how to train fully connected layers?
hujinsen opened this issue · comments
When calculating affine parameters, Z_y is input into three full-connection layers, and then the mean and standard deviation are output. Why do we do this? How do full-connection layers train?
Hi @hujinsen , I think the MLP part works as a simple mapping function before we use them as the std and mean parameters of the adaptive instance normalization layer.
It is similar to the module in some other works, e.g., StyleGAN and MUNIT.
