Skip to content
This repository has been archived by the owner on Jun 25, 2024. It is now read-only.

Did this implementation do the train data normalization? #145

Open
sonallhay opened this issue Aug 29, 2018 · 0 comments
Open

Did this implementation do the train data normalization? #145

sonallhay opened this issue Aug 29, 2018 · 0 comments

Comments

@sonallhay
Copy link

sonallhay commented Aug 29, 2018

After saved the xml by the code get_data_from_XML.py, I couldn't find train data & test data normalization in the Generator class. Is there need to be added? Or not implement it for a reason?
Sth like this is what I'm trying to look for in the code.
#z-score
mean = np.mean(x_train,axis=(0,1,2,3))
std = np.std(x_train,axis=(0,1,2,3))
x_train = (x_train-mean)/(std+1e-7)
x_test = (x_test-mean)/(std+1e-7)

@sonallhay sonallhay changed the title Did this implementation did the train data normalization? Did this implementation do the train data normalization? Aug 30, 2018
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant