MNIST example transform

[astorfi]

Hi,

In the mnist example, why do you use the following transform and what's the reason behind those numbers:

transforms.Normalize((0.1307,), (0.3081,))

Thank you

[Darktex]

This tracks the MNIST example in PyTorch.

[astorfi]

Sorry if I could not convey what I meant.
I understand it tracks that. My question is why 0.1307 and 0.3081?
Thank you

[JohnlNguyen]

0.1307 and 0.3081 are the global mean and standard deviation of the MNIST dataset. Typically you normalize by the global mean and standard deviation in the transform

[astorfi]

Thank you.