TransWikia.com

CNN kernel location for input image

Data Science Asked by Benedict K. on August 10, 2021

Given a CNN, say AlexNet:
AlexNet

How could one relate kernel locations at the 3rd conv block, i.e 13×13 filter size to the input image. Would that give a meaningful representation in terms of the input image.

I was thinking of just upsampling the location, from 13×13 to 224×224.

Add your own answers!

Ask a Question

Get help from others!

© 2024 TransWikia.com. All rights reserved. Sites we Love: PCI Database, UKBizDB, Menu Kuliner, Sharing RPP