MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Andrew G. HowardMenglong ZhuBo ChenDmitry KalenichenkoWeijun WangTobias WeyandMarco AndreettoHartwig Adam

   Papers with code   Abstract  PDF

We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks... (read more)

Benchmarked Models

RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD
1
MobileNet x1.0
73.4%
--
2
MobileNet x0.75
69.9%
--
3
MobileNet x0.5
65.8%
--
4
MobileNet x0.25
53.7%
--