diff --git a/README.md b/README.md index f18766817c..e8f014f6ff 120000 --- a/README.md +++ b/README.md @@ -1 +1 @@ -README_EN.md \ No newline at end of file +README_CN.md diff --git a/README_CN.md b/README_CN.md index b8eed04585..0b74d1f02b 100644 --- a/README_CN.md +++ b/README_CN.md @@ -1,4 +1,4 @@ -[English](README.md) | 简体中文 +[English](README_EN.md) | 简体中文 ![⚡️FastDeploy](https://user-images.githubusercontent.com/31974251/185771818-5d4423cd-c94c-4a49-9894-bc7a8d1c29d0.png) @@ -18,13 +18,13 @@ **⚡️FastDeploy**是一款**易用高效**的推理部署开发套件。覆盖业界🔥**热门CV、NLP、Speech的AI模型**并提供📦**开箱即用**的部署体验，包括图像分类、目标检测、图像分割、人脸检测、人脸识别、人体关键点识别、文字识别、语义理解等多任务，满足开发者**多场景**，**多硬件**、**多平台**的产业部署需求。 -| [Object Detection](examples/vision) | [3D Object Detection](https://github.com/PaddlePaddle/FastDeploy/issues/6) | [Semantic Segmentation](examples/vision/segmentation/paddleseg) | [Potrait Segmentation](examples/vision/segmentation/paddleseg) | +| [Object Detection](examples/vision/detection) | [3D Object Detection](https://github.com/PaddlePaddle/FastDeploy/issues/6) | [Semantic Segmentation](examples/vision/segmentation/paddleseg) | [Potrait Segmentation](examples/vision/segmentation/paddleseg) | |:---------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| | | | | | -| [**Image Matting**](examples/vision/matting) | [**Real-Time Matting**](examples/vision/matting) | [**OCR**](examples/vision/ocr) |[**Face Alignment**](examples/vision/ocr) +| [**Image Matting**](examples/vision/matting) | [**Real-Time Matting**](examples/vision/matting) | [**OCR**](examples/vision/ocr) |[**Face Alignment**](examples/vision/facealign) | | | | | | [**Pose Estimation**](examples/vision/keypointdetection) | [**Behavior Recognition**](https://github.com/PaddlePaddle/FastDeploy/issues/6) | [**NLP**](examples/text) |[**Speech**](examples/audio/pp-tts) -| | | |

**input** ：早上好，今天是2020
/10/29，最低温度是-3°C。

**output**: [](https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/001.wav)

| +| | | |

**input** ：早上好今天是2020
/10/29，最低温度是-3°C。

**output**: [](https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/001.wav)

| ## 近期更新 @@ -40,7 +40,7 @@ - **🖥️ 服务端部署：支持推理速度更快的后端，支持更多的模型** - 集成 Paddle Inference TensorRT后端，并保证其使用与Paddle Inference、TensorRT、OpenVINO、ONNX Runtime、Paddle Lite等一致的开发体验； - 支持并测试 Graphcore IPU 通过 Paddle Inference后端; - - 优化[一键模型量化工具](tools/quantization)，支持YOLOv7、YOLOv6、YOLOv5等视觉模型，在CPU和GPU推理速度可提升1.5～2倍； + - 优化[一键模型自动化压缩工具](./tools/auto_compression)，支持YOLOv7、YOLOv6、YOLOv5等视觉模型，在CPU和GPU推理速度可提升1.5～2倍； - 新增 [PP-Tracking](./examples/vision/tracking/pptracking) 和 [RobustVideoMatting](./examples/vision/matting) 等模型； - 🔥 **2022.10.24：Release FastDeploy [release v0.4.0](https://github.com/PaddlePaddle/FastDeploy/tree/release/0.4.0)** diff --git a/README_EN.md b/README_EN.md index d30fd587ad..5fdfe0c554 100644 --- a/README_EN.md +++ b/README_EN.md @@ -20,13 +20,13 @@ English | [简体中文](README_CN.md) **⚡️FastDeploy** is an **accessible and efficient** deployment Development Toolkit. It covers 🔥**critical CV、NLP、Speech AI models** in the industry and provides 📦**out-of-the-box** deployment experience. It covers image classification, object detection, image segmentation, face detection, face recognition, human keypoint detection, OCR, semantic understanding and other tasks to meet developers' industrial deployment needs for **multi-scenario**, **multi-hardware** and **multi-platform** . -| [Object Detection](examples/vision) | [3D Object Detection](https://github.com/PaddlePaddle/FastDeploy/issues/6) | [Semantic Segmentation](examples/vision/segmentation/paddleseg) | [Potrait Segmentation](examples/vision/segmentation/paddleseg) | +| [Object Detection](examples/vision/detection) | [3D Object Detection](https://github.com/PaddlePaddle/FastDeploy/issues/6) | [Semantic Segmentation](examples/vision/segmentation/paddleseg) | [Potrait Segmentation](examples/vision/segmentation/paddleseg) | |:---------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| | | | | | -| [**Image Matting**](examples/vision/matting) | [**Real-Time Matting**](examples/vision/matting) | [**OCR**](examples/vision/ocr) |[**Face Alignment**](examples/vision/ocr) +| [**Image Matting**](examples/vision/matting) | [**Real-Time Matting**](examples/vision/matting) | [**OCR**](examples/vision/ocr) |[**Face Alignment**](examples/vision/facealign) | | | | | | [**Pose Estimation**](examples/vision/keypointdetection) | [**Behavior Recognition**](https://github.com/PaddlePaddle/FastDeploy/issues/6) | [**NLP**](examples/text) |[**Speech**](examples/audio/pp-tts) -| | | |

