Skip to content

sStonemason/RET-CLIP

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

25 Commits
 
 
 
 
 
 
 
 

Repository files navigation

RET-CLIP: A Retinal Image Foundation Model Pre-trained with Clinical Diagnostic Reports

Accepted by MICCAI2024.

The RET-CLIP series is based on Chinese text. We will soon make the English version available.

This code repository is based on the official Chinese-CLIP. (LINK)

| Paper |

News

  • 2026.1.30 Introducing RET-CLIP➕ -- PLUS version of RET-CLIP. (LINK)
  • 2026.1.29 ⭐Introducing ReVision -- the most powerful retinal foundation model to date. (LINK)
  • 2024.7.16 Fix several bugs in the code.
  • 2024.7.10 Release the pretrained model using vit-b-16 as vision backbone.
  • More updates coming soon...

Environments

To start with this project, make sure that your environment meets the requirements below:

python >= 3.6.4 pytorch >= 1.8.0 (with torchvision >= 0.9.0) CUDA Version >= 10.2

Run the following command to install required packages.

pip install -r requirements.txt

Pretrained Model

If you encounter any issue while downloading or using the pretrained model, please feel free to contact us.

Vision Backbone Text Backbone
ViT-b-16 RoBERTa-wwm-ext-base-chinese LINK

About

RET-CLIP: A Retinal Image Foundation Model Pre-trained with Clinical Diagnostic Reports

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors