This is an implementation of FRED-Net using keras. (https://www.sciencedirect.com/science/article/abs/pii/S0957417419300119)
In the following, there is a predicted mask with image and groundtruth (In order from left to right: Eye image-Groundtruth image-Predicted mask):
- requirements
pip install -r requirements.txt
- images and masks
Put images and maks in dataset/images and dataset/masks
- train.txt and val.txt
put images name in here:
image_name_1
image_name_2
.
.
.
image_nameN
- image size
The default image size is 256X256
I will be happy to help you. Please feel free to contact me.