1
$\begingroup$

I was trying to normalize my input data images for feeding to my convolutional neural network and wanted to use standardize my input data. I referred to this article:

https://stackoverflow.com/questions/57200621/model-not-training-and-negative-loss-when-whitening-input-data

which says that featurewise_center and featurewise_std_normalization scales the images to range [-1,1]. Wouldn't training the model with this data lead to inaccuracies since the testing data would not be normalized in a similar way and would only range between [0,1]? How can I standardize my data while keeping it's range between [0,1]?

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.