |
|[PP-HumanSegV2-Lite-with-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV2_Lite_192x192_with_argmax_infer.tgz) \| [PP-HumanSegV2-Lite-without-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV2_Lite_192x192_infer.tgz) | 12MB | 192x192 | 92.52% | - | - |
| [PP-HumanSegV2-Mobile-with-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV2_Mobile_192x192_with_argmax_infer.tgz) \| [PP-HumanSegV2-Mobile-without-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV2_Mobile_192x192_infer.tgz) | 29MB | 192x192 | 93.13% | - | - |
|[PP-HumanSegV1-Server-with-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV1_Server_with_argmax_infer.tgz) \| [PP-HumanSegV1-Server-without-argmax(通用人像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/PP_HumanSegV1_Server_infer.tgz) | 103MB | 512x512 | 96.47% | - | - |
| [Portait-PP-HumanSegV2-Lite-with-argmax(肖像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/Portrait_PP_HumanSegV2_Lite_256x144_with_argmax_infer.tgz) \| [Portait-PP-HumanSegV2-Lite-without-argmax(肖像分割模型)](https://bj.bcebos.com/paddlehub/fastdeploy/Portrait_PP_HumanSegV2_Lite_256x144_infer.tgz) | 3.6M | 256x144 | 96.63% | - | - |
| [FCN-HRNet-W18-cityscapes-with-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/FCN_HRNet_W18_cityscapes_with_argmax_infer.tgz) \| [FCN-HRNet-W18-cityscapes-without-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/FCN_HRNet_W18_cityscapes_without_argmax_infer.tgz)(暂时不支持ONNXRuntime的GPU推理) | 37MB | 1024x512 | 78.97% | 79.49% | 79.74% |
| [Deeplabv3-ResNet101-OS8-cityscapes-with-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/Deeplabv3_ResNet101_OS8_cityscapes_with_argmax_infer.tgz) \| [Deeplabv3-ResNet101-OS8-cityscapes-without-argmax](https://bj.bcebos.com/paddlehub/fastdeploy/Deeplabv3_ResNet101_OS8_cityscapes_without_argmax_infer.tgz) | 150MB | 1024x512 | 79.90% | 80.22% | 80.47% |
## 详细部署文档
- [Python部署](python)
- [C++部署](cpp)

6
tutorials/intel_gpu/cpp/README_CN.md
View File

@@ -1,11 +1,11 @@
English | [中文](README_CN.md) [English](README.md) | 中文
# PaddleClas Python Example # PaddleClas Python Example
在部署前，需确认以下两个步骤 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) - 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. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md) - 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
**注意** 本文档依赖FastDeploy>=1.0.2版本，或nightly built版本。 **注意** 本文档依赖FastDeploy>=1.0.2版本，或nightly built版本。

6
tutorials/intel_gpu/python/README_CN.md
View File

@@ -1,11 +1,11 @@
English | [中文](README_CN.md) [English](README.md) | 中文
# PaddleClas Python Example # PaddleClas Python Example
在部署前，需确认以下两个步骤 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) - 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. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md) - 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
```bash ```bash
# Get FastDeploy codes # Get FastDeploy codes

4
tutorials/multi_thread/cpp/pipeline/README.md
View File

@@ -45,9 +45,9 @@ wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_
# KunlunXin XPU multi-thread inference # KunlunXin XPU multi-thread inference
./multi_thread_demo ./ch_PP-OCRv3_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer ./ppocr_keys_v1.txt ./12.jpg 4 1 ./multi_thread_demo ./ch_PP-OCRv3_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer ./ppocr_keys_v1.txt ./12.jpg 4 1
>> **Notice**: the last number in above command is thread number >> **Notice**: the last number in above command is thread number
```
The above command works for Linux or MacOS. For SDK in Windows, refer to: 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 result returned after running is as follows The result returned after running is as follows
``` ```

4
tutorials/multi_thread/cpp/pipeline/README_CN.md
View File

@@ -45,9 +45,9 @@ wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_
# 昆仑芯XPU推理 # 昆仑芯XPU推理
./multi_thread_demo ./ch_PP-OCRv3_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer ./ppocr_keys_v1.txt ./12.jpg 4 1 ./multi_thread_demo ./ch_PP-OCRv3_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer ./ppocr_keys_v1.txt ./12.jpg 4 1
>> **注意**: 最后一位数字表示线程数 >> **注意**: 最后一位数字表示线程数
```
以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考: 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)
运行完成后返回结果如下所示 运行完成后返回结果如下所示
``` ```

4
tutorials/multi_thread/cpp/single_model/README.md
View File

@@ -1,4 +1,4 @@
English | [中文]((README_CN.md)) English | [中文](README_CN.md)
# Example of PaddleClas models Python Deployment # Example of PaddleClas models Python Deployment
@@ -36,7 +36,7 @@ wget https://gitee.com/paddlepaddle/PaddleClas/raw/release/2.4/deploy/images/Ima
>> **Notice**: the last number in above command is thread number >> **Notice**: the last number in above command is thread number
The above command works for Linux or MacOS. For SDK in Windows, refer to: 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 result returned after running is as follows The result returned after running is as follows
``` ```

2
tutorials/multi_thread/cpp/single_model/README_CN.md
View File

@@ -36,7 +36,7 @@ wget https://gitee.com/paddlepaddle/PaddleClas/raw/release/2.4/deploy/images/Ima
>> **注意**: 最后一位数字表示线程数 >> **注意**: 最后一位数字表示线程数
以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考: 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)
运行完成后返回结果如下所示 运行完成后返回结果如下所示
``` ```