CLIP

by openai · Machine Learning

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

New0 ratings34,265 starsActive
Machine LearningAI ApplicationJupyter NotebookPython
GitHub⚑ Report
CLIP — image 1

About this project

CLIP [[Blog]](https://openai.com/blog/clip/) [[Paper]](https://arxiv.org/abs/2103.00020) [[Model Card]](model-card.md) [[Colab]](https://colab.research.google.com/github/openai/clip/blob/master/notebooks/InteractingwithCLIP.ipynb) CLIP (Contrastive Language-Image Pre-Training) is a neural network trained on a variety of (image, text) pairs. It can be instructed in natural language to predict the most relevant text snippet, given an image, without directly optimizing for the task, similarly to the zero-shot capabilities of GPT-2 and 3. We found CLIP matches the performance of the original ResNet50 on ImageNet “zero-shot” without using any of the original 1.28M labeled examples, overcoming…

Technologies

Pythondeep-learningJupyter Notebookmachine-learning

Project health

Low recent activity
Last update5 months ago
Contributors23
Latest release
Open issues & PRs272
LicenseMIT
On GitHubsince 2020

GitHub

34,265
stars
4,045
forks
23
contributors
272
open issues & PRs
Jupyter Notebook
language
5 months ago
last commit
View on GitHub ↗

Reviews

out of 5 · 0 ratings
★★★★★
0%
★★★★
0%
★★★
0%
★★
0%
0%
Sign in to write a review
No reviews yet
Be the first to review CLIP.

Built by

openai
Imported from GitHub · not yet claimed on GitPalace
View developer pageSign in with GitHub to claim

Maintain openai/CLIP? Claiming verifies admin access through your GitHub account and gives you control of this listing.

You might also like