CNN Inference Costs Estimation on Microcontrollers: the EST Primitive-based Model - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

CNN Inference Costs Estimation on Microcontrollers: the EST Primitive-based Model

Thomas Garbay
Wilfried Dron
  • Function : Author
  • PersonId : 1120757
Pedro Lusich
  • Function : Author
Imane Khalis
  • Function : Author
Bertrand Granado

Abstract

Neural network inference on embedded devices will have an important industrial impact on our society. Embedded devices are ubiquitous in many fields, like human activity recognition or visual object detection. As a matter of fact, Convolutional Neural Networks (CNNs) are now the best modality to solve most of computer vision problems. Although, the accuracy offered by these algorithms has a cost: an important energy consumption, a high execution time, and a significant memory footprint. This cost is a major challenge to implement CNNs within embedded devices with limited computational power, memory space and energy available. This makes prior estimation about the impact of a CNN on a given microcontroller, a design key point before applying neural network compression techniques. We introduce the EST primitive-based model to estimate the impact of a CNN on a microcontroller, regarding the latency, the power consumption and the needed memory space. The target hardware is the STM32L496ZG with CPU ARM Cortex M4 running at 14 different frequencies. Our model shows an average estimation error of 13.66% on latency, 5.52% on power consumption and 2.09% on needed memory space.
Fichier principal
Vignette du fichier
CNN Inference Costs Estimation on Microcontrollers the EST Primitive-based Model.pdf (469.74 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03485353 , version 1 (17-12-2021)

Identifiers

  • HAL Id : hal-03485353 , version 1

Cite

Thomas Garbay, Petr Dobias, Wilfried Dron, Pedro Lusich, Imane Khalis, et al.. CNN Inference Costs Estimation on Microcontrollers: the EST Primitive-based Model. 28th IEEE International Conference on Electronics Circuits and Systems IEEE ICECS 2021, Nov 2021, Dubaï, United Arab Emirates. ⟨hal-03485353⟩
102 View
279 Download

Share

Gmail Mastodon Facebook X LinkedIn More