How To Deploy ML Models With Google Cloud Run

Learn how to deploy Machine Learning models with Google Cloud Run.

Learn how to deploy Machine Learning / Deep Learning models with Google Cloud Run. We build a simple app with TensorFlow and Flask, containerize it with Docker, and deploy it to Google Cloud Run.

You can find the code on GitHub: https://github.com/patrickloeber/ml-deployment.

1. Write App (Flask, TensorFlow)¶

The code to build, train, and save the model is in the test folder.
Implement the app in main.py

2. Setup Google Cloud¶

Create new project
Activate Cloud Run API and Cloud Build API

3. Install and init Google Cloud SDK¶

https://cloud.google.com/sdk/docs/install

4. Dockerfile, requirements.txt, .dockerignore¶

https://cloud.google.com/run/docs/quickstarts/build-and-deploy#containerizing

5. Cloud build & deploy¶

gcloud builds submit --tag gcr.io/<project_id>/<function_name>
gcloud run deploy --image gcr.io/<project_id>/<function_name> --platform managed

Test¶

Test the code with test/test.py

FREE VS Code / PyCharm Extensions I Use

✅ Write cleaner code with Sourcery, instant refactoring suggestions: Link*

PySaaS: The Pure Python SaaS Starter Kit

🚀 Build a software business faster with pure Python: Link*

* These are affiliate link. By clicking on it you will not have any additional costs. Instead, you will support my project. Thank you! 🙏