Open John1231983 opened 3 years ago
your acc is normal
Thanks @cavalleria but the log is unnormal.
Training Prec@1 44.824 (45.528) Training Prec@5 58.203 (57.886)
It should be 99%
If training precision gets to 99%, you have overfitted the data. It'll probably eventually hit 80-90% depending on depth if you leave it training much longer with lower learning rates, but it isn't necessary. Your learning rate is still fairly high so I wouldn't expect high training accuracy. If you have augmentation turned on, you can expect even lower training accuracy.
@xsacha @cavalleria thanks your comments but I refer log from https://github.com/HuangYG123/CurricularFace
The log shows at the same epoch
Training Prec@1 99.8 (100.0) Training Prec@5 100 (100)
Yeah that log looks wrong. You definitely should never get 100% training accuracy. Even close to it is bad. Your model will probably be bogus if you get 100% trained and you need to add more augmentation or training data.
The '1000' looks like a bug too.
Sorry it is typo :)
I used your code with AMP FP16 from pytorch 1.6. I achieved a good accuracy on validation set but showing the training accuracy is wrong. Do you have any suggestion to fix it? @xsacha @cavalleria . Thanks in advance This is my log
I think
Training Prec@1
andTraining Prec@5
should be near 100. This is my training codeAnd this is my head