extractor.train()?
yunsangq opened this issue · comments
Hi, Thanks for your code!!
extractor was not included in the optimizer parameter.
So, I think the extractor was only used for inference, but wonder why used train().
In this case, batch_norm different results than eval().
because running_mean, running_var changed when train().
Line 148 in 5307795
Line 207 in 5307795
Line 78 in 5307795