Hi,
What is the best way to deal with smaller images? Padding or resizing (enlarging)?
Hey @kamil_kurach, I did a little search and found this research paper.
To quote from it’s Introduction:
" This study proposes zero-padding for resizing images to the same size and compares it with the conventional approach of scaling images up (zooming in) using interpolation. Our study showed that zero-padding had no effect on the classification accuracy but considerably reduced the training time."
Just trying to help. Do share more if it helped! 