Skip to content
Snippets Groups Projects
Unverified Commit f23718e7 authored by NBouteldja's avatar NBouteldja Committed by GitHub
Browse files

Update README.md

parent a4fbb6e9
No related branches found
No related tags found
No related merge requests found
Show whitespace changes
Inline Side-by-side
Showing
with 6 additions and 0 deletions
README.md
+ 6
− 0
View file @ f23718e7
# KidneyStainTranslation # KidneyStainTranslation
This repo provides a framework to train CycleGAN- and U-GAT-IT-based translators for unsupervised stain-to-stain translation in histology. This repo provides a framework to train CycleGAN- and U-GAT-IT-based translators for unsupervised stain-to-stain translation in histology.
<br>
| Input aSMA image | Fake PAS translation |
|:--:|:--:|
| <img src="https://github.com/NBouteldja/KidneyStainTranslation/blob/master/exemplaryResults/aSMA_image.png?raw=true" width="400">| <img src="https://github.com/NBouteldja/KidneyStainTranslation/blob/master/exemplaryResults/fakePAS_translation.png?raw=true" width="324"> |
| Prediction | Ground-truth |
| <img src="https://github.com/NBouteldja/KidneyStainTranslation/blob/master/exemplaryResults/prediction.png?raw=true" width="400">| <img src="https://github.com/NBouteldja/KidneyStainTranslation/blob/master/exemplaryResults/groundtruth.png?raw=true" width="324"> |
# Training # Training
To train a CycleGAN translator (e.g. incorporating a prior segmentation model), use the following command: To train a CycleGAN translator (e.g. incorporating a prior segmentation model), use the following command:
......
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment