PaddlePaddle · jiangjiajun · Aug 18, 2022 · Aug 18, 2022 · Aug 18, 2022 · Aug 18, 2022
diff --git a/README.md b/README.md
@@ -14,7 +14,7 @@
     <a href="https://github.com/PaddlePaddle/FastDeploy/stargazers"><img src="https://img.shields.io/github/stars/PaddlePaddle/FastDeploy?color=ccf"></a>
 </p>
 
-**⚡️FastDeploy**是一款**简单易用**的推理部署工具箱。覆盖业界主流**优质预训练模型**并提供**开箱即用**的开发体验，包括图像分类、目标检测、图像分割、人脸检测、人体关键点识别、文字识别等多任务，满足开发者**多场景**，**多硬件**、**多平台**的快速部署需求。
+**⚡️FastDeploy**是一款**简单易用**的推理部署工具箱。覆盖业界主流**优质预训练模型**并提供**开箱即用**的开发体验，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、文字识别等多任务，满足开发者**多场景**，**多硬件**、**多平台**的快速部署需求。
 
 ## 近期更新
 
@@ -27,7 +27,7 @@
         - 支持Python API 和 C++ API
         - 开发AI模型部署代码量减少～60%
     - **端侧继ARM CPU后，延伸至瑞芯微、晶晨、恩智浦等NPU能力**
-        - 发布轻量化目标检测Picodet-NPU模型，提供低门槛INT8全量化能力
+        - 发布轻量化目标检测[Picodet-NPU部署Demo](https://github.com/PaddlePaddle/Paddle-Lite-Demo/tree/develop/object_detection/linux/picodet_detection)，提供低门槛INT8全量化能力
 
 ## 内容目录
 * **服务端**

diff --git a/examples/vision/detection/nanodet_plus/python/README.md b/examples/vision/detection/nanodet_plus/python/README.md
@@ -10,7 +10,7 @@
 ```
 #下载部署示例代码
 git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd examples/vison/detection/nanodet_plus/python/
+cd examples/vision/detection/nanodet_plus/python/
 
 #下载NanoDetPlus模型文件和测试图片
 wget https://bj.bcebos.com/paddlehub/fastdeploy/nanodet-plus-m_320.onnx

diff --git a/examples/vision/detection/paddledetection/cpp/README.md b/examples/vision/detection/paddledetection/cpp/README.md
@@ -10,26 +10,28 @@
 以Linux上推理为例，在本目录执行如下命令即可完成编译测试
 
 ```
+以ppyoloe为例进行推理部署
+
 #下载SDK，编译模型examples代码（SDK中包含了examples代码）
-wget https://bj.bcebos.com/paddlehub/fastdeploy/libs/0.2.0/fastdeploy-linux-x64-gpu-0.2.0.tgz
+wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-gpu-0.2.0.tgz
 tar xvf fastdeploy-linux-x64-gpu-0.2.0.tgz
-cd fastdeploy-linux-x64-gpu-0.2.0/examples/vision/detection/paddledetection
+cd fastdeploy-linux-x64-gpu-0.2.0/examples/vision/detection/paddledetection/cpp
 mkdir build && cd build
 cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../../../fastdeploy-linux-x64-gpu-0.2.0
 make -j
 
 # 下载PPYOLOE模型文件和测试图片
-wget https://bj.bcebos.com/paddlehub/fastdeploy/picodet_l_320_coco_lcnet.tgz
-wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000087038.jpg
-tar xvf picodet_l_320_coco_lcnet.tgz
+wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz
+wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
+tar xvf ppyoloe_crn_l_300e_coco.tgz
 
