kykosic/actix-tensorflow-example

An example of using TensorFlow rust bindings to serve trained machine learning models via Actix Web

21
/ 100
Experimental

This project helps machine learning engineers efficiently deploy trained TensorFlow models as web services. It takes a pre-trained TensorFlow model and image data (PNG or JPG) and outputs the model's prediction, including a digit label and confidence score. This is for machine learning engineers who need to serve their models for real-time inference via a web API.

No commits in the last 6 months.

Use this if you need to build a high-performance, low-latency API endpoint for your TensorFlow models, especially for image recognition tasks.

Not ideal if you are looking for a no-code solution or want to serve models other than TensorFlow, such as PyTorch, without adaptation.

machine-learning-deployment model-serving image-recognition API-development inference-pipelines
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

49

Forks

2

Language

Rust

License

Last pushed

Mar 25, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kykosic/actix-tensorflow-example"

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