---
metrics:
- accuracy
library_name: keras
pipeline_tag: image-segmentation
tags:
- medical
---
 I  present a demo showcasing retinal vessel segmentation using the U-Net model, which is a well-known and widely used model in medical image segmentation. The model was trained on the DRIVE dataset, and the training process was conducted on Google Colab. The demo itself was built using Streamlit and deployed using localtunnel.