mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +08:00

Files

Dantès 34bea7649d [Backend] add sophgo backend (#1015 )

* Add Sophgo Device

add sophgo backend in fastdeploy

add resnet50, yolov5s, liteseg examples.

* replace sophgo lib with download links; fix model.cc bug

* modify CodeStyle

* remove unuseful files;change the names of sophgo device and sophgo
backend

* sophgo support python and add python examples

* remove unuseful rows in cmake according pr

Co-authored-by: Zilong Xing <zilong.xing@sophgo.com>

2023-01-04 15:49:17 +08:00

1.4 KiB

Raw Blame History

YOLOv5 C++部署示例

本目录下提供infer.cc快速完成yolov5s模型在SOPHGO BM1684x板子上加速部署的示例。

在部署前，需确认以下两个步骤:

软硬件环境满足要求
根据开发环境，从头编译FastDeploy仓库

以上步骤请参考SOPHGO部署库编译实现

生成基本目录文件

该例程由以下几个部分组成

.
├── CMakeLists.txt
├── build  # 编译文件夹
├── image  # 存放图片的文件夹
├── infer.cc
└── model  # 存放模型文件的文件夹

编译

编译并拷贝SDK到thirdpartys文件夹

请参考SOPHGO部署库编译仓库编译SDK，编译完成后，将在build目录下生成fastdeploy-0.0.3目录.

拷贝模型文件，以及配置文件至model文件夹

将Paddle模型转换为SOPHGO bmodel模型，转换步骤参考文档
将转换后的SOPHGO bmodel模型文件拷贝至model中

准备测试图片至image文件夹

wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
cp 000000014439.jpg ./images

编译example

cd build
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-0.0.3
make

运行例程

./infer_demo model images/000000014439.jpg

1.4 KiB Raw Blame History Unescape Escape