What if my learning rate plot shows no clear dip?

Hi there!

I’m trying to improve a classification model I’ve trained which distinguishes video game screenshots between super nintendo and sega megadrive

I’m getting okish results, but while looking for ways to speed up iteration, i tried the learning rate finder, and it doesnt have the pronounced dip i’ve seen in the examples.

this is resnet18

this is resnet34

Any guidance on what this graph suggests?

My guess is that it suggests my data isnt very good for learning?

this is my project so far

This lesson might be helpful: Practical Deep Learning for Coders - 17: Initialization/normalization

1 Like

Watched the vid. Thanks!

Looks like incrementing the lr smaller MAY help get a closer picture but most likely my model is not great…

I guess it literally means

“adjusting the learning rate aint gonna help you son, your problems are elsewhere”!