My team is doing research in some kinds of Medical Image analysis for paper publication. I’m adopting some Fast.ai techniques such as LR finder and Annealing LR also. However, in term of comparison between model (such as 2DCNN , 3DCNN etc…) I wonder is it ok to use different LR to find best result?
Some people argue that we have to use fix learning rate and WD for scientific comparison. Does anyone has experience or any idea?