FastDeploy 开源项目教程

最新推荐文章于 2025-06-22 22:52:09 发布

庞锦宇

最新推荐文章于 2025-06-22 22:52:09 发布

阅读量283

点赞数 5

CC 4.0 BY-SA版权

本文链接：https://blog.youkuaiyun.com/gitblog_00092/article/details/138599768

FastDeploy 开源项目教程

FastDeploy ⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models with end-to-end optimization, multi-platform and multi-framework support. 项目地址: https://gitcode.com/gh_mirrors/fa/FastDeploy

1. 项目介绍

FastDeploy 是一个易于使用且高性能的深度学习模型部署工具包，适用于云、移动和边缘设备。它支持多种主流场景和150多个SOTA模型，提供端到端的优化、多平台和多框架支持。FastDeploy 旨在满足开发者在多场景、多硬件和多平台上的工业部署需求。

2. 项目快速启动

2.1 安装 FastDeploy

2.1.1 安装前提条件

CUDA >= 11.2
cuDNN >= 8.0
Python >= 3.6
操作系统：Linux x86_64/macOS/Windows 10

2.1.2 安装 FastDeploy SDK（CPU 和 GPU 支持）

pip install fastdeploy-gpu-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html

2.1.3 Conda 安装（推荐）

conda config --add channels conda-forge && conda install cudatoolkit=11.2 cudnn=8.2

2.1.4 安装 FastDeploy SDK（仅 CPU 支持）

pip install fastdeploy-python -f https://www.paddlepaddle.org.cn/whl/fastdeploy.html

2.2 Python 快速启动示例

2.2.1 准备模型和图片

wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz
tar xvf ppyoloe_crn_l_300e_coco.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg

2.2.2 测试推理结果

import cv2
import fastdeploy.vision as vision

im = cv2.imread("000000014439.jpg")
model = vision.detection.PPYOLOE("ppyoloe_crn_l_300e_coco/model.pdmodel", 
                                 "ppyoloe_crn_l_300e_coco/model.pdiparams", 
                                 "ppyoloe_crn_l_300e_coco/infer_cfg.yml")
result = model.predict(im)
print(result)

vis_im = vision.vis_detection(im, result, score_threshold=0.5)
cv2.imwrite("vis_image.jpg", vis_im)

2.3 C++ 快速启动示例

2.3.1 准备模型和图片

wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz
tar xvf ppyoloe_crn_l_300e_coco.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg

2.3.2 测试推理结果

#include "fastdeploy/vision.h"

int main(int argc, char* argv[]) {
    namespace vision = fastdeploy::vision;
    auto im = cv::imread("000000014439.jpg");
    auto model = vision::detection::PPYOLOE("ppyoloe_crn_l_300e_coco/model.pdmodel", 
                                            "ppyoloe_crn_l_300e_coco/model.pdiparams", 
                                            "ppyoloe_crn_l_300e_coco/infer_cfg.yml");
    vision::DetectionResult res;
    model.Predict(&im, &res);
    auto vis_im = vision::VisDetection(im, res, 0.5);
    cv::imwrite("vis_image.jpg", vis_im);
    return 0;
}