**input** ：Life was like a box of chocolates, you never know what you're gonna get.

**output**: [](https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/tacotron2_ljspeech_waveflow_samples_0.2/sentence_1.wav)

| +| | | |

**input** ：早上好今天是2020
/10/29，最低温度是-3°C。

**output**: [](https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/001.wav)

| ## 📣 Recent Updates diff --git a/docs/api_docs/python/README.md b/docs/api_docs/python/README.md index c6bccc576c..789ae76bbc 100644 --- a/docs/api_docs/python/README.md +++ b/docs/api_docs/python/README.md @@ -2,7 +2,7 @@ This directory help to generate Python API documents for FastDeploy. -1. First, to generate the latest api documents, you need to install the latest FastDeploy, refer [build and install](en/build_and_install) to build FastDeploy python wheel package with the latest code. +1. First, to generate the latest api documents, you need to install the latest FastDeploy, refer [build and install](../../cn/build_and_install) to build FastDeploy python wheel package with the latest code. 2. After installed FastDeploy in your python environment, there are some dependencies need to install, execute command `pip install -r requirements.txt` in this directory 3. Execute command `make html` to generate API documents diff --git a/docs/cn/build_and_install/android.md b/docs/cn/build_and_install/android.md index 899ec2985a..fb945ed3a0 100644 --- a/docs/cn/build_and_install/android.md +++ b/docs/cn/build_and_install/android.md @@ -102,4 +102,4 @@ make install 如何使用FastDeploy Android C++ SDK 请参考使用案例文档： - [图像分类Android使用文档](../../../examples/vision/classification/paddleclas/android/README.md) - [目标检测Android使用文档](../../../examples/vision/detection/paddledetection/android/README.md) -- [在 Android 通过 JNI 中使用 FastDeploy C++ SDK](../../../../../docs/cn/faq/use_cpp_sdk_on_android.md) +- [在 Android 通过 JNI 中使用 FastDeploy C++ SDK](../../cn/faq/use_cpp_sdk_on_android.md) diff --git a/docs/cn/faq/use_sdk_on_windows.md b/docs/cn/faq/use_sdk_on_windows.md index be1e1ab0a0..7209d50bb3 100644 --- a/docs/cn/faq/use_sdk_on_windows.md +++ b/docs/cn/faq/use_sdk_on_windows.md @@ -218,7 +218,7 @@ D:\qiuyanjun\fastdeploy_test\infer_ppyoloe\x64\Release\infer_ppyoloe.exe ![image](https://user-images.githubusercontent.com/31974251/192144782-79bccf8f-65d0-4f22-9f41-81751c530319.png) （2）其中infer_ppyoloe.cpp的代码可以直接从examples中的代码拷贝过来： -- [examples/vision/detection/paddledetection/cpp/infer_ppyoloe.cc](../../examples/vision/detection/paddledetection/cpp/infer_ppyoloe.cc) +- [examples/vision/detection/paddledetection/cpp/infer_ppyoloe.cc](../../../examples/vision/detection/paddledetection/cpp/infer_ppyoloe.cc) （3）CMakeLists.txt主要包括配置FastDeploy C++ SDK的路径，如果是GPU版本的SDK，还需要配置CUDA_DIRECTORY为CUDA的安装路径，CMakeLists.txt的配置如下： diff --git a/docs/en/faq/use_sdk_on_windows.md b/docs/en/faq/use_sdk_on_windows.md index f75c6d911b..367f6e1df1 100644 --- a/docs/en/faq/use_sdk_on_windows.md +++ b/docs/en/faq/use_sdk_on_windows.md @@ -179,7 +179,7 @@ D:\qiuyanjun\fastdeploy_build\built\fastdeploy-win-x64-gpu-0.2.1\third_libs\inst ![image](https://user-images.githubusercontent.com/31974251/192827842-1f05d435-8a3e-492b-a3b7-d5e88f85f814.png) -Compile successfully, you can see the exe saved in： +Compile successfully, you can see the exe saved in： ```bat D:\qiuyanjun\fastdeploy_test\infer_ppyoloe\x64\Release\infer_ppyoloe.exe @@ -221,7 +221,7 @@ This section is for CMake users and describes how to create CMake projects in Vi ![image](https://user-images.githubusercontent.com/31974251/192144782-79bccf8f-65d0-4f22-9f41-81751c530319.png) （2）The code of infer_ppyoloe.cpp can be copied directly from the code in examples： -- [examples/vision/detection/paddledetection/cpp/infer_ppyoloe.cc](../../examples/vision/detection/paddledetection/cpp/infer_ppyoloe.cc) +- [examples/vision/detection/paddledetection/cpp/infer_ppyoloe.cc](../../../examples/vision/detection/paddledetection/cpp/infer_ppyoloe.cc) （3）CMakeLists.txt mainly includes the configuration of the path of FastDeploy C++ SDK, if it is the GPU version of the SDK, you also need to configure CUDA_DIRECTORY as the installation path of CUDA, the configuration of CMakeLists.txt is as follows： @@ -361,7 +361,7 @@ A brief description of the usage is as follows. #### 4.1.2 fastdeploy_init.bat View all dll, lib and include paths in the SDK
-Go to the root directory of the SDK and run the show command to view all the dll, lib and include paths in the SDK. In the following command, %cd% means the current directory (the root directory of the SDK). +Go to the root directory of the SDK and run the show command to view all the dll, lib and include paths in the SDK. In the following command, %cd% means the current directory (the root directory of the SDK). ```bat D:\path-to-fastdeploy-sdk-dir>fastdeploy_init.bat show %cd% @@ -504,7 +504,7 @@ copy /Y %FASTDEPLOY_HOME%\third_libs\install\yaml-cpp\lib\*.dll Release\ copy /Y %FASTDEPLOY_HOME%\third_libs\install\openvino\bin\*.dll Release\ copy /Y %FASTDEPLOY_HOME%\third_libs\install\openvino\bin\*.xml Release\ copy /Y %FASTDEPLOY_HOME%\third_libs\install\openvino\3rdparty\tbb\bin\*.dll Release\ -``` +``` Note that if you compile the latest SDK or version >0.2.1 by yourself, the opencv and openvino directory structure has changed and the path needs to be modified appropriately. For example： ```bat copy /Y %FASTDEPLOY_HOME%\third_libs\install\opencv\build\x64\vc15\bin\*.dll Release\ diff --git a/docs/en/quantize.md b/docs/en/quantize.md index effce0700b..c4535808e1 100644 --- a/docs/en/quantize.md +++ b/docs/en/quantize.md @@ -27,7 +27,7 @@ FastDeploy基于PaddleSlim, 集成了一键模型量化的工具, 同时, FastDe ### 用户使用FastDeploy一键模型量化工具来量化模型 Fastdeploy基于PaddleSlim, 为用户提供了一键模型量化的工具，请参考如下文档进行模型量化. -- [FastDeploy 一键模型量化](../../tools/quantization/) +- [FastDeploy 一键模型量化](../../tools/auto_compression/) 当用户获得产出的量化模型之后，即可以使用FastDeploy来部署量化模型. diff --git a/examples/runtime/README.md b/examples/runtime/README.md index 849d6ecef6..18651bd699 100644 --- a/examples/runtime/README.md +++ b/examples/runtime/README.md @@ -1,16 +1,16 @@ -# FastDeploy Runtime推理示例 +# FastDeploy Runtime examples -| 示例代码 | 编程语言 | 说明 | +| Example Code | Program Language | Description | | :------- | :------- | :---- | -| python/infer_paddle_paddle_inference.py | Python | paddle模型通过paddle inference在cpu/gpu上的推理 | -| python/infer_paddle_tensorrt.py | Python | paddle模型通过tensorrt在gpu上的推理 | -| python/infer_paddle_openvino.py | Python | paddle模型通过openvino在cpu上的推理 | -| python/infer_paddle_onnxruntime.py | Python | paddle模型通过onnx runtime在cpu/gpu上的推理 | -| python/infer_onnx_openvino.py | Python | onnx模型通过openvino在cpu上的推理 | -| python/infer_onnx_tensorrt.py | Python | onnx模型通过tensorrt在gpu上的推理 | -| cpp/infer_paddle_paddle_inference.cc | C++ | paddle模型通过paddle inference在cpu/gpu上的推理 | -| cpp/infer_paddle_tensorrt.cc | C++ | paddle模型通过tensorrt在gpu上的推理 | -| cpp/infer_paddle_openvino.cc | C++ | paddle模型通过openvino在cpu上的推理 | -| cpp/infer_paddle_onnxruntime.cc | C++ | paddle模型通过onnx runtime在cpu/gpu上的推理 | -| cpp/infer_onnx_openvino.cc | C++ | onnx模型通过openvino在cpu上的推理 | -| cpp/infer_onnx_tensorrt.cc | C++ | onnx模型通过tensorrt在gpu上的推理 | +| python/infer_paddle_paddle_inference.py | Python | Deploy Paddle model with Paddle Inference(CPU/GPU) | +| python/infer_paddle_tensorrt.py | Python | Deploy Paddle model with TensorRT(GPU) | +| python/infer_paddle_openvino.py | Python | Deploy Paddle model with OpenVINO(CPU) | +| python/infer_paddle_onnxruntime.py | Python | Deploy Paddle model with ONNX Runtime(CPU/GPU) | +| python/infer_onnx_openvino.py | Python | Deploy ONNX model with OpenVINO(CPU) | +| python/infer_onnx_tensorrt.py | Python | Deploy ONNX model with TensorRT(GPU) | +| cpp/infer_paddle_paddle_inference.cc | C++ | Deploy Paddle model with Paddle Inference(CPU/GPU) | +| cpp/infer_paddle_tensorrt.cc | C++ | Deploy Paddle model with TensorRT(GPU) | +| cpp/infer_paddle_openvino.cc | C++ | Deploy Paddle model with OpenVINO(CPU | +| cpp/infer_paddle_onnxruntime.cc | C++ | Deploy Paddle model with ONNX Runtime(CPU/GPU) | +| cpp/infer_onnx_openvino.cc | C++ | Deploy ONNX model with OpenVINO(CPU) | +| cpp/infer_onnx_tensorrt.cc | C++ | Deploy ONNX model with TensorRT(GPU) | diff --git a/examples/text/ernie-3.0/serving/README.md b/examples/text/ernie-3.0/serving/README.md index df969724a2..487a5eddca 100644 --- a/examples/text/ernie-3.0/serving/README.md +++ b/examples/text/ernie-3.0/serving/README.md @@ -168,4 +168,4 @@ entity: 华夏 label: LOC pos: [14, 15] ## 配置修改 -当前分类任务(ernie_seqcls_model/config.pbtxt)默认配置在CPU上运行OpenVINO引擎; 序列标注任务默认配置在GPU上运行Paddle引擎。如果要在CPU/GPU或其他推理引擎上运行, 需要修改配置，详情请参考[配置文档](../../../../../serving/docs/zh_CN/model_configuration.md) +当前分类任务(ernie_seqcls_model/config.pbtxt)默认配置在CPU上运行OpenVINO引擎; 序列标注任务默认配置在GPU上运行Paddle引擎。如果要在CPU/GPU或其他推理引擎上运行, 需要修改配置，详情请参考[配置文档](../../../../serving/docs/zh_CN/model_configuration.md) diff --git a/examples/vision/README.md b/examples/vision/README.md index f439d6e721..347da1be75 100755 --- a/examples/vision/README.md +++ b/examples/vision/README.md @@ -30,4 +30,4 @@ FastDeploy针对飞桨的视觉套件，以及外部热门模型，提供端到 - 加载模型 - 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/runtime/how_to_change_backend.md)。 +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)。 diff --git a/examples/vision/classification/paddleclas/quantize/cpp/README.md b/examples/vision/classification/paddleclas/quantize/cpp/README.md index e2e625dbd5..76ffa0be9b 100644 --- a/examples/vision/classification/paddleclas/quantize/cpp/README.md +++ b/examples/vision/classification/paddleclas/quantize/cpp/README.md @@ -8,7 +8,7 @@ ### 量化模型准备 - 1. 用户可以直接使用由FastDeploy提供的量化模型进行部署. -- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../../../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署.(注意: 推理量化后的分类模型仍然需要FP32模型文件夹下的inference_cls.yaml文件, 自行量化的模型文件夹内不包含此yaml文件, 用户从FP32模型文件夹下复制此yaml文件到量化后的模型文件夹内即可.) +- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../../../../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署.(注意: 推理量化后的分类模型仍然需要FP32模型文件夹下的inference_cls.yaml文件, 自行量化的模型文件夹内不包含此yaml文件, 用户从FP32模型文件夹下复制此yaml文件到量化后的模型文件夹内即可.) ## 以量化后的ResNet50_Vd模型为例, 进行部署 在本目录执行如下命令即可完成编译,以及量化模型部署. diff --git a/examples/vision/classification/paddleclas/quantize/python/README.md b/examples/vision/classification/paddleclas/quantize/python/README.md index 00fd7bef9c..6b874e77ab 100644 --- a/examples/vision/classification/paddleclas/quantize/python/README.md +++ b/examples/vision/classification/paddleclas/quantize/python/README.md @@ -8,7 +8,7 @@ ### 量化模型准备 - 1. 用户可以直接使用由FastDeploy提供的量化模型进行部署. -- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署.(注意: 推理量化后的分类模型仍然需要FP32模型文件夹下的inference_cls.yaml文件, 自行量化的模型文件夹内不包含此yaml文件, 用户从FP32模型文件夹下复制此yaml文件到量化后的模型文件夹内即可.) +- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../../../../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署.(注意: 推理量化后的分类模型仍然需要FP32模型文件夹下的inference_cls.yaml文件, 自行量化的模型文件夹内不包含此yaml文件, 用户从FP32模型文件夹下复制此yaml文件到量化后的模型文件夹内即可.) ## 以量化后的ResNet50_Vd模型为例, 进行部署 diff --git a/examples/vision/classification/paddleclas/web/README.md b/examples/vision/classification/paddleclas/web/README.md index 837773cc3f..710dd53ad4 100644 --- a/examples/vision/classification/paddleclas/web/README.md +++ b/examples/vision/classification/paddleclas/web/README.md @@ -6,7 +6,7 @@ ## 前端部署图像分类模型 -图像分类模型web demo使用[**参考文档**](../../../../examples/application/js/web_demo) +图像分类模型web demo使用[**参考文档**](../../../../application/js/web_demo/) ## MobileNet js接口 @@ -34,4 +34,3 @@ console.log(res); - [PaddleClas模型 python部署](../../paddleclas/python/) - [PaddleClas模型 C++部署](../cpp/) - diff --git a/examples/vision/classification/resnet/cpp/README.md b/examples/vision/classification/resnet/cpp/README.md index eb3bff6f48..1180d26c9c 100644 --- a/examples/vision/classification/resnet/cpp/README.md +++ b/examples/vision/classification/resnet/cpp/README.md @@ -4,8 +4,8 @@ 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/environment.