Login / Signup

Training EfficientNets at Supercomputer Scale: 83% ImageNet Top-1 Accuracy in One Hour.

Arissa WongpanichHieu PhamJames DemmelMingxing TanQuoc V. LeYang YouSameer Kumar
Published in: IPDPS Workshops (2021)
Keyphrases
  • high accuracy
  • massively parallel
  • prediction accuracy
  • computational cost
  • error rate
  • image segmentation
  • multiscale
  • building blocks
  • training samples
  • training examples
  • object categories