Home > deep learning > Learning deep learning (project 5, generate new celebrity faces)

Learning deep learning (project 5, generate new celebrity faces)

In this class project, I used generative adversarial network (GAN) to generate new images of faces, similar to celebrity faces in the database.

The model we use is a deep convolutional network, which has been used widely in image classification.

First, we use the MNIST database (collection of 60,000 handwriting digits). After the training, the model can generate digits similar to what we have in the training set. We only trained it for two epochs.  I believe we can generate more realistic images if we train it longer.

Generate new handwriting digits

Generate new handwriting digits

Then we use ~200,000 images of celebrity faces to train our model. The training takes much longer time, but with my Nvidia 1080 Ti it’s fast. In the beginning, just after learning from 20,000 images, the model was able to generate face-like patterns. Then after the complete 10 epoch training, it generate very clear faces.

Generate new faces

Generate new faces

The project can be found at http://www.alivelearn.net/deeplearning/dlnd_face_generation.html

Author: Xu Cui Categories: deep learning Tags:
Try Stork, a research tool we developed

Stork is a publication alert app developed by us at Stanford. As a researcher we often forget to follow up important publications - and it's practically impossible to search many keywords or researchers' names everyday. Stork can help us to search everyday and notifies us when there are new publications/grants. How Stork helped me?

About the author:

Xu Cui is a human brain research scientist in Stanford University. He lives in the Bay Area in the United States. He is also the founder of Stork (smart publication alert app), PaperBox and BizGenius.


He was born in He'nan province, China. He received education in Beijing University(BS), University of Tennessee (Knoxville) (MS), Baylor College of Medicine (PhD) and Stanford University (PostDoc). Read more ...
  1. No comments yet.