apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Jason
2022-08-12 18:00:09 +08:00
committed by GitHub
parent 32047016d6
commit d9b6587f0c
1 changed files with 17 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

69
README.md
View File

@@ -25,59 +25,24 @@
**⚡️FastDeploy**是一款**简单易用**的推理部署工具箱。覆盖业界主流**优质预训练模型**并提供**开箱即用**的开发体验，包括图像分类、目标检测、图像分割、人脸检测、人体关键点识别、文字识别等多任务，满足开发者**多场景**，**多硬件**、**多平台**的快速部署需求。
## News 📢
* 🔥 2022.8.15 [**⚡️FastDeploy v0.2.0**](https://github.com/PaddlePaddle/FastDeploy/releases/tag/release%2F0.2.0)测试版发布！🎉
* 💎 升级服务器端（CPU/GPU/Jetson）SDK代码架构，速度SOTA
* 😊 支持PyTorch模型部署，如YOLOv5、YOLOv6、YOLOv7等热门模型
## 特性
### 📦开箱即用的推理部署工具链，支持云边端、多硬件、多平台部署
- 支持 PIP 安装，一行命令快速下载SDK安装包，开箱即用
- 服务器与云端部署：
- 跨平台：同时支持 Windows、Linux 操作系统
- 多语言：提供 Python、C++ 多种语言部署示例
- 移动与边缘端侧部署：
- 支持 iOS、Android 移动端部署
- 支持 ARM Linux、NVIDIA Jetson 系列等边缘设备
- 覆盖主流AI硬件：
- 支持 Intel CPU 系列（含酷睿、至强等）
- 支持 ARM CPU 全系（含高通、MTK、RK等）
- 支持 NVIDIA GPU 全系（含 A100、V100、T4、Jetson 等）
### 🤗丰富的预置模型与高性能部署示例
#### 服务器与云端（含Jetson）
| <font size=2> 任务场景 | <font size=2> 模型 | <font size=2> 大小(MB) | <font size=2>边缘端 | <font size=2>服务器/云端 | <font size=2>服务器/云端 | <font size=2> 服务器/云端 | <font size=2> 服务器/云端 |
| ------------------------------- | --------------------------------------------------------- | --------------------- | --------------------------------------- | ------------------------------- | -------------------- | ------------------------- | --------------------- |
| ---- | ---- | ---- | <font size=2> [Jetson](./doc/Jetson.md) | <font size=2> [X86 CPU](./doc/) | <font size=2>[GPU]() | <font size=2> [X86 CPU]() | <font size=2> [GPU]() |
| ---- | ---- | ---- | Linux | Windows | Linux | Windows | Linux |
| Classfication | | | | | | | |
| Detection | [NanoDet-Plus](./model_zoo/vision/nanodet_plus/README.md) | 0.95~2.44 | ✅ | ✅ | ✅ | ✅ | ✅ |
| | [YOLOR](./model_zoo/vison/yolor/README.md) | | ✅ | ✅ | ✅ | ✅ | ✅ |
| | [YOLOX](./model_zoo/vison/yolox/README.md) | | ✅ | ✅ | ✅ | ✅ | ✅ |
| | [Scaled-YOLOv4](./model_zoo/vison/scaledyolov4/README.md) | 4.9 | ✅ | ✅ | ✅ | ✅ | ✅ |
| | [YOLOv5](./model_zoo/vison/yolov5/README.md) | | ✅ | ✅ | ✅ | ✅ | ✅ |
| | [YOLOv5_Lite](./model_zoo/vison/yolov5lite/README.md) | 94.6 | ✅ | ✅ | ✅ | ✅ | ✅ |
| | [YOLOv6](./model_zoo/vison/yolov6/README.md) | 4.4 | ✅ | ✅ | ✅ | ✅ | ✅ |
| | [YOLOv7](./model_zoo/vison/yolov7/README.md) | 23.3 | ✅ | ✅ | ✅ | ✅ | ✅ |
| <font size=2>Face Detection | [UltraFace](./model_zoo/vison/ultraface/README.md) | 1.04~1.1 | ✅ | ✅ | ✅ | ✅ | ✅ |
| | [YOLOv5Face](./model_zoo/vison/yolov5face/README.md) | | ✅ | ✅ | ✅ | ✅ | ✅ |
| <font size=2>Face Localisation | [RetinaFace](./model_zoo/vison/retinaface/README.md) | 1.7M | ✅ | ✅ | ✅ | ✅ | ✅ |
| <font size=2>Face Recognition | [ArcFace](./model_zoo/vison/arcface/README.md) | 1.7 | ✅ | ✅ | ✅ | ✅ | ✅ |
| <font size=2>Keypoint Detection | [SCRFD](./model_zoo/vison/scrfd/README.md) | 5.5 | ✅ | ✅ | ✅ | ✅ | ✅ |
| <font size=2>Segmentation | [PP-Seg](./model_zoo/vison/ppseg/README.md) | 32.2 | ✅ | ✅ | ✅ | ✅ | ✅ |
| <font size=2>OCR | [PP-OCRv1](./model_zoo/vison/ppocrv1/README.md) | 2.3+4.4 | ✅ | ✅ | ✅ | ✅ | ✅ |
| | [PP-OCRv2](./model_zoo/vison/ppocrv2/README.md) | 2.3+4.4 | ✅ | ✅ | ✅ | ✅ | ✅ |
| | [PP-OCRv3](./model_zoo/vison/ppocrv3/README.md) | 2.4+10.6 | ✅ | ✅ | ✅ | ✅ | ✅ |
## 支持模型
| 任务场景 | 模型 | X64 CPU | Nvidia-GPU | Nvidia-GPU TensorRT |
| -------- | ------------------------------------------------------------ | ------- | ---------- | ------------------- |
| 图像分类 | [PaddleClas/ResNet50](./examples/vision/classification/paddleclas) | √ | √ | √ |
| | [PaddleClas/PPLCNet](./examples/vision/classification/paddleclas) | √ | √ | √ |
| | [PaddleClas/EfficientNet](./examples/vision/classification/paddleclas) | √ | √ | √ |
| | [PaddleClas/GhostNet](./examples/vision/classification/paddleclas) | √ | √ | √ |
| | [PaddleClas/MobileNetV1](./examples/vision/classification/paddleclas) | √ | √ | √ |
| | [PaddleClas/MobileNetV2](./examples/vision/classification/paddleclas) | √ | √ | √ |
| | [PaddleClas/ShuffleNetV2](./examples/vision/classification/paddleclas) | √ | √ | √ |
| 目标检测 | [PaddleDetection/PPYOLOE](./examples/vision/detection/paddledetection) | √ | √ | √ |
| | [PaddleDetection/PicoDet](./examples/vision/detection/paddledetection) | √ | √ | √ |
| | [PaddleDetection/YOLOX](./examples/vision/detection/paddledetection) | √ | √ | √ |
| | [PaddleDetection/YOLOv3](./examples/vision/detection/paddledetection) | √ | √ | √ |
| | [PaddleDetection/PPYOLO](./examples/vision/detection/paddledetection) | √ | √ | - |
| | [PaddleDetection/PPYOLOv2](./examples/vision/detection/paddledetection) | √ | √ | - |
| | [PaddleDetection/FasterRCNN](./examples/vision/detection/paddledetection) | √ | √ | - |
#### 快速开始（服务器与云端部署）