StevenLauHKHK comments

Repositories
Issues
Comments

Results 2 comments of


                                            StevenLauHKHK

Replicate paper results

@kumar-shridhar How to reproduce the validation accuracy as stated in the paper on the cifar10 dataset? The network cannot break through 64% in validation accuracy when I use the same...

Question about the loss calculation

> Hi, > > Thanks for contributing the source code. I have some questions about the loss calculation in > > https://github.com/zhiqiangdon/online-augment/blob/9d46ab4789f6cd91b84fd05445866f3b3927e94f/train_aug_stn.py#L154 > > ![image](https://user-images.githubusercontent.com/37952703/111310083-a3ba2080-8697-11eb-85d5-26e86a136067.png) According to the paper, for...