New answers tagged

1 vote
Accepted

Does the Weights of Discriminator get updated when traning Generators in GANs?

Since you are using Pytorch, an optimizer can only update parameters wrapped inside it since initializing. Therefore, even if the gradient of discriminator parameters exists while updating generator, ...
user avatar
  • 857
0 votes

ImageNet Dataset (for PyTorch VGG16 training)

These are the detailed steps on how I obtained ImageNet and ran a PyTorch example training on it: ...
user avatar
2 votes
Accepted

"Tweaking" the cost function to penalize rarer cases more severely

Yes, you can use weighted MSE by applying different coefficients to each data point. Here is an implementation given by Francisco Massa at https://discuss.pytorch.org/t/how-to-implement-weighted-mean-...
user avatar
-1 votes

ImageNet Dataset (for PyTorch VGG16 training)

ImageNet is available in torchvision datasets. https://pytorch.org/vision/stable/generated/torchvision.datasets.ImageNet.html
user avatar
  • 269
1 vote
Accepted

what is `Normalize` for in PyTorch transfer learning tutorial?

Those are mean and standard deviation used to standardize each channel of the images from IMAGENET used to train the torchvision pretrained models. Since the models were trained using this ...
user avatar

Top 50 recent answers are included