mselimata / neurohack_dl_gan

Neurohack project deep learning and GANs

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

"Oldify for Brains": what will your brain look like in 40 years?

Neurohackademy project: deep learing and GANs

What do these people have in common?

GAN_examples https://thispersondoesnotexist.com/

(Try this website, each time it will continue to generate new faces)

More technical information is here: https://www.lyrn.ai/2018/12/26/a-style-based-generator-architecture-for-generative-adversarial-networks/

STEP 1 – Generating “fake” old brains

STEP 2 – Estimate “brain age” of fake brains

... but how does it work?

Basic architecture of our Generative Adversarial Networks (GANs) (based on https://skymind.com/wiki/generative-adversarial-network-gan)

This repo was brought to you by the amazing Deep learning and GANs team of Neurohackademy 2019:
Alberto Lazari [alberto.lazari@univ.ox.ac.uk]
Anna Truzzi [truzzia@tcd.ie]
Bastian David [Bastian.david90@gmail.com]
Benjamin Wade [benjamin.sc.wade@gmail.com]
Jeffrey Durieux [j.durieux@fsw.leidenuniv.nl]
Meltem Atay [meltemiatay@gmail.com]
Suniyya Waraich [suniyya94@gmail.com]

Original GAN Paper
@inproceedings{goodfellow2014generative,
  title={Generative adversarial nets},
  author={Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua},
  booktitle={Advances in neural information processing systems},
  pages={2672--2680},
  year={2014}
}

About

Neurohack project deep learning and GANs

License:MIT License


Languages

Language:Jupyter Notebook 98.0%Language:Python 1.9%Language:Shell 0.1%Language:R 0.0%