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/quick_start) +- 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 ResNet50 推理为例，在本目录执行如下命令即可完成编译测试 @@ -33,7 +33,7 @@ wget https://gitee.com/paddlepaddle/PaddleClas/raw/release/2.4/deploy/images/Ima ``` 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/compile/how_to_use_sdk_on_windows.md) +- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md) ## ResNet C++接口 @@ -74,4 +74,4 @@ fastdeploy::vision::classification::ResNet( - [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/runtime/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) diff --git a/examples/vision/classification/resnet/python/README.md b/examples/vision/classification/resnet/python/README.md index 6315ee06a6..a115bcdf40 100644 --- a/examples/vision/classification/resnet/python/README.md +++ b/examples/vision/classification/resnet/python/README.md @@ -2,8 +2,8 @@ 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/environment.md) -- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/quick_start) +- 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) 本目录下提供`infer.py`快速完成ResNet50_vd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 @@ -69,4 +69,4 @@ fd.vision.classification.ResNet(model_file, params_file, runtime_option=None, mo - [ResNet 模型介绍](..) - [ResNet 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/runtime/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) diff --git a/examples/vision/detection/paddledetection/quantize/cpp/README.md b/examples/vision/detection/paddledetection/quantize/cpp/README.md index 42bf40acbe..bcc66e7f79 100644 --- a/examples/vision/detection/paddledetection/quantize/cpp/README.md +++ b/examples/vision/detection/paddledetection/quantize/cpp/README.md @@ -9,7 +9,7 @@ ### 量化模型准备 - 1. 用户可以直接使用由FastDeploy提供的量化模型进行部署. -- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署.(注意: 推理量化后的分类模型仍然需要FP32模型文件夹下的infer_cfg.yml文件, 自行量化的模型文件夹内不包含此yaml文件, 用户从FP32模型文件夹下复制此yaml文件到量化后的模型文件夹内即可.) +- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../../../../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署.(注意: 推理量化后的分类模型仍然需要FP32模型文件夹下的infer_cfg.yml文件, 自行量化的模型文件夹内不包含此yaml文件, 用户从FP32模型文件夹下复制此yaml文件到量化后的模型文件夹内即可.) ## 以量化后的PP-YOLOE-l模型为例, 进行部署 在本目录执行如下命令即可完成编译,以及量化模型部署. diff --git a/examples/vision/detection/paddledetection/quantize/python/README.md b/examples/vision/detection/paddledetection/quantize/python/README.md index cecb5a1401..3efcd232b9 100644 --- a/examples/vision/detection/paddledetection/quantize/python/README.md +++ b/examples/vision/detection/paddledetection/quantize/python/README.md @@ -8,7 +8,7 @@ ### 量化模型准备 - 1. 用户可以直接使用由FastDeploy提供的量化模型进行部署. -- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署.(注意: 推理量化后的分类模型仍然需要FP32模型文件夹下的infer_cfg.yml文件, 自行量化的模型文件夹内不包含此yaml文件, 用户从FP32模型文件夹下复制此yaml文件到量化后的模型文件夹内即可.) +- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../../../../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署.(注意: 推理量化后的分类模型仍然需要FP32模型文件夹下的infer_cfg.yml文件, 自行量化的模型文件夹内不包含此yaml文件, 用户从FP32模型文件夹下复制此yaml文件到量化后的模型文件夹内即可.) ## 以量化后的PP-YOLOE-l模型为例, 进行部署 diff --git a/examples/vision/detection/yolov5/quantize/cpp/README.md b/examples/vision/detection/yolov5/quantize/cpp/README.md index 7d76bad514..5afaecce4b 100644 --- a/examples/vision/detection/yolov5/quantize/cpp/README.md +++ b/examples/vision/detection/yolov5/quantize/cpp/README.md @@ -9,7 +9,7 @@ ### 量化模型准备 - 1. 用户可以直接使用由FastDeploy提供的量化模型进行部署. -- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署. +- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../../../../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署. ## 以量化后的YOLOv5s模型为例, 进行部署 在本目录执行如下命令即可完成编译,以及量化模型部署. diff --git a/examples/vision/detection/yolov5/quantize/python/README.md b/examples/vision/detection/yolov5/quantize/python/README.md index 9aa03a8cc0..28086d8b5b 100644 --- a/examples/vision/detection/yolov5/quantize/python/README.md +++ b/examples/vision/detection/yolov5/quantize/python/README.md @@ -8,7 +8,7 @@ ### 量化模型准备 - 1. 用户可以直接使用由FastDeploy提供的量化模型进行部署. -- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署. +- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../../../../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署. ## 以量化后的YOLOv5s模型为例, 进行部署 diff --git a/examples/vision/detection/yolov6/quantize/cpp/README.md b/examples/vision/detection/yolov6/quantize/cpp/README.md index bf2208fab7..53a05cab7c 100644 --- a/examples/vision/detection/yolov6/quantize/cpp/README.md +++ b/examples/vision/detection/yolov6/quantize/cpp/README.md @@ -9,7 +9,7 @@ ### 量化模型准备 - 1. 用户可以直接使用由FastDeploy提供的量化模型进行部署. -- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署. +- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../../../../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署. ## 以量化后的YOLOv6s模型为例, 进行部署 在本目录执行如下命令即可完成编译,以及量化模型部署. diff --git a/examples/vision/detection/yolov6/quantize/python/README.md b/examples/vision/detection/yolov6/quantize/python/README.md index 5f70a02c84..889fe2f113 100644 --- a/examples/vision/detection/yolov6/quantize/python/README.md +++ b/examples/vision/detection/yolov6/quantize/python/README.md @@ -8,7 +8,7 @@ ### 量化模型准备 - 1. 用户可以直接使用由FastDeploy提供的量化模型进行部署. -- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署. +- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../../../../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署. ## 以量化后的YOLOv6s模型为例, 进行部署 ```bash diff --git a/examples/vision/detection/yolov7/python/README_EN.md b/examples/vision/detection/yolov7/python/README_EN.md index 64ce3b6ed4..57b341dd75 100644 --- a/examples/vision/detection/yolov7/python/README_EN.md +++ b/examples/vision/detection/yolov7/python/README_EN.md @@ -4,8 +4,8 @@ English | [简体中文](README.md) Two steps before deployment: -- 1. The hardware and software environment meets the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/docs_en/environment.md) -- 2. Install FastDeploy Python whl package. Please refer to [FastDeploy Python Installation](../../../../../docs/docs_en/quick_start) +- 1. The hardware and software environment meets the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md) +- 2. Install