|
|
|
|
|
|
by belval
1846 days ago
|
|
|
The classic "we achieve SOTA on ImageNet by using a novel training procedure" where they just played with learning rate schedules until they got 0.1% over previous SOTA. To be fair to there are a lot of smells in DL papers, usually you can tell whether an approach is worth your time by looking at code availability, lab, previous publications and the conference where it was published. |
|
|