apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-15 13:10:55 +08:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity
Files
3e7cb880493e6a75c259ee8b51bcfc025a9d9768
FastDeploy/examples/vision/classification/paddleclas
History
seyosum df8dd3e3ac 【Hackthon_4th 180】Support HORIZON BPU Backend for FastDeploy (#1822) 
* add horizon backend and PPYOLOE examples

* 更改horizon头文件编码规范

* 更改horizon头文件编码规范

* 更改horizon头文件编码规范

* 增加horizon packages下载及自动安装

* Add UseHorizonNPUBackend Method

* 删除编译FD SDK后多余的头文件,同时更改部分规范

* Update horizon.md

* Update horizon.md

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2023-05-06 16:10:37 +08:00
..
amlogic/a311d
[Docs] Pick paddleclas fastdeploy docs from PaddleClas (#1654)
2023-03-23 13:06:09 +08:00
android
[Docs] Pick paddleclas fastdeploy docs from PaddleClas (#1654)
2023-03-23 13:06:09 +08:00
ascend
[Docs] Pick paddleclas fastdeploy docs from PaddleClas (#1654)
2023-03-23 13:06:09 +08:00
cpu-gpu
[Docs] Pick paddleclas fastdeploy docs from PaddleClas (#1654)
2023-03-23 13:06:09 +08:00
graphcore
[Docs] Pick paddleclas fastdeploy docs from PaddleClas (#1654)
2023-03-23 13:06:09 +08:00
horizon
【Hackthon_4th 180】Support HORIZON BPU Backend for FastDeploy (#1822)
2023-05-06 16:10:37 +08:00
kunlunxin
[Docs] Pick paddleclas fastdeploy docs from PaddleClas (#1654)
2023-03-23 13:06:09 +08:00
quantize
[Docs] Pick paddleclas fastdeploy docs from PaddleClas (#1654)
2023-03-23 13:06:09 +08:00
rockchip
[Docs] Pick paddleclas fastdeploy docs from PaddleClas (#1654)
2023-03-23 13:06:09 +08:00
serving
[Docs] Pick paddleclas fastdeploy docs from PaddleClas (#1654)
2023-03-23 13:06:09 +08:00
sophgo
[Docs] Pick paddleclas fastdeploy docs from PaddleClas (#1654)
2023-03-23 13:06:09 +08:00
web
[Docs] Pick paddleclas fastdeploy docs from PaddleClas (#1654)
2023-03-23 13:06:09 +08:00
README.md
[Docs] Pick paddleclas fastdeploy docs from PaddleClas (#1654)
2023-03-23 13:06:09 +08:00

README.md

PaddleClas高性能全场景模型部署方案—FastDeploy

目录

1. FastDeploy介绍

⚡️FastDeploy是一款全场景、易用灵活、极致高效的AI推理部署工具，支持云边端部署。使用FastDeploy可以简单高效的在X86 CPU、NVIDIA GPU、飞腾CPU、ARM CPU、Intel GPU、Graphcore IPU、昆仑、昇腾、瑞芯微、晶晨、算能等10+款硬件上对PaddleClas模型进行快速部署，并且支持Paddle Inference、Paddle Lite、TensorRT、OpenVINO、ONNXRuntime、RKNPU2、SOPHGO等多种推理后端。

2. 图像分类模型部署

2.1 硬件支持列表

硬件类型 该硬件是否支持 使用指南 Python C++
X86 CPU ✅ 链接 ✅ ✅
NVIDIA GPU ✅ 链接 ✅ ✅
飞腾CPU ✅ 链接 ✅ ✅
ARM CPU ✅ 链接 ✅ ✅
Intel GPU(集成显卡) ✅ 链接 ✅ ✅
Intel GPU(独立显卡) ✅ 链接 ✅ ✅
Graphcore IPU ✅ 链接 ✅ ✅
昆仑 ✅ 链接 ✅ ✅
昇腾 ✅ 链接 ✅ ✅
瑞芯微 ✅ 链接 ✅ ✅
晶晨 ✅ 链接 -- ✅
算能 ✅ 链接 ✅ ✅

2.2. 详细使用文档

2.3 更多部署方式

4. 常见问题

遇到问题可查看常见问题集合，搜索FastDeploy issue，或给FastDeploy提交issue:

常见问题集合
FastDeploy issues