Sample code for Triple GAN
This software is a python implementation of Triple GAN using chainer.
See the paper. https://arxiv.org/abs/1703.02291
Notice that this code had not implement gaussian noise in discriminator, Because I don't know how to implement it in chainer.
I only confirm the operation under this environment
- python 3.5.3
- chainer 3.3.0
- pillow 5.0.0
- numpy 1.14.0
- cupy 2.3.0
First of all, prepare mnist data as npy form.
Then, you can get mnist_train_img.npy, mnist_train_label.npy, mnist_test_img.npy and mnist_test_label.npy.
To train this model, do
I also made triple GAN code in tensorflow.
But, there are some bugs.