tensorflow-generative-model-collections
tensorflow-generative-model-collections copied to clipboard
Gradient Penalty code error in WGAN_GP
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
You are right. I have the same view.The performance improved after changing thie code.
You are right. I have the same view.The performance improved after changing thie code.
I have a question that wheather the bn in Discrimator should be removed?