ova-server

Open source computer vision API based on open source models

🚀 Quick start

An instance of ova-server is free and publicly available here:

https://api.openvisionapi.com

Checkout ova-client for a quick demo.

Installing

  1. Setup a local enviroment using tensorflow lite as backend framework
$ make setup-tensorflow-lite

See the documentation for the list of supported deep learning frameworks.

  1. Download the models:
$ ./cli.py download --model=yolov4 --framework=tensorflow_lite --hardware=cpu

Usage

Run the ova-server

$ make run

[2021-03-26 19:45:37 +0100] [396769] [INFO] Starting gunicorn 20.0.4
[2021-03-26 19:45:37 +0100] [396769] [INFO] Listening at: http://0.0.0.0:8000 (396769)
[2021-03-26 19:45:37 +0100] [396769] [INFO] Using worker: sync
[2021-03-26 19:45:37 +0100] [396771] [INFO] Booting worker with pid: 396771

Get the official client

$ git clone https://github.com/openvisionapi/ova-client
$ cd ova-client
$ make setup
$ source .venv/bin/activate
$ DETECTION_URL=http://localhost:8000/api/v1/detection ./ova_client.py detection images/cat.jpeg

More information about the ova-client https://github.com/openvisionapi/ova-client

⛏️ Built Using

✍️ Author

Badr BADRI

🤝 Contributing

Your contributions are welcome !

Setting up development environment

To setup the development environment, simply run this command

$ make dev

Code-style checks

black is used for code formatting.

mypy is used for static typing.

🔧 Tests

To run the tests, simply run those commands

$ make dev
$ make test

📄 Documentation

Full documentation can be found here:

https://openvisionapi-documentation.readthedocs.io/en/latest/

GitHub

https://github.com/openvisionapi/ova-server