Understanding U-Net architecture and building it from scratch.
This tutorial should clear any doubts you may have regarding the architecture of U-Net. It should also inform you on the process of building your own U-Net using functional blocks for encoder and decoder.
Example use case: Segmentation of mitochondria using only 12 images and about 150 labeled objects.
Dataset: https://www.epfl.ch/labs/cvlab/data/data-em/
Code generated in the video can be downloaded from here:
https://github.com/bnsreenu/python_for_microscopists