Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Is the normalizatin values for CIFAR-10 correct? #68

Closed
abduallahmohamed opened this issue May 24, 2020 · 1 comment
Closed

Is the normalizatin values for CIFAR-10 correct? #68

abduallahmohamed opened this issue May 24, 2020 · 1 comment

Comments

@abduallahmohamed
Copy link
Contributor

abduallahmohamed commented May 24, 2020

Hi,
I believe that the CIFAR-10 normalization values used are actually for CIFAR-100.

The current values are (which actually are CIFAR-100 normalization values):

mean = [0.5071, 0.4867, 0.4408]
stdv = [0.2675, 0.2565, 0.2761]

But they should be:

mean=[0.49139968  0.48215841  0.44653091]
stdv= [0.24703223  0.24348513  0.26158784]

Ref: https://github.com/Armour/pytorch-nn-practice/blob/master/utils/meanstd.py

@gpleiss
Copy link
Owner

gpleiss commented May 25, 2020

That seems correct. Shouldn't make a difference in practice w/ batch norm.
I'd be happy to accept a PR fixing these numbers

abduallahmohamed added a commit to abduallahmohamed/efficient_densenet_pytorch that referenced this issue Feb 14, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants