EasyDeepLearn

What is MobileNet designed for?

medium

Answer

  • Efficient inference on mobile and embedded devices.
  • Uses depthwise-separable convolutions everywhere and a 'width multiplier' α scaling all layer widths, plus a resolution multiplier ρ.
  • MobileNet-v2 adds inverted residuals (expand → depthwise → project) and linear bottlenecks.
  • MobileNet-v3 uses NAS + h-swish. 5-10x smaller and faster than ResNet at similar accuracy.
Check yourself — multiple choice
  • Standard convolutions
  • Depthwise-separable convs + width/resolution multipliers — small, fast on mobile/embedded
  • Same size as VGG
  • Only for cloud

MobileNet: depthwise-separable convs + multipliers → mobile-scale efficient inference.

#architectures#computer-vision

Practise Deep Learning

214 interview questions in this topic.

Related questions