Commit
·
21478db
1
Parent(s):
0b34793
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- gan
|
| 4 |
+
- computer vision
|
| 5 |
+
- horse to zebra
|
| 6 |
+
license:
|
| 7 |
+
- cc0-1.0
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
## Keras Implementation of CycleGAN model using [Horse to Zebra dataset](https://www.tensorflow.org/datasets/catalog/cycle_gan#cycle_ganhorse2zebra) 🤖🦹🏻
|
| 11 |
+
|
| 12 |
+
This repo contains the model and the notebook [to this Keras example on CycleGAN](https://keras.io/examples/generative/cyclegan/).
|
| 13 |
+
|
| 14 |
+
Full credits to: [Aakash Kumar Nain](https://twitter.com/A_K_Nain)
|
| 15 |
+
|
| 16 |
+
## Background Information
|
| 17 |
+
CycleGAN is a model that aims to solve the image-to-image translation problem. The goal of the image-to-image translation problem is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, obtaining paired examples isn't always feasible. CycleGAN tries to learn this mapping without requiring paired input-output images, using cycle-consistent adversarial networks.
|
| 18 |
+
|