why not using dropout in the wide resnet as done in the wide resnet paper? about mixmatch

[carlini]

Two reasons. First, We wanted mixmatch to be as simple as possible and dropout is extra complexity. And second, we tried briefly, and it didn't seem to do much very much (the original paper found something like +0.1% gains, and we saw something around that).

thank you, that make sense!

i have one more question, what does the function "tune" in your code do?

mixmatch/libml/train.py

Line 175 in 1011a1d

def tune(self, train_nimg):

I have a hard time relating it to the other part of the code

[carlini]

You can basically ignore it. It's used to adjust batchnorm statistics at eval time but in practice is usually a no-op.

thanks