1587causalai / gan_basic_example Goto Github PK

Blog(in Chinese): 用GAN生成二维样本的小例子
Inspired & based on Dev Nag's GAN example:

1. Use batch size instead of cardinality to achieve better convergency, the original version is actually generating 100 (cardinality by default) dimensional gaussian distribution for discriminator, so the convergency is BAD.
2. Use 2D samples, with visualization of training.
3. Demo of conditional GAN.
4. GPU support.

Play with GAN to generate 2D samples that you can define your own probability density function (PDF) with a gray image.

python sampler.py

Will demo 10000 samples from the PDF defined by a gray image.

python gan_demo.py inputs/zig.jpg

Training will be visualized as the following:

More examples:

For more complex distributions, conditional GAN is much better. This demo reads distributions from different pdfs, encoding conditions as one-hot vector.

python cgan_demo.py inputs/binary

Training will be visualized as the following:

Compared to vanilla GAN version:

More examples:
Vortex with C-GAN

Vortex with vanilla GAN

Pentagram with C-GAN

Pentagram with vanilla GAN

python gan_demo.py -h