Closed hsm207 closed 6 years ago
In page 7 of the paper, it says:
Also, for a pair of generated images in different domains, we minimized the L1 distance between the features extracted by the highest layer of the discriminators...
And in the code in cocogan_trainer_da,py, this is implemented as follows:
dummy_variable = Variable(torch.zeros(fake_feat_aa.size())) feature_loss_a = self._compute_ll_lloss(fake_feat_ab - fake_feat_aa, dummy_variable) feature_loss_b = self._compute_ll_loss(fake_feat_ba - fake_feat_bb, dummy_variable)
Isn't this L2 loss because self._compute_ll_loss is implemented usingtorch.nn.MSELoss()?
self._compute_ll_loss
torch.nn.MSELoss()
Thanks for reporting. This is a typo in the paper. Will fix it in the nips final version.
In page 7 of the paper, it says:
And in the code in cocogan_trainer_da,py, this is implemented as follows:
Isn't this L2 loss because
self._compute_ll_loss
is implemented usingtorch.nn.MSELoss()
?