1
$\begingroup$

i just tried to improve my image dataset by inverting the images with a probability of 50% (means white background, black features transforms to black background, white features)

I thought this will improve the ability to recognize abstract features for my network. Right now, the network does not perform really well. Is inverting the intensity of images too much for a training algorithm to deal with?

$\endgroup$

0

You must log in to answer this question.

Browse other questions tagged .