Question about the feature maps

[subrtade662]

Hello, I have a question about the feature maps, which are fed into the style interpreter. It is said in the paper, that the feature maps are the outputs of AdaIN layers. However, the code below (forward function of the Gsynthesis block) suggests something different (x is the output of the second convolution layer in the block). Which one is the correct version ? Or am I missing something?

Thanks in advance

datasetGAN_release/models/stylegan1.py

Lines 397 to 410 in d9564d4

	def forward(self, x, dlatents_in_range, latent_after_trans=None):
	x = self.conv0_up(x)
	if latent_after_trans is None:
	x = self.epi1(x, dlatents_in_range[:, 0])
	else:
	x = self.epi1(x, dlatents_in_range[:, 0], latent_after_trans[0]) # latent_after_trans is a list
	x = self.conv1(x)
	if latent_after_trans is None:
	x1 = self.epi2(x, dlatents_in_range[:, 1])
	else:
	x1 = self.epi2(x, dlatents_in_range[:, 1], latent_after_trans[1])
	return x1, x