Semantic segmentation describes the process of associating every pixel of an image with a class label, such as person, animal and in our case artery or vein. This repository provides DeepLab-Resnet model trained on retinal images for sematic segmentation of arteries and veins .
Python3
Tensorflow
Numpy
PIL
Download trained model from here and put it in trained_model folder.
To perform inference over your own images, use the following command:
python inference.py /path/to/your/image /path/to/ckpt/file