Getting significantly worse performance using BackboneFinetuning
Callback
#18855
Unanswered
sandeepmukh
asked this question in
code help: CV
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Hi! I am new to lightning, but have used pytorch a fair amount in the past. I'm trying to use the
BackboneFinetuning
callback, but I'm getting terrible results doing so verus just manually enabling gradients in theon_validation_epoch_end
hook.My architecture is roughly:
backbone: ResNet50
Classification Head: SelfAttention blocks
This is my
BackboneFinetuning
:BackboneFinetuning(unfreeze_backbone_at_epoch=3, backbone_initial_ratio_lr=1, verbose=True),
I have tried using different
backbone_initial_ratio_lr
with the same poor results.This approach is what is currently working:
Am I doing something obviously wrong?
Here are some reference training curves:

With bespoke implementation is green and using the callback is brown.
Beta Was this translation helpful? Give feedback.
All reactions