FastDeploy Python whl package. Please refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md) This doc provides a quick `infer.py` demo of YOLOv7 deployment on CPU/GPU, and accelerated GPU deployment by TensorRT. Run the following command: @@ -21,7 +21,7 @@ wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/0000000 # CPU Inference python infer.py --model yolov7.onnx --image 000000014439.jpg --device cpu -# GPU +# GPU python infer.py --model yolov7.onnx --image 000000014439.jpg --device gpu # GPU上使用TensorRT推理 python infer.py --model yolov7.onnx --image 000000014439.jpg --device gpu --use_trt True @@ -51,18 +51,18 @@ YOLOv7 model loading and initialisation, with model_file being the exported ONNX > ```python > YOLOv7.predict(image_data, conf_threshold=0.25, nms_iou_threshold=0.5) > ``` -> +> > Model prediction interface with direct output of detection results from the image input. -> +> > **Parameters** -> +> > > * **image_data**(np.ndarray): Input image. Images need to be in HWC or BGR format > > * **conf_threshold**(float): Filter threshold for detection box confidence > > * **nms_iou_threshold**(float): iou thresholds during NMS processing > **Return** -> -> > Return to`fastdeploy.vision.DetectionResult`Struct. For more details, please refer to [Vision Model Results](../../../../../docs/docs_en/api/vision_results/) +> +> > Return to`fastdeploy.vision.DetectionResult`Struct. For more details, please refer to [Vision Model Results](../../../../../docs/api/vision_results/) ### Class Member Variables @@ -80,5 +80,5 @@ Users can modify the following pre-processing parameters for their needs. This w - [YOLOv7 Model Introduction](..) - [YOLOv7 C++ Deployment](../cpp) -- [Vision Model Results](../../../../../docs/docs_en/api/vision_results/) -- [how to change inference backend](../../../../../docs/docs_en/runtime/how_to_change_inference_backend.md) +- [Vision Model Results](../../../../../docs/api/vision_results/) +- [how to change inference backend](../../../../../docs/en/faq/how_to_change_backend.md) diff --git a/examples/vision/detection/yolov7/quantize/cpp/README.md b/examples/vision/detection/yolov7/quantize/cpp/README.md index 53110591e0..dc78745284 100644 --- a/examples/vision/detection/yolov7/quantize/cpp/README.md +++ b/examples/vision/detection/yolov7/quantize/cpp/README.md @@ -9,7 +9,7 @@ ### 量化模型准备 - 1. 用户可以直接使用由FastDeploy提供的量化模型进行部署. -- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署. +- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../../../../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署. ## 以量化后的YOLOv7模型为例, 进行部署 在本目录执行如下命令即可完成编译,以及量化模型部署. diff --git a/examples/vision/detection/yolov7/quantize/python/README.md b/examples/vision/detection/yolov7/quantize/python/README.md index ac1c44889b..e82dc46159 100644 --- a/examples/vision/detection/yolov7/quantize/python/README.md +++ b/examples/vision/detection/yolov7/quantize/python/README.md @@ -8,7 +8,7 @@ ### 量化模型准备 - 1. 用户可以直接使用由FastDeploy提供的量化模型进行部署. -- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署. +- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../../../../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署. ## 以量化后的YOLOv7模型为例, 进行部署 ```bash diff --git a/examples/vision/keypointdetection/det_keypoint_unite/python/README.md b/examples/vision/keypointdetection/det_keypoint_unite/python/README.md index e401b655a8..1b2fc0f181 100644 --- a/examples/vision/keypointdetection/det_keypoint_unite/python/README.md +++ b/examples/vision/keypointdetection/det_keypoint_unite/python/README.md @@ -71,4 +71,4 @@ PPTinyPosePipeline模型加载和初始化，其中det_model是使用`fd.vision. - [Pipeline 模型介绍](..) - [Pipeline 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/runtime/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) diff --git a/examples/vision/keypointdetection/tiny_pose/python/README.md b/examples/vision/keypointdetection/tiny_pose/python/README.md index 2d95e7a2fd..f8835e00ec 100644 --- a/examples/vision/keypointdetection/tiny_pose/python/README.md +++ b/examples/vision/keypointdetection/tiny_pose/python/README.md @@ -76,4 +76,4 @@ 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/runtime/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) diff --git a/examples/vision/matting/ppmatting/cpp/README.md b/examples/vision/matting/ppmatting/cpp/README.md index a2eaeee1a2..04809ca699 100644 --- a/examples/vision/matting/ppmatting/cpp/README.md +++ b/examples/vision/matting/ppmatting/cpp/README.md @@ -7,7 +7,7 @@ - 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 PP-Matting 推理为例，在本目录执行如下命令即可完成编译测试（如若只需在CPU上部署，可在[Fastdeploy C++预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md/CPP_prebuilt_libraries.md)下载CPU推理库） +以Linux上 PP-Matting 推理为例，在本目录执行如下命令即可完成编译测试（如若只需在CPU上部署，可在[Fastdeploy C++预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)下载CPU推理库） ```bash #下载SDK，编译模型examples代码（SDK中包含了examples代码） diff --git a/examples/vision/matting/rvm/cpp/README.md b/examples/vision/matting/rvm/cpp/README.md index 1e4ade6eb9..ff80ecaf7d 100755 --- a/examples/vision/matting/rvm/cpp/README.md +++ b/examples/vision/matting/rvm/cpp/README.md @@ -5,7 +5,7 @@ - 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 RobustVideoMatting 推理为例，在本目录执行如下命令即可完成编译测试（如若只需在CPU上部署，可在[Fastdeploy C++预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md/CPP_prebuilt_libraries.md)下载CPU推理库） +以Linux上 RobustVideoMatting 推理为例，在本目录执行如下命令即可完成编译测试（如若只需在CPU上部署，可在[Fastdeploy C++预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)下载CPU推理库） 本目录下提供`infer.cc`快速完成RobustVideoMatting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 diff --git a/examples/vision/ocr/PP-OCRv3/mini_program/README.md b/examples/vision/ocr/PP-OCRv3/mini_program/README.md index 6bbe854b42..447a02e725 100644 --- a/examples/vision/ocr/PP-OCRv3/mini_program/README.md +++ b/examples/vision/ocr/PP-OCRv3/mini_program/README.md @@ -16,7 +16,7 @@ import * as ocr from "@paddle-js-models/ocr"; await ocr.init(detConfig, recConfig); const res = await