 
 # CPU推理
-./infer_ppyoloe_demo ./picodet_l_320_coco_lcnet 000000087038.jpg 0
+./infer_ppyoloe_demo ./ppyoloe_crn_l_300e_coco 000000014439.jpg 0
 # GPU推理
-./infer_ppyoloe_demo ./picodet_l_320_coco_lcnet 000000087038.jpg 1
+./infer_ppyoloe_demo ./ppyoloe_crn_l_300e_coco 000000014439.jpg 1
 # GPU上TensorRT推理
-./infer_ppyoloe_demo ./picodet_l_320_coco_lcnet 000000087038.jpg 2
+./infer_ppyoloe_demo ./ppyoloe_crn_l_300e_coco 000000014439.jpg 2
 ```
 
 ## PaddleDetection C++接口

diff --git a/examples/vision/detection/paddledetection/python/README.md b/examples/vision/detection/paddledetection/python/README.md
@@ -8,7 +8,6 @@
 本目录下提供`infer_xxx.py`快速完成PPYOLOE/PicoDet等模型在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
 
 ```
-
 #下载部署示例代码
 git clone https://github.com/PaddlePaddle/FastDeploy.git
 cd examples/vision/detection/paddledetection/python/
@@ -19,11 +18,11 @@ wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/0000000
 tar xvf ppyoloe_crn_l_300e_coco.tgz
 
 # CPU推理
-python infer.py --model_dir ppyoloe_crn_l_300e_coco --image 000000087038.jpg --device cpu
+python infer_ppyoloe.py --model_dir ppyoloe_crn_l_300e_coco --image 000000014439.jpg --device cpu
 # GPU推理
-python infer.py --model_dir ppyoloe_crn_l_300e_coco --image 000000087038.jpg --device gpu
+python infer_ppyoloe.py --model_dir ppyoloe_crn_l_300e_coco --image 000000014439.jpg --device gpu
 # GPU上使用TensorRT推理 （注意：TensorRT推理第一次运行，有序列化模型的操作，有一定耗时，需要耐心等待）
-python infer.py --model_dir ppyoloe_crn_l_300e_coco --image 000000087038.jpg --device gpu --use_trt True
+python infer_ppyoloe.py --model_dir ppyoloe_crn_l_300e_coco --image 000000014439.jpg --device gpu --use_trt True
 ```
 
 运行完成可视化结果如下图所示

diff --git a/examples/vision/detection/scaledyolov4/python/README.md b/examples/vision/detection/scaledyolov4/python/README.md
@@ -10,7 +10,7 @@
 ```
 #下载部署示例代码
 git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd examples/vison/detection/scaledyolov4/python/
+cd examples/vision/detection/scaledyolov4/python/
 
 #下载scaledyolov4模型文件和测试图片
 wget https://bj.bcebos.com/paddlehub/fastdeploy/scaled_yolov4-p5.onnx

diff --git a/examples/vision/detection/yolor/python/README.md b/examples/vision/detection/yolor/python/README.md
@@ -10,7 +10,7 @@
 ```
 #下载部署示例代码
 git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd examples/vison/detection/yolor/python/
+cd examples/vision/detection/yolor/python/
 
 #下载YOLOR模型文件和测试图片
 wget https://bj.bcebos.com/paddlehub/fastdeploy/yolor-p6-paper-541-640-640.onnx

diff --git a/examples/vision/detection/yolov5/python/README.md b/examples/vision/detection/yolov5/python/README.md
@@ -8,15 +8,14 @@
 本目录下提供`infer.py`快速完成YOLOv5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
 
 ```
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/detection/yolov5/python/
+
 #下载yolov5模型文件和测试图片
 wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s.onnx
 wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
 
-
-#下载部署示例代码
-git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd examples/vison/detection/yolov5/python/
-
 # CPU推理
 python infer.py --model yolov5s.onnx --image 000000014439.jpg --device cpu
 # GPU推理

diff --git a/examples/vision/detection/yolov5lite/python/README.md b/examples/vision/detection/yolov5lite/python/README.md
@@ -8,15 +8,14 @@
 本目录下提供`infer.py`快速完成YOLOv5Lite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
 
 ```
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/detection/yolov5lite/python/
+
 #下载YOLOv5Lite模型文件和测试图片
 wget https://bj.bcebos.com/paddlehub/fastdeploy/v5Lite-g-sim-640.onnx
 wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
 
-
-#下载部署示例代码
-git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd examples/vison/detection/yolov5lite/python/
-
 # CPU推理
 python infer.py --model v5Lite-g-sim-640.onnx --image 000000014439.jpg --device cpu
 # GPU推理

diff --git a/examples/vision/detection/yolov6/python/README.md b/examples/vision/detection/yolov6/python/README.md
@@ -8,15 +8,15 @@
 本目录下提供`infer.py`快速完成YOLOv6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
 
