AMC: AutoML for Model Compression and Acceleration on Mobile Devices
release_iwidedwqefhlliysn22ny5i72e
by
Yihui He, Ji Lin, Zhijian Liu, Hanrui Wang, Li-Jia Li, Song Han
2018
Abstract
Model compression is a critical technique to efficiently deploy neural
network models on mobile devices which have limited computation resources and
tight power budgets. Conventional model compression techniques rely on
hand-crafted heuristics and rule-based policies that require domain experts to
explore the large design space trading off among model size, speed, and
accuracy, which is usually sub-optimal and time-consuming. In this paper, we
propose AutoML for Model Compression (AMC) which leverage reinforcement
learning to provide the model compression policy. This learning-based
compression policy outperforms conventional rule-based compression policy by
having higher compression ratio, better preserving the accuracy and freeing
human labor. Under 4x FLOPs reduction, we achieved 2.7% better accuracy than
the handcrafted model compression policy for VGG-16 on ImageNet. We applied
this automated, push-the-button compression pipeline to MobileNet and achieved
1.81x speedup of measured inference latency on an Android phone and 1.43x
speedup on the Titan XP GPU, with only 0.1% loss of ImageNet Top-1 accuracy.
In text/plain
format
Archived Files and Locations
application/pdf 811.7 kB
file_mpcjfjulrjfrpnbh2rqgz52com
|
arxiv.org (repository) web.archive.org (webarchive) |
1802.03494v2
access all versions, variants, and formats of this works (eg, pre-prints)