psrahul / dcgan

Implementation of DCGAN for face generation

Face Generating GAN

A deep convolutional GAN was trained from scratch on the Large scale CelebFaces dataset^[1] consisting of 200k images of faces.

A random sample vector as well as a dropout was used in both the Discriminator and the Generator to induce noise.

Various values of dropouts were tried.

Training Method

Download the images into data/celeba/ folder in the same directory.

./train.py --d1 [argument] --d2 [argument]

d1 and d2 are dropout values that are applied on the odd and even layers of the network respectively.They can be independently chosen.

Sample Generation

./sample_generator.py --d1 [argument] --d2 [argument]

Model state dictionaries for models with different dropouts values are provided for trained models in models folder

Sample Images

Some generated face images are stored in samples folder with the d1 and d2 used.

Future Scope

Decrease single mode generator outputs by adding more random noise to the generator network

References

[1] http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html
[2] https://pytorch.org/tutorials/beginner/dcgan_faces_tutorial.html