Deploy YOLOv5 model in TorchServe environment
Explore the docs »
View Demo
·
Report Bug
·
Request Feature
Table of Contents
Here is an instructions on setting up this project locally. To get a local copy up and running follow these simple example steps.
Before proceeding, you MUST install things listed below.
- Clone the repo
git clone https://github.com/ben-omji/serve_yolov5.git
- Setup
cd serve_yolov5 # Object detection ./setup.sh box # Object segmentation ./setup.sh seg # Check generated model archive ls ./resources/model-store/
- Run
# Object detection ./run_ts.sh coco_yolov5s.mar docker logs $(docker ps -lq) # !WARNING! >> If you want to run both models simultaneously, YOU MUST CHANGE THE PORT IN SCRIPT for preventing the conflict. # Object segmentation ./run_ts.sh coco_yolov5s-seg.mar docker logs $(docker ps -lq)
- Test
# Object detection curl -T PATH/TO/TEST/IMAGE 127.0.0.1:9080/predictions/coco_yolov5s # Object segmentation curl -T PATH/TO/TEST/IMAGE 127.0.0.1:9080/predictions/coco_yolov5s-seg
TODO: Add instruction to deploy our own yolov5 model which is trained on custom datatset.
- gRPC client
- python
See the open issues for a full list of proposed features (and known issues).
Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Distributed under the Apache License, Version 2.0. See LICENSE for more information.