Skip to content
Discussion options

You must be logged in to vote

Hi @fibr1900 , one possible reason is because the GPU memory is not big enough to train the models. For reverse distillation, you can try to use a smaller backbone, by changing the default backbone from wide_resnet50_2 to resnet18.

Replies: 2 comments

Comment options

You must be logged in to vote
0 replies
Answer selected by fibr1900
Comment options

You must be logged in to vote
0 replies
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
3 participants