视觉 AI 模型部署框架
Project description
xdeploy 项目
xdeploy 是一款视觉 AI 模型部署框架，支持目标检测、人脸识别、光学字符识别（OCR）和图像分割等任务。该项目提供了灵活的后端支持和模型接口，使您能够轻松部署各种深度学习模型。
支持的推理后端
- ONNX Runtime
- OpenVino
- TensorRT
安装
常规安装
uv add xdeploy
添加 TensorRT 支持
uv add "xdeploy[tensorrt]"
支持的算法
| 任务场景 | 模型 | 部署 | 训练文档 |
|---|---|---|---|
| 目标检测 | YOLOv8 | ✔️ | - |
| 目标检测 | YOLOv10 | ✔️ | - |
| 目标检测 | YOLO11 | ✔️ | - |
| 目标检测 | RT-DETR | ✔️ | - |
| 旋转框 | YOLOv8-OBB | ✔️ | - |
| 旋转框 | YOLO11-OBB | ✔️ | - |
| 图像分类 | YOLOv8-CLS | ✔️ | - |
| 图像分类 | YOLO11-CLS | ✔️ | - |
| 实例分割 | YOLOv8-SEG | ✔️ | - |
| 实例分割 | YOLO11-SEG | ✔️ | - |
| 关键点 | YOLOv8-Pose | ✔️ | - |
| 关键点 | YOLO11-Pose | ✔️ | - |
| 图像分割 | PaddleSeg | ✔️ | - |
| OCR | PPOCRv4 | ✔️ | - |
| 语音转文字 | - | ❌ | - |
| 文字转语音 | - | ❌ | - |
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
xdeploy-0.1.6.tar.gz
(62.0 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
xdeploy-0.1.6-py3-none-any.whl
(71.7 kB
view details)
File details
Details for the file xdeploy-0.1.6.tar.gz.
File metadata
- Download URL: xdeploy-0.1.6.tar.gz
- Upload date:
- Size: 62.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.8.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5ae106fa76ac40f12af96ababc582bf0fc1419206286053a7ab2bc9776cf9c33
|
|
| MD5 |
b22b16e5e519905179b26b2ca6ee3f3d
|
|
| BLAKE2b-256 |
21fc1bc1ce3cc5f68259d02e9bbadf7a749207a0e4eff6cf4fafca4da0f7d80e
|
File details
Details for the file xdeploy-0.1.6-py3-none-any.whl.
File metadata
- Download URL: xdeploy-0.1.6-py3-none-any.whl
- Upload date:
- Size: 71.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.8.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ab7ec76b9afb9b9cad0f403716fc7517d9d173de63d49d633d4baf63cd533f02
|
|
| MD5 |
42773be21c997446d96664b5564ed1cc
|
|
| BLAKE2b-256 |
21b8ad6c96299e2fee0f9995110056e263068e7c195080eb5f12860cc0bea2c5
|
