Open vidda13 opened 7 years ago
I see that the pretrained model you provided runs at higher resolutions compared to the models I trained for a few style images. What might be the reason for this?Did you use VGG19 or normalised vgg?
I don't know the reason, but in the paper he says that he doesn't uses VGG19 at all.
OK, anyway the loss network wont be used once the training is complete. So, How can the FCN size be different ?
I see that the pretrained model you provided runs at higher resolutions compared to the models I trained for a few style images. What might be the reason for this?Did you use VGG19 or normalised vgg?