-
Notifications
You must be signed in to change notification settings - Fork 500
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
data normalization - possible bug #20
Comments
This "normalize" converts images from [0,+1] to [-1,+1]. We do the actual imagenet normalization here: https://github.com/richzhang/PerceptualSimilarity/blob/master/models/networks_basic.py#L112 . |
Hi So the question is: Where did you get this values and what do they mean? |
Thanks for the question. The imagenet statistics assume images are normalized between [0,1]. This code uses images from [-1,+1], so the appropriate transformation is done (notice that the std is just doubled) |
Thank you for the fast answer =) |
I noticed that the data normalization is
(for example in twoafc_dataset.py).
The imagenet normalization coefficients are
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]
This raises the questions:
The text was updated successfully, but these errors were encountered: