Hi, guys. In your paper, you compared your results with some other methods. Did you report the median of best test error during training or median of test error after training? What is the common way to report results?
Besides, why did not you report the results using both data augmentation and dropout?
In our paper, we only report test error of one training pass (no median), after training finishes.
For other methods, we copy the results from their papers. Mostly they just report in the same way as ours.
We didn't use data augmentation and dropout at the same time. When there is data augmentation, there is no dropout, when there is dropout, there is no data augmentation.
Hi, guys. In your paper, you compared your results with some other methods. Did you report the median of best test error during training or median of test error after training? What is the common way to report results? Besides, why did not you report the results using both data augmentation and dropout?