apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 17:17:14 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
Files
409c5dc05669b51a8fcc392cd161f24956761491
FastDeploy/examples/vision/facedet/scrfd/rknpu2/cpp/README_CN.md
Zheng-Bicheng dd01b3ca0b [Model] 更新SCRFD模型demo以及文档 (#1108) 
* 更新scrfd

* 更新scrfd
2023-01-11 13:56:17 +08:00

1.6 KiB
Raw Blame History

English | 简体中文

SCRFD C++部署示例

本目录下提供infer.cc在RK356X上，快速完成SCRFD在NPU加速部署的示例。

在部署前，需确认以下两个步骤:

  1. 软硬件环境满足要求
  2. 根据开发环境，下载预编译部署库或者从头编译FastDeploy仓库

以上步骤请参考RK2代NPU文档导航实现

编译

mkdir build
cd build
# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-aarch64-rk356X-x.x.x.tgz
tar -xzvf fastdeploy-linux-aarch64-rk356X-x.x.x.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-aarch64-rk356X
make -j8

运行例程

#下载官方转换好的SCRFD模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/rknpu2/scrfd_500m_bnkps_shape640x640_rknpu2.zip
unzip scrfd_500m_bnkps_shape640x640_rknpu2.zip
wget https://raw.githubusercontent.com/DefTruth/lite.ai.toolkit/main/examples/lite/resources/test_lite_face_detector_3.jpg
./infer_demo scrfd_500m_bnkps_shape640x640_rknpu2/scrfd_500m_bnkps_shape640x640_rk3568_quantized.rknn \
              test_lite_face_detector_3.jpg \
              1

运行完成可视化结果如下图所示