Choice of Layers for Processing z in Discriminator

[djgagne]

In the paper and code you used a set of 1x1 2D convolution layers to process the latent vector z in the discriminator. What was the motivation behind using 2D Convolutions versus fully connected layers or some other kind of convolutional layer? What other architectures did you try, and did you find success with any of those?

[vdumoulin]

Given that z is a vector, it can be interpreted as a 1x1xN stack of feature maps. In that case, a 1x1 convolution and a fully-connected layer are equivalent. I don't see how one could use another type of convolutional layer, though.

Hope that answers your question!