1
$\begingroup$

What is the preferred order of data augmentation and normalization? Is it the former followed by the latter?

$\endgroup$
1
  • 1
    $\begingroup$ Although I'm not really an expert in this topic, I would say that normalization should be applied after data augmentation, given that the latter can change e.g. the range of values of the inputs, and neural networks should generally learn better when the inputs are normalized. $\endgroup$ – nbro Feb 7 at 20:42

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.