The respository contains the code for the Deep Convolutional Generative Adversarial Network (DCGAN) trained on the anime faces dataset.
Blog post: https://idiotdeveloper.com/dcgan-implementing-deep-convolutional-generative-adversarial-network-in-tensorflow/
Video explaination: https://youtu.be/rJBp2L-JM_g
There are two files:
- gan.py: It is used to train the DCGAN on the anime faces dataset.
- test.py: This file loads the saved generator model and generates some fake samples and save them with the name fake.png
Download the dataset and put all the images in the data folder.
Link: https://www.kaggle.com/soumikrakshit/anime-faces
 |
|---|
| Image at epoch 1 |
 |
|---|
| Image at epoch 60 |
 |
|---|