Published July 28, 2021
| Version 0.1
Software
Open
OpenCLIP
Description
Welcome to the initial release of open_clip, an open source implementation of OpenAI's CLIP (Contrastive Language-Image Pre-training).
The goal of this repository is to enable training models with contrastive image-text supervision, and to investigate their properties such as robustness to distribution shift. Our starting point is an implementation of CLIP that matches the accuracy of the original CLIP models when trained on the same dataset.
Notes
Files
mlfoundations/open_clip-v0.1.zip
Files
(2.5 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:207f84e0654a2cb3da7659f8deb3c6c5
|
2.5 MB | Preview Download |
Additional details
Related works
- Is supplement to
- https://github.com/mlfoundations/open_clip/tree/v0.1 (URL)