hujie-frank/SENet

Training reproduce issue

amsword opened this issue · 4 comments

I tried to reproduce the training from scratch, but the accuracy is 5 point lower on Inception network. Can you share the solver file, e.g. number of iterations, learning rate policy, or any more details of the training?

Hi, @amsword
I also met the problem. Have you got any idea?

You can employ the data augmentation strategy described here and decrease the learning rate by a factor of 10 manually when the validation loss plateau, rather taking step strategy with fixed epoches.

@hujie-frank

Random Crop 8% ~ 100%
may only crop 8% of the whole image during training. Is it a typo (80% ~ 100%)?

It is not a typo, you can refer to "Training Methodology" in Going deeper with convolutions.