yangzhikai

The attention layer that you proposed is so excellent. Not only did it help me a lot, but it was also used by more people. I hope that it can...

Whether it is right about KL_loss

1

I find the calculation of KL-loss is different from VAE. Because: latent_loss = 0.5 * tf.reduce_sum(　tf.square(z_mean) + tf.square(z_stddev) 　　　　　　　　　　　　　　　　　　　　　　- tf.log(tf.square(z_stddev)) - 1,　1　) I think the "self.mu.pow(2) "...

I have no Idea of how to us these code . Should the code be used as "cd /root...." and "gan_cifar10.py" ?