sayakpaul/deploy-hf-tf-vision-models

This repository shows various ways of deploying a vision model (TensorFlow) from πŸ€— Transformers.

32
/ 100
Emerging

This project helps machine learning engineers or MLOps practitioners take their pre-trained vision models, like those from Hugging Face Transformers, and make them available for others to use. It shows how to convert a trained model into a web service that can process new images and return predictions. The output is a robust, scalable serving infrastructure for visual AI.

No commits in the last 6 months.

Use this if you are an MLOps engineer needing to deploy TensorFlow-based vision models from Hugging Face Transformers for live inference, either on-premises or using Google Cloud services like Vertex AI or GKE.

Not ideal if you are an application developer simply looking to integrate an existing vision API into your app, or if you are training models and not concerned with their deployment.

MLOps model-deployment computer-vision scalable-inference cloud-ML-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

30

Forks

3

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Aug 22, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sayakpaul/deploy-hf-tf-vision-models"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.