tensorflow-generative-model-collections

tensorflow-generative-model-collections copied to clipboard

Muzhi1920

can you add hinge loss

shaonianruntu

Question about batch normalization in WGAN_GP

2

Thank for your work! I'm confused about the batch normalization layer used in the discriminator of wgan_gp. I think there shouldn't be any batch normalization layer in the discriminator. I...

YukiRain

Gradient Penalty code error in WGAN_GP

2

at 113 line in WGAN_GP, I recommend changing the code `alpha = tf.random_uniform(shape=self.inputs.get_shape(), minval=0.,maxval=1.)` to `alpha = tf.random_uniform(shape=[BATCH_SIZE,1,1,1], minval=0.,maxval=1.)` Because It must be created **one** alpha value for each batch

jwc0906

Thanks for sharing the code. However, it seems the Tensorflow VAE doesn't have implementation for color images, eg. cifar10 data, only MNIST and fashion MNIST is available.Also, the Pytorch version...

k123jack

Thank you for sharing your codes. I found that there is no weight clipping in the paper Least Squares Generative Adversarial Networks. The weight clipping is used in the paper...

AliceAria

Not an issue, but a request

2

Hi @hwalsuklee , Thank you for sharing this neat-n-clean code... It's really helpful. I have two requests: **1.** Could you please provide a model to generate RGB data like: CIFAR...

ArghyaPal

request about input data

1

Thank you very much for sharing your perfect code with everyone. I learned a lot from it. I found that in all GAN networks, your input data is binary image...

Mukefan

Thanks for your code! I found that Discriminator los sfunction of w-gan is the same as Discriminator los sfunction of gan in your code,but actually not! Pleace check it!

changkaiyupingwen

Fix ACGAN training

1

The ACGAN training procedure is not optimal

yang-song