Does the image size for convolutional neural networks have to be small?

by Amani   Last Updated October 18, 2018 09:19 AM

I'm new to Caffe. I'm trying to understand the rules of using convolutional neural networks. And my questions are:

  • is it mandatory for the images to be small for training?
  • is it mandatory for the images to be squared?

I'm asking this because the biggest example of images used I found is 512 x 512. Would it be counter-intuitive to use for example HD size images?



Related Questions


How to inprove SVHN result with Keras?

Updated March 02, 2017 20:19 PM


Receptive field of neurons in LeNet

Updated February 22, 2017 01:19 AM

Triplet Deep Learning Embedding Loss Functions

Updated April 13, 2017 21:19 PM