search

grey-eye / talking-heads

Our implementation of "Few-Shot Adversarial Learning of Realistic Neural Talking Head Models" (Egor Zakharov et al.)
GNU General Public License v3.0
593 stars 110 forks source link

About AdaptiveResidualBlock #27

Closed yujitong closed 5 years ago

yujitong commented 5 years ago

In the implementation of AdaptiveResidualBlock, 

def forward(self, x, mean1, std1, mean2, std2):
    residual = x

    out = self.conv1(x)
    out = self.in1(out, mean1, std1)
    out = F.relu(out)
    out = self.conv2(out)
    out = self.in2(out, mean1, std1)

Should it be self.in2(out, mean2, std2) instead?

castelo-software commented 5 years ago

Yep. You're right.