Go to file
2022-12-07 12:03:32 +11:00
output_anime Add project files. 2019-06-13 19:20:34 +10:00
output_faces Add project files. 2019-06-13 19:20:34 +10:00
.gitattributes Add .gitignore and .gitattributes. 2019-06-13 19:20:22 +10:00
.gitignore Add .gitignore and .gitattributes. 2019-06-13 19:20:22 +10:00
GAN.py Add project files. 2019-06-13 19:20:34 +10:00
GAN.pyproj Add project files. 2019-06-13 19:20:34 +10:00
GAN.sln Add project files. 2019-06-13 19:20:34 +10:00
README.md Update README.md 2022-12-07 12:03:32 +11:00

Generative Adverserial Network for generating images

The code here is a slightly altered version of the code that has been generously made publicly available at https://github.com/gsurma/image_generator

As an introduction to the world of GANs, I decided to try the above model on some different datasets. You can see the results of two example trainings in the respective output folders.

Training on human faces for 100 epochs took around 13 hours using the hardware mentioned on my profile. I am yet to optimise the architecture and hyperparameters.