Face Generator Project is a part of Udacity Deep Learning Nanodegree online course
Generate new faces using Generative Adversarial Networks (GANs).
The model is trained on the CelebFaces Attributes Dataset (CelebA):
It generates new human faces that look like this:
- Create a deeper model and use it to generate larger (say 128x128) images of faces.
- Read existing literature to see if you can use padding and normalization techniques to generate higher-resolution images.
- Use WGAN - Wasserstein loss with Gradient penalty to mitigate problems like mode collapse(where generated faces have features from just few faces in training dataset and not from entire distribution of Celeb A dataset) and stabilise training process.