The discriminator loss

[yzp12]

Hi! Thank you for sharing the code! I notice in the paper the output of the discriminator is a vector. I am wondering if the loss of the discriminator is the different between two sum of the output vector(one for real and one for fake)? Thanks!

[Yang7879]

@yzp12 Yes, the output of the discriminator is a vector instead of a single scalar. Mean value of that vector is the loss. For a real reconstruction pair, the mean value is optimized to be "1", otherwise, the mean value is pushed to "0".