https://github.com/sayakpaul/ccd-ahm-2022

Contains my code and deck for Cloud Community Days Ahmedabad 2022.
https://github.com/sayakpaul/ccd-ahm-2022

deployment docker gcp keras onnx tensorflow vertex-ai vision

Last synced: 18 days ago
JSON representation

Contains my code and deck for Cloud Community Days Ahmedabad 2022.

• Host: GitHub
• URL: https://github.com/sayakpaul/ccd-ahm-2022
• Owner: sayakpaul
• License: apache-2.0
• Created: 2022-09-19T04:55:14.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2022-09-23T12:47:01.000Z (over 2 years ago)
• Last Synced: 2024-12-28T03:36:33.209Z (about 1 month ago)
• Topics: deployment, docker, gcp, keras, onnx, tensorflow, vertex-ai, vision
• Language: Jupyter Notebook
• Homepage:
• Size: 367 KB
• Stars: 4
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# ccd-ahm-2022

Contains my code and deck for [Cloud Community Days Ahmedabad 2022](https://gdg.community.dev/events/details/google-gdg-cloud-ahmedabad-presents-google-cloud-community-day-2022/): **Fantastic ML Deployments and How to Do Them with Vertex AI**. 

## Prerequisites

The notebooks provided in this repository use _paid_ Google Cloud Platform (GCP) services:

* [Vertex AI Workbench](https://www.youtube.com/watch?v=_Q1Nf-rgSiE)

* [Google Cloud Storage (GCS)](https://cloud.google.com/storage)

* [Vertex AI Prediction](https://cloud.google.com/vertex-ai/docs/predictions/getting-predictions)

* [Google Container Registry (GCR)](https://cloud.google.com/container-registry)

So, I assume you already have a billing-enabled GCP Project and you can:

* spin up Vertex AI Workbench instances

* create buckets on GCS

* push Docker images to GCR

## Notebooks

The notebooks are in `notebooks` directory. Below is a brief description of each notebook:

* `resnet-export.ipynb` shows how to export a TensorFlow model (image recognition) compatible with

off-the-shelf Vertex AI deployment. The deployment part will be covered via the Vertex AI GUI console. 

* `onnx-conversion.ipynb` shows how to optimized the TensorFlow model with ONNX and compares the latency

of the both the models (TensorFlow and ONNX).

* `custom-onnx-deployment.ipynb` shows how to deploy the ONNX model to Vertex AI using custom prediction

routes.

## Slides

[Link](https://bit.ly/ccd-ahm-deck)

## Acknowledgements

Thanks to the ML Developer Programs team at Google for providing GCP credit support.