UCSC-VLAA/CLIPA

[NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"

36
/ 100
Emerging

This project offers a way to train advanced image and text recognition models, known as CLIP, much more efficiently and at a lower cost. It takes large datasets of images and their corresponding text descriptions as input, and outputs highly accurate CLIP models that can understand and connect visual and linguistic information. This is for machine learning researchers and practitioners who build and deploy AI models for tasks like image search or content moderation.

319 stars. No commits in the last 6 months.

Use this if you need to train high-performing image-text understanding models like CLIP, but are constrained by significant computing resources and high training costs.

Not ideal if you are looking for a pre-trained model to use directly without any further training or fine-tuning, or if you don't work with large-scale vision-language datasets.

deep-learning computer-vision natural-language-processing model-training AI-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

319

Forks

14

Language

Python

License

Apache-2.0

Last pushed

Jun 03, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/UCSC-VLAA/CLIPA"

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