More details of U-Net architecture can be found on U-Net: Convolutional Networks for Biomedical Image Segmentation. The code was derived from UNet with additional supprt for RGB images.
The following dependencies are needed:
- Numpy
- Tensorflow-gpu
- Keras
- Scikit-image
- Install dependencies:
conda env create -f env.yml
- Configure paths and parameters with config.py
- Train the model with train.py
- Test the trained model with test.py
