-
Notifications
You must be signed in to change notification settings - Fork 122
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
SVHN normalization issue #11
Comments
Hi! |
better results mean that it provides faster convergence and higher accuracy. which the previous normalization technique was unable to achieve. |
ok |
Yes i was asking the permission to have a pull request. Let me just make a graph comparison of first 6 epochs of both methods. |
Hm, so huge difference. |
It seems it image is substracted by 255 then divided by 2*255, why this one works better? |
Hi ZhenyF! Actually I still not compare normalization methods - so I have no answer for your question. You may try both approaches and tell about the difference |
normalization process of SVHN images has issues. I have changed it which yields much better results.
elseif normalization_type =='mean_0':
train_n = np.full(((images.shape(0),images.shape(1),images.shape(3)),255.0,dtype-np.float32)
pixel_depth=255.0
images = ((images-train_n)/2)/pixel_depth
The text was updated successfully, but these errors were encountered: