Lednik7/CLIP-ONNX

It is a simple library to speed up CLIP inference up to 3x (K80 GPU)

42
/ 100
Emerging

This library helps machine learning engineers and researchers speed up image and text understanding tasks. It takes an existing CLIP model and converts it into a more efficient format. The output is a faster-performing model that can categorize images based on text descriptions or vice-versa, which is crucial for large-scale deployments.

232 stars. No commits in the last 6 months.

Use this if you are a machine learning engineer working with CLIP models and need to significantly boost their processing speed for large datasets or real-time applications, especially on GPU.

Not ideal if you are not familiar with model conversion or are looking for a pre-trained, ready-to-use CLIP model without needing to optimize its performance.

deep-learning-optimization computer-vision natural-language-processing model-deployment ML-performance
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

232

Forks

30

Language

Python

License

MIT

Last pushed

Jul 20, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Lednik7/CLIP-ONNX"

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