Open ahmed-fau opened 6 years ago
Hi,
I am a little confused about taking only the zero index of gradient tensor in calculating the penalty:
gradients = tf.gradients(Discriminator(interpolates), [interpolates])[0]
Why is it not possible to take the whole grad tensor ?
Best
Hi,
I am a little confused about taking only the zero index of gradient tensor in calculating the penalty:
gradients = tf.gradients(Discriminator(interpolates), [interpolates])[0]
Why is it not possible to take the whole grad tensor ?
Best