Open dagarshali opened 4 years ago
On line 163 we have (loss = criterion(model(batch_y), batch_x))
batch_y = clean + noise model(batch_y) = x - output of the network.
If so, shouldn't the loss function be loss = criterion(model(batch_y),noise)?
I think the model is designed to predict noise
On line 163 we have (loss = criterion(model(batch_y), batch_x))
batch_y = clean + noise model(batch_y) = x - output of the network.
If so, shouldn't the loss function be loss = criterion(model(batch_y),noise)?