GitHub - HMS-IDAC/UNet: A TensorFlow implementation of the U-Net architecture for pixel classification (image segmentation).

HMS-IDAC / UNet Public

Notifications You must be signed in to change notification settings
Fork 3
Star 3

A TensorFlow implementation of the U-Net architecture for pixel classification (image segmentation).

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 9 Commits
LICENSE		LICENSE
PartitionOfImage.py		PartitionOfImage.py
ReadMe.txt		ReadMe.txt
UNet2D.py		UNet2D.py
ftools.py		ftools.py
imtools.py		imtools.py

Repository files navigation

A TensorFlow implementation of the U-Net architecture for pixel classification (image segmentation).

For a sample dataset to test the code on, see https://www.dropbox.com/s/hv5h483tlx08eo0/UNetData_Sinem.zip?dl=0

See main script on UNet2D.py for examples on how to train and deploy a model.
Familiarity with Python, TensorFlow, and Deep Learning is needed to understand and run the code.
Detailed documentation is currently not available. Please check LICENSE for further details.

References:
    https://arxiv.org/abs/1505.04597 (original U-Net paper)
    https://www.biorxiv.org/content/early/2018/12/28/507566 (paper where this implementation is used)

Developed by:
    Marcelo Cicconet
    marceloc.net