Aucune description

Hao SUN 7d73cf04f0 migrate to new scipy il y a 3 ans
datasets aa2d50d2df added data il y a 5 ans
imgs 9d0cb59da7 initial commit il y a 5 ans
.gitattributes c0c20cf92b Initial commit il y a 5 ans
.gitignore aa2d50d2df added data il y a 5 ans
README.md 7d73cf04f0 migrate to new scipy il y a 3 ans
dice_score.m 9d0cb59da7 initial commit il y a 5 ans
dice_score_multiple.m 9d0cb59da7 initial commit il y a 5 ans
main.py 7d73cf04f0 migrate to new scipy il y a 3 ans
model.py 7d73cf04f0 migrate to new scipy il y a 3 ans
module.py 9d0cb59da7 initial commit il y a 5 ans
ops.py 9d0cb59da7 initial commit il y a 5 ans
prepareimgs.m 9d0cb59da7 initial commit il y a 5 ans
requirements.txt 9d0cb59da7 initial commit il y a 5 ans
utils.py 7d73cf04f0 migrate to new scipy il y a 3 ans

README.md

CycleGAN

As proposed by Jun-Yan Zhu in Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks.

Prerequisites

  • tensorflow r1.1
  • numpy 1.11.0
  • scipy 0.17.0
  • pillow 3.3.0

Train

python main.py --dataset_dir=med-image

Test

python main.py --dataset_dir=med-image --phase=test --which_direction=AtoB

References