ocr.recognize(img, option, postConfig); ``` -ocr模型加载和初始化，其中模型为Paddle.js模型格式，js模型转换方式参考[文档](../../../../application/web_demo/README.md) +ocr模型加载和初始化，其中模型为Paddle.js模型格式，js模型转换方式参考[文档](../../../../application/js/web_demo/README.md) **init函数参数** @@ -37,5 +37,4 @@ ocr模型加载和初始化，其中模型为Paddle.js模型格式，js模型转 - [PP-OCRv3 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) -- [PP-OCRv3模型web demo文档](../../../../application/web_demo/README.md) - +- [PP-OCRv3模型web demo文档](../../../../application/js/web_demo/README.md) diff --git a/examples/vision/ocr/PP-OCRv3/web/README.md b/examples/vision/ocr/PP-OCRv3/web/README.md index 7217783104..3afd247612 100644 --- a/examples/vision/ocr/PP-OCRv3/web/README.md +++ b/examples/vision/ocr/PP-OCRv3/web/README.md @@ -16,7 +16,7 @@ import * as ocr from "@paddle-js-models/ocr"; await ocr.init(detConfig, recConfig); const res = await ocr.recognize(img, option, postConfig); ``` -ocr模型加载和初始化，其中模型为Paddle.js模型格式，js模型转换方式参考[文档](../../../../application/web_demo/README.md) +ocr模型加载和初始化，其中模型为Paddle.js模型格式，js模型转换方式参考[文档](../../../../application/js/web_demo/README.md) **init函数参数** diff --git a/examples/vision/segmentation/paddleseg/quantize/cpp/README.md b/examples/vision/segmentation/paddleseg/quantize/cpp/README.md index fa334fba41..9c1ec4b6aa 100644 --- a/examples/vision/segmentation/paddleseg/quantize/cpp/README.md +++ b/examples/vision/segmentation/paddleseg/quantize/cpp/README.md @@ -8,7 +8,7 @@ ### 量化模型准备 - 1. 用户可以直接使用由FastDeploy提供的量化模型进行部署. -- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署.(注意: 推理量化后的分类模型仍然需要FP32模型文件夹下的deploy.yaml文件, 自行量化的模型文件夹内不包含此yaml文件, 用户从FP32模型文件夹下复制此yaml文件到量化后的模型文件夹内即可.) +- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../../../../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署.(注意: 推理量化后的分类模型仍然需要FP32模型文件夹下的deploy.yaml文件, 自行量化的模型文件夹内不包含此yaml文件, 用户从FP32模型文件夹下复制此yaml文件到量化后的模型文件夹内即可.) ## 以量化后的PP_LiteSeg_T_STDC1_cityscapes模型为例, 进行部署 在本目录执行如下命令即可完成编译,以及量化模型部署. diff --git a/examples/vision/segmentation/paddleseg/quantize/python/README.md b/examples/vision/segmentation/paddleseg/quantize/python/README.md index 9fd3b900bc..2e06ae145c 100644 --- a/examples/vision/segmentation/paddleseg/quantize/python/README.md +++ b/examples/vision/segmentation/paddleseg/quantize/python/README.md @@ -8,7 +8,7 @@ ### 量化模型准备 - 1. 用户可以直接使用由FastDeploy提供的量化模型进行部署. -- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署.(注意: 推理量化后的分类模型仍然需要FP32模型文件夹下的deploy.yaml文件, 自行量化的模型文件夹内不包含此yaml文件, 用户从FP32模型文件夹下复制此yaml文件到量化后的模型文件夹内即可.) +- 2. 用户可以使用FastDeploy提供的[一键模型自动化压缩工具](../../../../../../tools/auto_compression/),自行进行模型量化, 并使用产出的量化模型进行部署.(注意: 推理量化后的分类模型仍然需要FP32模型文件夹下的deploy.yaml文件, 自行量化的模型文件夹内不包含此yaml文件, 用户从FP32模型文件夹下复制此yaml文件到量化后的模型文件夹内即可.) ## 以量化后的PP_LiteSeg_T_STDC1_cityscapes模型为例, 进行部署 diff --git a/examples/vision/segmentation/paddleseg/rknpu2/python/README.md b/examples/vision/segmentation/paddleseg/rknpu2/python/README.md index 74aeed2a07..64460c68e4 100644 --- a/examples/vision/segmentation/paddleseg/rknpu2/python/README.md +++ b/examples/vision/segmentation/paddleseg/rknpu2/python/README.md @@ -4,7 +4,7 @@ - 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../../docs/cn/build_and_install/rknpu2.md) -【注意】如你部署的为**PP-Matting**、**PP-HumanMatting**以及**ModNet**请参考[Matting模型部署](../../../matting) +【注意】如你部署的为**PP-Matting**、**PP-HumanMatting**以及**ModNet**请参考[Matting模型部署](../../../../matting/) 本目录下提供`infer.py`快速完成PPHumanseg在RKNPU上部署的示例。执行如下脚本即可完成 diff --git a/examples/vision/segmentation/paddleseg/web/README.md b/examples/vision/segmentation/paddleseg/web/README.md index 2402b18a73..6c214347c0 100644 --- a/examples/vision/segmentation/paddleseg/web/README.md +++ b/examples/vision/segmentation/paddleseg/web/README.md @@ -7,7 +7,7 @@ ## 前端部署PP-Humanseg v1模型 -PP-Humanseg v1模型web demo部署及使用参考[文档](../../../../application/web_demo/README.md) +PP-Humanseg v1模型web demo部署及使用参考[文档](../../../../application/js/web_demo/README.md) ## PP-Humanseg v1 js接口 @@ -41,7 +41,3 @@ humanSeg.blurBackground(res) **drawHumanSeg()函数参数** > * **seg_values**(number[]): 输入参数，一般是getGrayValue函数计算的结果作为输入 - - - - diff --git a/examples/vision/tracking/pptracking/cpp/README.md b/examples/vision/tracking/pptracking/cpp/README.md index 9adef9dc79..dd46425868 100644 --- a/examples/vision/tracking/pptracking/cpp/README.md +++ b/examples/vision/tracking/pptracking/cpp/README.md @@ -7,7 +7,7 @@ - 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 PP-Tracking 推理为例，在本目录执行如下命令即可完成编译测试（如若只需在CPU上部署，可在[Fastdeploy C++预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md/CPP_prebuilt_libraries.md)下载CPU推理库） +以Linux上 PP-Tracking 推理为例，在本目录执行如下命令即可完成编译测试（如若只需在CPU上部署，可在[Fastdeploy C++预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)下载CPU推理库） ```bash #下载SDK，编译模型examples代码（SDK中包含了examples代码） diff --git a/fastdeploy/vision/common/processors/normalize.cc b/fastdeploy/vision/common/processors/normalize.cc index 726ba67a74..e16379ba5c 100644 --- a/fastdeploy/vision/common/processors/normalize.cc +++ b/fastdeploy/vision/common/processors/normalize.cc @@ -19,7 +19,7 @@ namespace vision { Normalize::Normalize(const std::vector& mean, const std::vector& std, bool is_scale, const std::vector& min, - const std::vector& max) { + const std::vector& max, bool swap_rb) { FDASSERT(mean.size() == std.size(), "Normalize: requires the size of mean equal to the size of std."); std::vector mean_(mean.begin(), mean.end()); @@ -50,6 +50,7 @@ Normalize::Normalize(const std::vector& mean, alpha_.push_back(alpha); beta_.push_back(beta); } + swap_rb_ = swap_rb; } bool Normalize::ImplByOpenCV(Mat* mat) { @@ -57,6 +58,7 @@ bool Normalize::ImplByOpenCV(Mat* mat) { std::vector split_im; cv::split(*im, split_im); + if (swap_rb_) std::swap(split_im[0], split_im[2]); for (int c = 0; c < im->channels(); c++) { split_im[c].convertTo(split_im[c], CV_32FC1, alpha_[c], beta_[c]); } @@ -79,9 +81,13 @@ bool Normalize::ImplByFlyCV(Mat* mat) { std[i] = 1.0 / alpha_[i]; mean[i] = -1 * beta_[i] * std[i]; } + + std::vector channel_reorder_index = {0, 1, 2}; + if (swap_rb_) std::swap(channel_reorder_index[0], channel_reorder_index[2]); + fcv::Mat