I have a set of images that I am using for a typical classification problem using Tensorflow. The images come in different sizes so I wrote a small piece of code to resize them all. But the question is what is the best strategy of resizing for training purposes? For example, is it better to resize them, no matter how they scale up or down, or it is better to keep the aspect ratio and add some artificial zero padding around the resized images? I believe this is a typical question with some existing studies or solutions. Appreciate your advice. Regards, Hamid
Asked
Active
Viewed 135 times
2
-
Great question but also quite broad :\ Can you add your code or at least pseudo-code for people to comment on? I have done a few experiments with padding etc. and so far cropping a centre square (see my linked question) performs best. – jtlz2 Jun 27 '19 at 11:23