Closed uestcwangxiao closed 3 years ago
虽然我没理解作者产生grid的过程和原因,但是感觉grid可以对应论文里的可训练参数h?
虽然我没理解作者产生grid的过程和原因,但是感觉grid可以对应论文里的可训练参数h?
但好像每一层都加了这个grid,而论文里只有在decoder第一层有这个h
It's true , that's just POS Embeeding, due to the z is one vector, It needs to be expanded to the same size as the feature map. Now I have removed the avg pool layer, so the shape of z change to (b, z_dim, map_h, map_w), there is no need to add POS Embeeding, pull the latest code to see it.
I see in the decoder.py, you cat the grid with the latent representation z_rep in each layer of the decoder network. I don't quite understand what its function, either how to generate grid? Is it a position coding ? Would it have any effect if it was removed?