MATLAB Answers

Can we change the input size of a pretrained network for transfer learning

295 views (last 30 days)
Arjun Desai
Arjun Desai on 26 May 2018
Commented: Robert Jansen on 24 Aug 2020
I want to use transfer learning on the Resnet-50 architecture trained on Imagenet. I noticed that the input size into the Resnet-50 architecture is [224 224 3]. However my images are [150 150 3]. I was wondering if there were a way to change the input size of the input layer rather than resizing my images.
  3 Comments
Robert Jansen
Robert Jansen on 24 Aug 2020
None of these answers the original question which is again if there "were a way to change the input size of the input layer rather than resizing my images." i.e. can we change resnet50 to accept (unaltered) a different size image? Everyones answer is to resample the input. The question was explicitely not that! Pehaps the answer is no.

Sign in to comment.

Answers (1)

BERGHOUT Tarek
BERGHOUT Tarek on 16 Apr 2019
yes this methode is cold:
1- if you are changing the neumber of neurons from N to n where N>n: this is called :'constructive' learning
2- if you are changing the neumber of neurons from N to n where N<n: this is called :'distructive' learning
but retraining alwayse requeired , not from the begining but from the final weights that u have in final net
if you want to found some papaers in this area use this key words :
neural networks with additive hidden nodes ; distructive neural nets .....etc. good luck.
  2 Comments

Sign in to comment.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by