Did this project in "Generative Adversarial Network" module during completion of Udacitty Deep Learning Nanodegree.Built a CycleGAN to and trained on the unlabeled and unpaired dataset images of "summer" and "winter" from "Yosemite National Park" dataset to transform the images from the "summer" domain to "winter" domain and vice versa. Defined two sets of Discriminator and Generartor, each for transforming images from summer to winter and vise versa. Trained the two Discriminator separately by optimizing respective discriminator losses and the two Generator together by optimizing addition of two generator losses and two cycle consistency losses and visualized the tranformed images across the two domains by the CycleGAN network.
-
Notifications
You must be signed in to change notification settings - Fork 0
Did this project in "Generative Adversarial Network" module during completion of Udacitty Deep Learning Nanodegree.
License
mmrahman-utexas/Unpaired_Image_To_Image_translation_Using_CycleGAN
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Did this project in "Generative Adversarial Network" module during completion of Udacitty Deep Learning Nanodegree.
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published