FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search

Bichen WuXiaoliang DaiPeizhao ZhangYanghan WangFei SunYiming WuYuandong TianPeter VajdaYangqing JiaKurt Keutzer

   Papers with code   Abstract  PDF

Designing accurate and efficient ConvNets for mobile devices is challenging because the design space is combinatorially large. Due to this, previous neural architecture search (NAS) methods are computationally expensive... (read more)

Benchmarked Models

RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD