Skip to content

Latest commit

 

History

History
37 lines (35 loc) · 1.03 KB

File metadata and controls

37 lines (35 loc) · 1.03 KB

CycleGAN

Synthesizing Computer Tomographic Vertebrae Medical Images using CycleGAN.

CycleGAN Original Project

image

CycleGAN Medical Image Synthesis

image

Prerequisites

numpy~=1.25.2
scipy~=1.11.1
imageio~=2.26.0
tqdm~=4.65.0
torchvision~=0.15.2
tifffile~=2021.7.2

Train

python train.py --dataset_dir=med_image

Test

python test.py --dataset_dir=med-image 

References

CycleGAN, 
paper: @InProceedings{Zhu_2017_ICCV,
author = {Zhu, Jun-Yan and Park, Taesung and Isola, Phillip and Efros, Alexei A.},
title = {Unpaired Image-To-Image Translation Using Cycle-Consistent Adversarial Networks},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}
URL: [https://github.com/junyanz/CycleGAN](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix.git)