add notebook for tf to onnx conversion

sayakpaul / ml-deployment-k8s-fastapi

This project shows how to serve an ONNX-optimized image classification model as a web service with FastAPI, Docker, and Kubernetes.

https://medium.com/google-developer-experts/load-testing-tensorflow-serving-and-fastapi-on-gke-411bc14d96b2

Apache License 2.0

198 stars 36 forks source link

add notebook for tf to onnx conversion #1

Closed deep-diver closed 2 years ago

review-notebook-app[bot] commented 2 years ago

Check out this pull request on

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB

sayakpaul commented 2 years ago

@deep-diver I think it might be good to host the notebook under notebooks directory.

deep-diver commented 2 years ago

@sayakpaul

I have updated the notebook based on your comments! also, I think the notebook file is placed under notebooks directory.

Please review the updated notebook! thanks :)

sayakpaul commented 2 years ago

@deep-diver overall the notebook now looks better. A few more comments left.

deep-diver commented 2 years ago

@sayakpaul

updated the notebook with your comments. thanks for pointing out the built-in preprocess_input() method, training argument, and model.predict() method.