mmyolo/projects/easydeploy
tripleMu 1045b41b68
[Deploy] MMYOLO model convert to onnx for deployment. (#279)
* Fromat code

* Support ONNXRUNTIME

* Support mmyolo model convert to onnx for deploy.

* Same as dev branch

* Support yolox focus rewrite

* Support GConv Focus

* Update mmyolo/easydeploy/backbone/focus.py

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Add TensorRT build/infer Wrapper

* Add image_demo for deploy model

* Fix

* Merge dev

* Remove image-demo

* Roll back to dev

* Support model switch to deploy

* Remove --deploy

* Add new deploy method

* Format code and add doc

* Move md to project

* add readme and readme_zh to easy_deploy

* Update projects/easydeploy/README_zh-CN.md

Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>

* Update projects/easydeploy/README.md

Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>
Co-authored-by: xin-li-67 <williamlee.xin@gmail.com>
Co-authored-by: Xin Li <7219519+xin-li-67@users.noreply.github.com>
Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
2022-11-23 10:43:41 +08:00
..
backbone [Deploy] MMYOLO model convert to onnx for deployment. (#279) 2022-11-23 10:43:41 +08:00
bbox_code [Deploy] MMYOLO model convert to onnx for deployment. (#279) 2022-11-23 10:43:41 +08:00
docs [Deploy] MMYOLO model convert to onnx for deployment. (#279) 2022-11-23 10:43:41 +08:00
model [Deploy] MMYOLO model convert to onnx for deployment. (#279) 2022-11-23 10:43:41 +08:00
nms [Deploy] MMYOLO model convert to onnx for deployment. (#279) 2022-11-23 10:43:41 +08:00
tools [Deploy] MMYOLO model convert to onnx for deployment. (#279) 2022-11-23 10:43:41 +08:00
README.md [Deploy] MMYOLO model convert to onnx for deployment. (#279) 2022-11-23 10:43:41 +08:00
README_zh-CN.md [Deploy] MMYOLO model convert to onnx for deployment. (#279) 2022-11-23 10:43:41 +08:00

README.md

MMYOLO Model Easy-Deployment

Introduction

This project is developed for easily converting your MMYOLO models to other inference backends without the need of MMDeploy, which reduces the cost of both time and effort on getting familiar with MMDeploy.

Currently we support converting to ONNX and TensorRT formats, other inference backends such ncnn will be added to this project as well.

Supported Backends