new_im(im->width(), im->height(), fcv::FCVImageType::PKG_BGR_F32); - fcv::normalize_to_submean_to_reorder(*im, mean, std, std::vector(), + fcv::normalize_to_submean_to_reorder(*im, mean, std, channel_reorder_index, new_im, true); mat->SetMat(new_im); return true; @@ -91,8 +97,8 @@ bool Normalize::ImplByFlyCV(Mat* mat) { bool Normalize::Run(Mat* mat, const std::vector& mean, const std::vector& std, bool is_scale, const std::vector& min, - const std::vector& max, ProcLib lib) { - auto n = Normalize(mean, std, is_scale, min, max); + const std::vector& max, ProcLib lib, bool swap_rb) { + auto n = Normalize(mean, std, is_scale, min, max, swap_rb); return n(mat, lib); } diff --git a/fastdeploy/vision/common/processors/normalize.h b/fastdeploy/vision/common/processors/normalize.h index 515fcd7e6c..c489207df3 100644 --- a/fastdeploy/vision/common/processors/normalize.h +++ b/fastdeploy/vision/common/processors/normalize.h @@ -23,7 +23,8 @@ class FASTDEPLOY_DECL Normalize : public Processor { Normalize(const std::vector& mean, const std::vector& std, bool is_scale = true, const std::vector& min = std::vector(), - const std::vector& max = std::vector()); + const std::vector& max = std::vector(), + bool swap_rb = false); bool ImplByOpenCV(Mat* mat); #ifdef ENABLE_FLYCV bool ImplByFlyCV(Mat* mat); @@ -44,14 +45,23 @@ class FASTDEPLOY_DECL Normalize : public Processor { const std::vector& std, bool is_scale = true, const std::vector& min = std::vector(), const std::vector& max = std::vector(), - ProcLib lib = ProcLib::DEFAULT); + ProcLib lib = ProcLib::DEFAULT, bool swap_rb = false); std::vector GetAlpha() const { return alpha_; } std::vector GetBeta() const { return beta_; } + bool GetSwapRB() { + return swap_rb_; + } + + void SetSwapRB(bool swap_rb) { + swap_rb_ = swap_rb; + } + private: std::vector alpha_; std::vector beta_; + bool swap_rb_; }; } // namespace vision } // namespace fastdeploy diff --git a/fastdeploy/vision/common/processors/normalize_and_permute.cc b/fastdeploy/vision/common/processors/normalize_and_permute.cc index cb78cc7205..ca1565ec87 100644 --- a/fastdeploy/vision/common/processors/normalize_and_permute.cc +++ b/fastdeploy/vision/common/processors/normalize_and_permute.cc @@ -21,7 +21,8 @@ NormalizeAndPermute::NormalizeAndPermute(const std::vector& mean, const std::vector& std, bool is_scale, const std::vector& min, - const std::vector& max) { + const std::vector& max, + bool swap_rb) { FDASSERT(mean.size() == std.size(), "Normalize: requires the size of mean equal to the size of std."); std::vector mean_(mean.begin(), mean.end()); @@ -52,6 +53,7 @@ NormalizeAndPermute::NormalizeAndPermute(const std::vector& mean, alpha_.push_back(alpha); beta_.push_back(beta); } + swap_rb_ = swap_rb; } bool NormalizeAndPermute::ImplByOpenCV(Mat* mat) { @@ -60,6 +62,7 @@ bool NormalizeAndPermute::ImplByOpenCV(Mat* mat) { int origin_h = im->rows; std::vector split_im; cv::split(*im, split_im); + if (swap_rb_) std::swap(split_im[0], split_im[2]); for (int c = 0; c < im->channels(); c++) { split_im[c].convertTo(split_im[c], CV_32FC1, alpha_[c], beta_[c]); } @@ -94,8 +97,12 @@ bool NormalizeAndPermute::ImplByFlyCV(Mat* mat) { std[i] = 1.0 / alpha_[i]; mean[i] = -1 * beta_[i] * std[i]; } + + std::vector channel_reorder_index = {0, 1, 2}; + if (swap_rb_) std::swap(channel_reorder_index[0], channel_reorder_index[2]); + fcv::Mat new_im; - fcv::normalize_to_submean_to_reorder(*im, mean, std, std::vector(), + fcv::normalize_to_submean_to_reorder(*im, mean, std, channel_reorder_index, new_im, false); mat->SetMat(new_im); mat->layout = Layout::CHW; @@ -106,8 +113,9 @@ bool NormalizeAndPermute::ImplByFlyCV(Mat* mat) { bool NormalizeAndPermute::Run(Mat* mat, const std::vector& mean, const std::vector& std, bool is_scale, const std::vector& min, - const std::vector& max, ProcLib lib) { - auto n = NormalizeAndPermute(mean, std, is_scale, min, max); + const std::vector& max, ProcLib lib, + bool swap_rb) { + auto n = NormalizeAndPermute(mean, std, is_scale, min, max, swap_rb); return n(mat, lib); } diff --git a/fastdeploy/vision/common/processors/normalize_and_permute.h b/fastdeploy/vision/common/processors/normalize_and_permute.h index ec47665262..04715d9d7f 100644 --- a/fastdeploy/vision/common/processors/normalize_and_permute.h +++ b/fastdeploy/vision/common/processors/normalize_and_permute.h @@ -23,7 +23,8 @@ class FASTDEPLOY_DECL NormalizeAndPermute : public Processor { NormalizeAndPermute(const std::vector& mean, const std::vector& std, bool is_scale = true, const std::vector& min = std::vector(), - const std::vector& max = std::vector()); + const std::vector& max = std::vector(), + bool swap_rb = false); bool ImplByOpenCV(Mat* mat); #ifdef ENABLE_FLYCV bool ImplByFlyCV(Mat* mat); @@ -44,7 +45,7 @@ class FASTDEPLOY_DECL NormalizeAndPermute : public Processor { const std::vector& std, bool is_scale = true, const std::vector& min = std::vector(), const std::vector& max = std::vector(), - ProcLib lib = ProcLib::DEFAULT); + ProcLib lib = ProcLib::DEFAULT, bool swap_rb = false); void SetAlpha(const std::vector& alpha) { alpha_.clear(); @@ -58,9 +59,18 @@ class FASTDEPLOY_DECL NormalizeAndPermute : public Processor { beta_.assign(beta.begin(), beta.end()); } + bool GetSwapRB() { + return swap_rb_; + } + + void SetSwapRB(bool swap_rb) { + swap_rb_ = swap_rb; + } + private: std::vector alpha_; std::vector beta_; + bool swap_rb_; }; } // namespace vision } // namespace fastdeploy diff --git a/fastdeploy/vision/common/processors/transform.cc b/fastdeploy/vision/common/processors/transform.cc index 8d440b9c62..d54a4bca45 100644 --- a/fastdeploy/vision/common/processors/transform.cc +++ b/fastdeploy/vision/common/processors/transform.cc @@ -95,10 +95,77 @@ void FuseNormalizeHWC2CHW( << std::endl; } +void FuseNormalizeColorConvert( + std::vector>* processors) { + // Fuse Normalize and BGR2RGB/RGB2BGR + int normalize_index = -1; + int color_convert_index = -1; + // If these middle processors are after BGR2RGB/RGB2BGR and before Normalize, + // we can