 ```
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/detection/yolov6/python/
+
+
 #下载YOLOv6模型文件和测试图片
 wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov6s.onnx
 wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
 
-
-#下载部署示例代码
-git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd examples/vison/detection/yolov6/python/
-
 # CPU推理
 python infer.py --model yolov6s.onnx --image 000000014439.jpg --device cpu
 # GPU推理

diff --git a/examples/vision/detection/yolov7/python/README.md b/examples/vision/detection/yolov7/python/README.md
@@ -8,15 +8,14 @@
 本目录下提供`infer.py`快速完成YOLOv7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
 
 ```
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/detection/yolov7/python/
+
 #下载yolov7模型文件和测试图片
 wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7.onnx
 wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
 
-
-#下载部署示例代码
-git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd examples/vison/detection/yolov7/python/
-
 # CPU推理
 python infer.py --model yolov7.onnx --image 000000014439.jpg --device cpu
 # GPU推理

diff --git a/examples/vision/detection/yolox/python/README.md b/examples/vision/detection/yolox/python/README.md
@@ -10,7 +10,7 @@
 ```
 #下载部署示例代码
 git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd examples/vison/detection/yolox/python/
+cd examples/vision/detection/yolox/python/
 
 #下载YOLOX模型文件和测试图片
 wget https://bj.bcebos.com/paddlehub/fastdeploy/yolox_s.onnx

diff --git a/examples/vision/facedet/retinaface/python/README.md b/examples/vision/facedet/retinaface/python/README.md
@@ -8,17 +8,15 @@
 本目录下提供`infer.py`快速完成RetinaFace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
 
 ```
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision//retinaface/python/
+
 #下载retinaface模型文件和测试图片
 wget https://bj.bcebos.com/paddlehub/fastdeploy/Pytorch_RetinaFace_mobile0.25-640-640.onnx
 wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
 
-
-#下载部署示例代码
-git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd examples/vison//retinaface/python/
-
 # CPU推理
-
 python infer.py --model Pytorch_RetinaFace_mobile0.25-640-640.onnx --image test_lite_face_detector_3.jpg --device cpu
 # GPU推理
 python infer.py --model Pytorch_RetinaFace_mobile0.25-640-640.onnx --image test_lite_face_detector_3.jpg --device gpu

diff --git a/examples/vision/facedet/scrfd/python/README.md b/examples/vision/facedet/scrfd/python/README.md
@@ -8,15 +8,14 @@
 本目录下提供`infer.py`快速完成SCRFD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
 
 ```
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/facedet/scrfd/python/
+
 #下载SCRFD模型文件和测试图片
 wget https://bj.bcebos.com/paddlehub/fastdeploy/scrfd_500m_bnkps_shape640x640.onnx
 wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
 
-
-#下载部署示例代码
-git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd examples/vison/facedet/scrfd/python/
-
 # CPU推理
 python infer.py --model scrfd_500m_bnkps_shape640x640.onnx --image test_lite_face_detector_3.jpg --device cpu
 # GPU推理

diff --git a/examples/vision/facedet/ultraface/python/README.md b/examples/vision/facedet/ultraface/python/README.md
@@ -8,17 +8,15 @@
 本目录下提供`infer.py`快速完成UltraFace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
 
 ```
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/facedet/ultraface/python/
+
 #下载ultraface模型文件和测试图片
 wget https://bj.bcebos.com/paddlehub/fastdeploy/version-RFB-320.onnx
 wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
 
-
-#下载部署示例代码
-git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd examples/vison/facedet/ultraface/python/
-
 # CPU推理
-
 python infer.py --model version-RFB-320.onnx --image test_lite_face_detector_3.jpg --device cpu
 # GPU推理
 python infer.py --model version-RFB-320.onnx --image test_lite_face_detector_3.jpg --device gpu

diff --git a/examples/vision/facedet/yolov5face/python/README.md b/examples/vision/facedet/yolov5face/python/README.md
@@ -8,15 +8,14 @@
 本目录下提供`infer.py`快速完成YOLOv5Face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
 
