I've noticed that PyTorch's DataLoader is applying scaling to the input data with the MNIST dataset. I'm guessing its some sort of normalisation or scaling, but how do I actually find what transform is being applied, and how do I turn it off?
1 Answer
$\begingroup$ $\endgroup$
1 It was the "ToTensor" transform used by the dataset, which scales the elements to the range [0,1].
- $\begingroup$ Your answer could be improved with additional supporting information. Please edit to add further details, such as citations or documentation, so that others can confirm that your answer is correct. You can find more information on how to write good answers in the help center. $\endgroup$2023-11-11 02:08:16 +00:00Commented Nov 11, 2023 at 2:08