mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00

Files

T

DefTruth 9b848038a2 Add UltraFace Model support (#43 )

* update .gitignore

* Added checking for cmake include dir

* fixed missing trt_backend option bug when init from trt

* remove un-need data layout and add pre-check for dtype

* changed RGB2BRG to BGR2RGB in ppcls model

* add model_zoo yolov6 c++/python demo

* fixed CMakeLists.txt typos

* update yolov6 cpp/README.md

* add yolox c++/pybind and model_zoo demo

* move some helpers to private

* fixed CMakeLists.txt typos

* add normalize with alpha and beta

* add version notes for yolov5/yolov6/yolox

* add copyright to yolov5.cc

* revert normalize

* fixed some bugs in yolox

* Add UltraFace Model support

2022-07-26 22:15:40 +08:00

1.6 KiB

Raw Blame History

UltraFace部署示例

当前支持模型版本为：UltraFace CommitID:dffdddd

本文档说明如何进行UltraFace的快速部署推理。本目录结构如下

.
├── cpp                     # C++ 代码目录
│   ├── CMakeLists.txt      # C++ 代码编译CMakeLists文件
│   ├── README.md           # C++ 代码编译部署文档
│   └── ultraface.cc        # C++ 示例代码
├── api.md                  # API 说明文档
├── README.md               # UltraFace 部署文档
└── ultraface.py            # Python示例代码

安装FastDeploy

使用如下命令安装FastDeploy，注意到此处安装的是vision-cpu，也可根据需求安装vision-gpu

# 安装fastdeploy-python工具
pip install fastdeploy-python

# 安装vision-cpu模块
fastdeploy install vision-cpu

Python部署

执行如下代码即会自动下载YOLOv5Face模型和测试图片

python ultraface.py

执行完成后会将可视化结果保存在本地vis_result.jpg，同时输出检测结果如下

FaceDetectionResult: [xmin, ymin, xmax, ymax, score]
742.528931,261.309937, 837.749146, 365.145599, 0.999833
408.159332,253.410889, 484.747284, 353.378052, 0.999832
549.409424,225.051819, 636.311890, 337.824707, 0.999782
185.562805,233.364044, 252.001801, 323.948669, 0.999709
304.065918,180.468140, 377.097961, 278.932861, 0.999645

1.6 KiB Raw Blame History

UltraFace部署示例

安装FastDeploy

Python部署

其它文档

1.6 KiB

Raw Blame History