 ```
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/facedet/yolov5face/python/
+
 #下载YOLOv5Face模型文件和测试图片
 wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s-face.onnx
 wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
 
-
-#下载部署示例代码
-git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd examples/vison/facedet/yolov5face/python/
-
 # CPU推理
 python infer.py --model yolov5s-face.onnx --image test_lite_face_detector_3.jpg --device cpu
 # GPU推理

diff --git a/examples/vision/faceid/insightface/python/README.md b/examples/vision/faceid/insightface/python/README.md
@@ -9,17 +9,16 @@
 以ArcFace为例子, 提供`infer_arcface.py`快速完成ArcFace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
 
 ```
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/faceid/insightface/python/
+
 #下载ArcFace模型文件和测试图片
 wget https://bj.bcebos.com/paddlehub/fastdeploy/ms1mv3_arcface_r100.onnx
 wget https://bj.bcebos.com/paddlehub/test_samples/test_lite_focal_arcface_0.JPG
 wget https://bj.bcebos.com/paddlehub/test_samples/test_lite_focal_arcface_1.JPG
 wget https://bj.bcebos.com/paddlehub/test_samples/test_lite_focal_arcface_2.JPG
 
-
-#下载部署示例代码
-git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd examples/vison/faceid/insightface/python/
-
 # CPU推理
 python infer_arcface.py --model ms1mv3_arcface_r100.onnx --face test_lite_focal_arcface_0.JPG --face_positive test_lite_focal_arcface_1.JPG --face_negative test_lite_focal_arcface_2.JPG --device cpu
 # GPU推理

diff --git a/examples/vision/matting/modnet/python/README.md b/examples/vision/matting/modnet/python/README.md
@@ -8,23 +8,20 @@
 本目录下提供`infer.py`快速完成MODNet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
 
 ```
-#下载modnet模型文件和测试图片
+#下载部署示例代码
+git clone https://github.com/PaddlePaddle/FastDeploy.git
+cd examples/vision/matting/modnet/python/
 
+#下载modnet模型文件和测试图片
 wget https://bj.bcebos.com/paddlehub/fastdeploy/modnet_photographic_portrait_matting.onnx
 wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_matting_input.jpg
 
-
-#下载部署示例代码
-git clone https://github.com/PaddlePaddle/FastDeploy.git
-cd examples/vison/matting/modnet/python/
-
 # CPU推理
 python infer.py --model modnet_photographic_portrait_matting.onnx --image test_lite_matting_input.jpg --device cpu
 # GPU推理
 python infer.py --model modnet_photographic_portrait_matting.onnx --image test_lite_matting_input.jpg --device gpu
 # GPU上使用TensorRT推理
 python infer.py --model modnet_photographic_portrait_matting.onnx --image test_lite_matting_input.jpg --device gpu --use_trt True
-
 ```
 
 运行完成可视化结果如下图所示

diff --git a/examples/vision/segmentation/paddleseg/python/README.md b/examples/vision/segmentation/paddleseg/python/README.md
@@ -17,7 +17,6 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/Unet_cityscapes_without_argmax_i
 tar -xvf Unet_cityscapes_without_argmax_infer.tgz
 wget https://paddleseg.bj.bcebos.com/dygraph/demo/cityscapes_demo.png
 
-
 # CPU推理
 python infer.py --model Unet_cityscapes_without_argmax_infer --image cityscapes_demo.png --device cpu
 # GPU推理