ConvMAE
ConvMAE copied to clipboard
about the training loss
Hello, dear, master! I observe that the training loss decrease from 0.42 to 0.39 spending too much epoch. So, I have a question that it really have a big different for the test result when the training loss decrease from 0.42 to 0.39?
By the way, the above training loss is come from base model log.txt.