-
I've been trying to train Decided to try I suspect I am doing something wrong and it's the user (my) error, but I fail to see. This is the first time I am using timm. Here are my hparams (I'm on this commit):
|
Beta Was this translation helpful? Give feedback.
Replies: 2 comments 2 replies
-
I wonder if I'm being very impatient:
Looking at summary of @michaelklachko can you recall what the training curves looked like when you trained |
Beta Was this translation helpful? Give feedback.
-
@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. |
Beta Was this translation helpful? Give feedback.
@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 thenxxxxx
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.