xiaopanchen
xiaopanchen
where is the AttentionNet?
reg = l1_loss(generated[:, :, :, :-1], generated[:, :, :, 1:]) \ + l1_loss(generated[:, :, :-1, :], generated[:, :, 1:, :]) # reg = ( # torch.sum(torch.abs(generated[:, :, :, :-1] -...
When run CIFAR10_ConvClassifier_on_RotNet_NIN4blocks_Conv2_feats_K1000.py, there are some errors iin dataloader.py. if self.dataset_name == 'cifar10': labels = self.data.test_labels if (self.split == 'test') else self.data.train_labels data = self.data.test_data if (self.split == 'test') else...
Where is procedudre of the test, if I use the pretrained model on CACD-VS. And what is the data form of the test dataset? Thk.
The fid is not described in Fig 2. If it can be decripted, the readability would be improved.