RET-CLIP+: Advancing Retinal Image Understanding through Feature Flow between Pixel-Level Details and Semantic Abstractions

Advanced version of our previous RET-CLIP (LINK)

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

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