SR-Worker

Serving Super Resolution Model Using FastAPI and Celery.

For Developers

1. install dev package.

pip install -r requirements.txt
pip install -r requirements-dev.txt

2. install pre-commit.

pre-commit install

Installation

1. Run RabbitMQ image as a broker

docker run -d --name sr-rabbitmq -p 5672:5672 -p 8080:15672 --restart=unless-stopped rabbitmq:3.9.21-management

2. Build docker image

git clone https://github.com/ainize-team/SR-Worker.git
cd SR-Worker
docker build -t sr-worker .

3. Run docker image

docker run -d --name <worker_container_name> \
--gpus='"device=0"' -e BROKER_URI=<broker_uri> \
-e DATABASE_URL=<firebase_realtime_database_url> \
-e STORAGE_BUCKET=<firebase_storage_url> \
-v <firebase_credential_path>:/app/key -v <model_local_path>:/app/model \
sr-worker

Or, you can use the env file to run as follows.

docker run -d --name <worker_container_name> \
--gpus='"device=0"' \
--env-file <env filename> \
-v <firebase_credential_path>:/app/key -v <model_local_path>:/app/model \
sr-worker

Test with FastAPI

• Check our SR-FastAPI Repo.