openai / CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Why this job: works in the areas we cover, but does not say which job it does
What it does
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 several major challenges in computer vision.
Get started
$ conda install --yes -c pytorch pytorch=1.7.1 torchvision cudatoolkit=11.0
$ pip install ftfy regex tqdm
$ pip install git+https://github.com/openai/CLIP.git - Maintenance
- Inactive
- Last commit 7 months ago
- Stars
- 34,597
- +35 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Jupyter Notebook
- 99% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 43% closed
- 253 still open
- Pull requests
- 30 merged
- 20 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
More: languages, topics and project record
Languages
- Jupyter Notebook 99%
- Python 1%
Topics
- deep-learning
- machine-learning
Project record
- JobOther AI tools
- StatusListed
- Commits58
- Forks4,064
- Watching322
- Stars in 28 days+167
- CreatedDec 16, 2020
- First seen by usNov 7, 2026
- CheckedNov 8, 2026