Benchmarking of DL Libraries and Models on Mobile Devices. (arXiv:2202.06512v2 [cs.LG] UPDATED)

Deploying deep learning (DL) on mobile devices has been a notable trend in
recent years. To support fast inference of on-device DL, DL libraries play a
critical role as algorithms and hardware do. Unfortunately, no prior work ever
dives deep into the ecosystem of modern DL libs and provides quantitative
results on their performance. In this paper, we first build a comprehensive
benchmark that includes 6 representative DL libs and 15 diversified DL models.
We then perform extensive experiments on …

arxiv benchmarking devices dl lg libraries mobile