Lightweight Convolutional Neural Networks Framework for Really Small TinyML Devices

被引：0
|
作者：
Estrebou, Cesar A. [1 ]
Fleming, Martin [2 ]
Saavedra, Marcos D. [2 ]
Adra, Federico [2 ]
De Giusti, Armando E. [1 ,3 ]
机构：
[1] Natl Univ La Plata, Informat Res Inst LIDI, CICs Associated Res Ctr, RA-1900 La Plata, Argentina
[2] Natl Univ La Plata, Sch Informat, RA-1900 La Plata, Argentina
[3] CONICET Natl Council Sci & Tech Res, Buenos Aires, DF, Argentina
来源：
SMART TECHNOLOGIES, SYSTEMS AND APPLICATIONS, SMARTTECH-IC 2021 | 2022年 / 1532卷
关键词：
Machine learning; Convolutional neural networks; TinyML; Microcontrollers; Framework;
D O I：
10.1007/978-3-030-99170-8_1
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper presents a lightweight and compact framework designed to perform convolutional neural network inference on severely hardware constrained microcontrollers. A review of similar open source libraries is included and experiments are developed to compare their capabilities on several different microcontrollers. The proposed framework implementation shows at least a three-time improvement over the Google Tensorflow Lite Micro implementation with respect to memory usage and inference time.
引用
收藏
页码：3 / 16
页数：14
相关论文
共 50 条
  • [1] TinyML Olive Fruit Variety Classification by Means of Convolutional Neural Networks on IoT Edge Devices
    Hayajneh, Ali M.
    Batayneh, Sahel
    Alzoubi, Eyad
    Alwedyan, Motasem
    [J]. AGRIENGINEERING, 2023, 5 (04): : 2266 - 2283
  • [2] SSP Framework: A New Approach to Designing Lightweight Convolutional Neural Networks
    Turay, Tolga
    Vladimirova, Tanya
    [J]. IEEE ACCESS, 2022, 10 : 102292 - 102307
  • [3] Framework for automatic segmentation of breast cancer using lightweight convolutional neural networks
    Pires, Kleber S.
    Zampirolli, Francisco A.
    [J]. 17TH INTERNATIONAL SYMPOSIUM ON MEDICAL INFORMATION PROCESSING AND ANALYSIS, 2021, 12088
  • [4] FitCNN: A Cloud-Assisted Lightweight Convolutional Neural Network Framework for Mobile Devices
    Li, Shiming
    Liu, Duo
    Xiang, Chaoneng
    Liu, Jianfeng
    Ling, Yingjian
    Liao, Tianjun
    Liang, Liang
    [J]. 2017 IEEE 23RD INTERNATIONAL CONFERENCE ON EMBEDDED AND REAL-TIME COMPUTING SYSTEMS AND APPLICATIONS (RTCSA), 2017,
  • [5] Review of Lightweight Deep Convolutional Neural Networks
    Chen, Fanghui
    Li, Shouliang
    Han, Jiale
    Ren, Fengyuan
    Yang, Zhen
    [J]. ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING, 2024, 31 (04) : 1915 - 1937
  • [6] Review of Lightweight Deep Convolutional Neural Networks
    Fanghui Chen
    Shouliang Li
    Jiale Han
    Fengyuan Ren
    Zhen Yang
    [J]. Archives of Computational Methods in Engineering, 2024, 31 : 1915 - 1937
  • [7] Review of research on lightweight convolutional neural networks
    Zhou, Yan
    Chen, Shaochang
    Wang, Yiming
    Huan, Wenming
    [J]. PROCEEDINGS OF 2020 IEEE 5TH INFORMATION TECHNOLOGY AND MECHATRONICS ENGINEERING CONFERENCE (ITOEC 2020), 2020, : 1713 - 1720
  • [8] A Design Space Exploration Framework for Convolutional Neural Networks Implemented on Edge Devices
    Tsimpourlas, Foivos
    Papadopoulos, Lazaros
    Bartsokas, Anastasios
    Soudris, Dimitrios
    [J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2018, 37 (11) : 2212 - 2221
  • [9] Lightweight Convolutional Neural Networks for Vehicle Target Recognition
    Wang, Jintao
    Ji, Ping
    Xiao, Wen
    Ni, Tianwei
    Sun, Wei
    Zeng, Sheng
    [J]. 2020 IEEE 5TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION ENGINEERING (IEEE ICITE 2020), 2020, : 245 - 248
  • [10] Lightweight convolutional neural networks for player detection and classification
    Lu, Keyu
    Chen, Jianhui
    Little, James J.
    He, Hangen
    [J]. COMPUTER VISION AND IMAGE UNDERSTANDING, 2018, 172 : 77 - 87
12345