still fuse Normalize and BGR2RGB/RGB2BGR + static std::unordered_set middle_processors( + {"Resize", "ResizeByShort", "ResizeByLong", "Crop", "CenterCrop", + "LimitByStride", "LimitShort", "Pad", "PadToSize", "StridePad", + "WarpAffine"}); + + for (size_t i = 0; i < processors->size(); ++i) { + if ((*processors)[i]->Name() == "BGR2RGB" || + (*processors)[i]->Name() == "RGB2BGR") { + color_convert_index = i; + for (size_t j = color_convert_index + 1; j < processors->size(); ++j) { + if ((*processors)[j]->Name() == "Normalize" || + (*processors)[j]->Name() == "NormalizeAndPermute") { + normalize_index = j; + break; + } + } + if (normalize_index < 0) { + return; + } + for (size_t j = color_convert_index + 1; j < normalize_index; ++j) { + if (middle_processors.count((*processors)[j]->Name())) { + continue; + } + return; + } + } + } + + if (color_convert_index < 0) { + return; + } + + // Delete Color Space Convert + std::string color_processor_name = (*processors)[color_convert_index]->Name(); + processors->erase(processors->begin() + color_convert_index); + + // Toggle the swap_rb option of the Normalize processor + std::string normalize_processor_name = + (*processors)[normalize_index - 1]->Name(); + bool swap_rb; + if (normalize_processor_name == "Normalize") { + auto processor = dynamic_cast( + (*processors)[normalize_index - 1].get()); + swap_rb = processor->GetSwapRB(); + processor->SetSwapRB(!swap_rb); + } else if (normalize_processor_name == "NormalizeAndPermute") { + auto processor = dynamic_cast( + (*processors)[normalize_index - 1].get()); + swap_rb = processor->GetSwapRB(); + processor->SetSwapRB(!swap_rb); + } else { + FDASSERT(false, "Something wrong in FuseNormalizeColorConvert()."); + } + + FDINFO << color_processor_name << " and " << normalize_processor_name + << " are fused to " << normalize_processor_name + << " with swap_rb=" << !swap_rb << std::endl; +} + void FuseTransforms( std::vector>* processors) { FuseNormalizeCast(processors); FuseNormalizeHWC2CHW(processors); + FuseNormalizeColorConvert(processors); } diff --git a/fastdeploy/vision/common/processors/transform.h b/fastdeploy/vision/common/processors/transform.h index 53f7ffd63f..2a914fff71 100644 --- a/fastdeploy/vision/common/processors/transform.h +++ b/fastdeploy/vision/common/processors/transform.h @@ -31,6 +31,7 @@ #include "fastdeploy/vision/common/processors/resize_by_short.h" #include "fastdeploy/vision/common/processors/stride_pad.h" #include "fastdeploy/vision/common/processors/warp_affine.h" +#include namespace fastdeploy { namespace vision { @@ -41,6 +42,9 @@ void FuseTransforms(std::vector>* processors); void FuseNormalizeCast(std::vector>* processors); // Fuse Normalize + HWC2CHW to NormalizeAndPermute void FuseNormalizeHWC2CHW(std::vector>* processors); +// Fuse Normalize + Color Convert +void FuseNormalizeColorConvert( + std::vector>* processors); } // namespace vision } // namespace fastdeploy diff --git a/java/android/app/src/main/java/com/baidu/paddle/fastdeploy/app/ui/view/ResultListView.java b/java/android/app/src/main/java/com/baidu/paddle/fastdeploy/app/ui/view/ResultListView.java index a028c0f9cd..62b48a0547 100644 --- a/java/android/app/src/main/java/com/baidu/paddle/fastdeploy/app/ui/view/ResultListView.java +++ b/java/android/app/src/main/java/com/baidu/paddle/fastdeploy/app/ui/view/ResultListView.java @@ -5,10 +5,6 @@ import android.util.AttributeSet; import android.widget.ListView; -/** - * Created by ruanshimin on 2018/5/14. - */ - public class ResultListView extends ListView { public ResultListView(Context context) { super(context); diff --git a/java/android/app/src/main/java/com/baidu/paddle/fastdeploy/app/ui/view/adapter/DetectResultAdapter.java b/java/android/app/src/main/java/com/baidu/paddle/fastdeploy/app/ui/view/adapter/DetectResultAdapter.java index 3aecc5d4dd..404b9cbc5e 100644 --- a/java/android/app/src/main/java/com/baidu/paddle/fastdeploy/app/ui/view/adapter/DetectResultAdapter.java +++ b/java/android/app/src/main/java/com/baidu/paddle/fastdeploy/app/ui/view/adapter/DetectResultAdapter.java @@ -15,10 +15,6 @@ import java.text.DecimalFormat; import java.util.List; -/** - * Created by ruanshimin on 2018/5/13. - */ - public class DetectResultAdapter extends ArrayAdapter { private int resourceId; diff --git a/java/android/app/src/main/java/com/baidu/paddle/fastdeploy/app/ui/view/model/BaseResultModel.java b/java/android/app/src/main/java/com/baidu/paddle/fastdeploy/app/ui/view/model/BaseResultModel.java index 5cab72c500..cae71b6909 100644 --- a/java/android/app/src/main/java/com/baidu/paddle/fastdeploy/app/ui/view/model/BaseResultModel.java +++ b/java/android/app/src/main/java/com/baidu/paddle/fastdeploy/app/ui/view/model/BaseResultModel.java @@ -1,9 +1,5 @@ package com.baidu.paddle.fastdeploy.app.ui.view.model; -/** - * Created by ruanshimin on 2018/5/16. - */ - public class BaseResultModel { private int index; private String name; diff --git a/java/android/app/src/main/res/values/strings.xml b/java/android/app/src/main/res/values/strings.xml index a2128791fa..2bd2e43553 100644 --- a/java/android/app/src/main/res/values/strings.xml +++ b/java/android/app/src/main/res/values/strings.xml @@ -2,8 +2,8 @@ EasyEdge - FastDeploy PicoDet - FastDeploy PP-OCRv2 + EasyEdge + EasyEdge CHOOSE_INSTALLED_MODEL_KEY MODEL_DIR_KEY diff --git a/tests/models/test_mobilenetv2.py b/tests/models/test_mobilenetv2.py index 3bedc82f1a..fdc2733198 100755 --- a/tests/models/test_mobilenetv2.py +++ b/tests/models/test_mobilenetv2.py @@ -48,12 +48,10 @@ def test_classification_mobilenetv2(): im1 = cv2.imread("./resources/ILSVRC2012_val_00000010.jpeg") im2 = cv2.imread("./resources/ILSVRC2012_val_00030010.jpeg") - # for i in range(3000000): - while True: + for i in range(3): # test single predict - model.postprocessor.topk = 6 - result1 = model.predict(im1) - result2 = model.predict(im2) + result1 = model.predict(im1, 6) + result2 = model.predict(im2, 6) diff_label_1 = np.fabs( np.array(result1.label_ids) - np.array(expected_label_ids_1))