Multi-objective autotuning of MobileNets across the full software/hardware stack

By Anton Lokhmotov, Nikolay Chunosov, Flavio Vella, G. Fursin. 2018

13 citations recorded by the source corpus.

We present a customizable Collective Knowledge workflow to study the execution time vs. accuracy trade-offs for the MobileNets CNN family. We use this workflow to evaluate MobileNets on Arm Cortex CPUs using TensorFlow and Arm Mali GPUs using several versions of the Arm Compute Library. Our optimizations for the Arm Bifrost GPU architecture reduce the execution time by 2--3 times, while lying on a Pareto-optimal frontier. We also highlight the challenge of maintaining the accuracy when deploying CNN models across diverse platforms. We make all the workflow components (models, programs, scripts, etc.) publicly available to encourage further exploration by the community.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition, Hardware and Architecture

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

1. Luca Benini
2. Davide Scaramuzza
3. Srinivasan Murali
4. Giovanni De Micheli

In Computer Vision and Pattern Recognition

1. Antonio Loquercio
2. Davide Scaramuzza
3. Francesco Conti
4. Luca Benini
5. Daniele Palossi
6. Eric Flamand
7. Vladlen Koltun
8. Daniel Cremers

In Hardware and Architecture

1. Luca Benini
2. Daniele Palossi
3. Giovanni De Micheli
4. Srinivasan Murali

Citations in the corpus

• A 64-mW DNN-Based Visual Navigation Engine for Autonomous Nano-Drones (2018, background): “While significant work has been done within academia [25]–[27] and industry (e.”