Closed vdumoulin closed 6 years ago
This section was already refactored -> Do I have to update it again?
As described above, an improvement over this idea would be to concatenate \mathbf{z}z to the input of all layers in the neural network. This is in fact the approach adopted by the conditional variant of DCGAN [4] , a well-recognized class of network architectures for generative adversarial networks (GANs) [5] . The class label is broadcasted as a feature map and is concatenated to the input of convolutional and transposed convolutional layers in the generator and discriminator networks.
I update the figure: https://github.com/vdumoulin/distill-film/pull/129/files
Xavier