Skip to content

Efficientnet_b0 overfitting using "known good hparams" #1159

Answered by rwightman
dimitry12 asked this question in Q&A

You must be logged in to vote

@dimitry12 I don't see anything obviously wrong with the hparams, there is a significant lag between when EMA results start getting decent (and they can go the wrong direction for a while) ... the non-EMA numbers are more important to look at early on and they don't appear good.

You might want to check your dataset setup.. CLS_LOC looks like it might be the kaggle version? some ImageNet data layouts are a bit odd. timm expects folder per class with order by lexical sort of the nxxxxx wordnet id. And that holds for validation too, often validation is flat so you need to turn it into folders, 1000 folders for both the /train and /val (/validation works too) folder.

Replies: 2 comments 2 replies

You must be logged in to vote
1 reply
@michaelklachko

You must be logged in to vote
1 reply
@dimitry12

Answer selected by dimitry12
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