|
@barret_zoph | |||||
|
*New paper* RandAugment: a new data augmentation. Better & simpler than AutoAugment. Main idea is to select transformations at random, and tune their magnitude. It achieves 85.0% top-1 on ImageNet.
Paper: arxiv.org/abs/1909.13719
Code: git.io/Jeopl pic.twitter.com/equmk59K2i
|
||||||
|
||||||
|
Jeremy Howard
@jeremyphoward
|
19. stu |
|
Oh yes very relevant! We do like this paper :)
|
||
|
||
|
Alisher Abdulkhaev
@alisher_ai
|
19. stu |
|
|
||
|
Eric Schles
@EricSchles
|
19. stu |
|
Wow!!! Nice work
|
||
|
|
||
|
yosuke
@1004yyyytnk
|
19. stu |
|
so robust.nice.
|
||
|
|
||
|
Sakib
@Zooo000m
|
19. stu |
|
I should have come across this 1 week earlier. Anyways great work
|
||
|
|
||
|
Carlos Pedrinaci
@cpedrinaci
|
19. stu |
|
Looking forward to trying this out!
|
||
|
|
||
|
Diptodip
@diptodipdeb
|
19. stu |
|
xd
|
||
|
|
||