Linear learning-rate scaling plus warmup lets minibatch size 8192 train ResNet-50 on ImageNet in one hour at full small-batch accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 1years
2017 1verdicts
ACCEPT 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
Linear learning-rate scaling plus warmup lets minibatch size 8192 train ResNet-50 on ImageNet in one hour at full small-batch accuracy.