See more
…curate (large loss numbers have strong slopes, but small loss numbers are flatter, allowing larger learning rates) while being computationally simple.
DRN-A-18 and DRN-A-34 outperform ResNet-18 and ResNet-34 in 1-crop top-1 accuracy by 2.43 and 2.92 percentage points, respectively. …
Since we always worked on the top priority tasks, we had no opportunity to work on anything but new features. We had no time to work on our te…