NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications



Abstract

This work proposes an algorithm, called NetAdapt, that automatically adapts a pre-trained deep neural network to a mobile platform given a resource budget. While many existing algorithms simplify networks based on the number of MACs or weights, optimizing those indirect metrics may not necessarily reduce the direct metrics, such as latency and energy consumption. To solve this problem, NetAdapt incorporates direct metrics into its adaptation algorithm. These direct metrics are evaluated using empirical measurements, so that detailed knowledge of the platform and toolchain is not required. NetAdapt automatically and progressively simplifies a pre-trained network until the resource budget is met while maximizing the accuracy. Experiment results show that NetAdapt achieves better accuracy versus latency trade-offs on both mobile CPU and mobile GPU, compared with the state-of-the-art automated network simplification algorithms. For image classification on the ImageNet dataset, NetAdapt achieves up to a 1.7x speedup in measured inference latency with equal or higher accuracy on MobileNets (V1&V2).


Illustration of NetAdapt
Algorithm Flow of NetAdapt

Illustration of NetAdapt

Algorithm Flow of NetAdapt


Lookup Tables for Fast Resource Estimation
Performance on ImageNet Validation Set (MobileNet V1, Mobile CPU on Google Pixel 1)

Lookup Tables for Fast Resource Estimation

Performance on ImageNet Validation Set (MobileNet V1, Mobile CPU on Google Pixel 1)



Downloads


BibTeX


@InProceedings{eccv_2018_yang_netadapt,
	author = {Yang, Tien-Ju and Howard, Andrew and Chen, Bo and Zhang, Xiao and Go, Alec and Sandler, Mark and Sze, Vivienne and Adam, Hartwig},
	title = {NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications},
	booktitle = {The European Conference on Computer Vision (ECCV)},
	month = {September},
	year = {2018}
}