Abstract
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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Number of internet of things (IoT) connected devices worldwide from 2019 to 2030. https://www.statista.com/statistics/1183457/iot-connected-devices-worldwide/. Accessed 26 Aug 2021
Cisco annual internet report (2018–2023) white paper. https://www.cisco.com/c/en/us/solutions/collateral/executive-perspectives/annual-internet-report/white-paper-c11-741490.html. Accessed 26 Aug 2021
Shekhar, S., Gokhale, A.: Dynamic resource management across cloud-edge resources for performance-sensitive applications. In: 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, pp. 707–710, May 2017
Farhan, L., Kharel, R., Kaiwartya, O., Quiroz-Castellanos, M., Alissa, A., Abdulsalam, M.: A concise review on internet of things (IoT) -problems, challenges and opportunities. In: 2018 11th International Symposium on Communication Systems, Networks Digital Signal Processing (CSNDSP), pp. 1–6, July 2018
Lai, L., Suda, N.: Rethinking Machine Learning Development and Deployment for Edge Devices (2018). CoRR, vol. abs/1806.07846
Sharma, K., Nandal, R.: A literature study on machine learning fusion with IoT. In: 2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI), pp. 1440–1445, April 2019
David, R., et al.: TensorFlow lite micro: embedded machine learning on TinyML systems (2020). CoRR, vol. abs/2010.08678
Krishnamoorthi, R.: Quantizing deep convolutional networks for efficient inference: a whitepaper (2018). CoRR, vol. abs/1806.08342
Mitschke, N., Heizmann, M., Noffz, K.-H., Wittmann, R.: A fixed-point quantization technique for convolutional neural networks based on weight scaling. In: IEEE International Conference on Image Processing, pp. 3836–3840, September 2019
Liberis, E., Lane, N.D.: Neural networks on microcontrollers: saving memory at inference via operator reordering (2019). CoRR, vol. abs/1910.05110
Mocerino, L., Calimera, A.: Fast and accurate inference on microcontrollers with boosted cooperative convolutional neural networks (BC-Net). IEEE Trans. Circuits Syst. I: Reg. Papers 68, 77–88 (2021)
TensorFlow Lite. https://www.tensorflow.org/lite. Accessed 26 Aug 2021
uTensor. https://github.com/uTensor/uTensor. Accessed 26 Aug 2021
Lai, L., Suda, N., Chandra, V.: CMSIS-NN: Efficient neural network kernels for arm Cortex-M CPUs (2018)
Dennis, D.K., et al.: EdgeML: Machine Learning for resource-constrained edge devices
Eloquent TinyML. https://github.com/eloquentarduino/EloquentTinyML/. Accessed 26 Aug 2021
Goodfellow, I.J., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). http://www.deeplearningbook.org
LeCun, Y., Cortes, C., Burges, C.: MNIST handwritten digit database. ATT Labs, vol. 2(2010). http://yann.lecun.com/exdb/mnist
Alpaydin, E., Kaynak, C.: Optical Recognition of Handwritten Digits. UCI Machine Learning Repository (1998)
Cohen, G., Afshar, S., Tapson, J., Schaik, A.V.: EMNIST: extending MNIST to handwritten letters. In: 2017 International Joint Conference on Neural Networks (IJCNN) (2017)
Cun, L., et al.: Handwritten digit recognition with a back-propagation network. In: Advances in Neural Information Processing Systems, pp. 396–404. Morgan Kaufmann (1990)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Estrebou, C.A., Fleming, M., Saavedra, M.D., Adra, F., De Giusti, A.E. (2022). Lightweight Convolutional Neural Networks Framework for Really Small TinyML Devices. In: Narváez, F.R., Proaño, J., Morillo, P., Vallejo, D., González Montoya, D., Díaz, G.M. (eds) Smart Technologies, Systems and Applications. SmartTech-IC 2021. Communications in Computer and Information Science, vol 1532. Springer, Cham. https://doi.org/10.1007/978-3-030-99170-8_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-99170-8_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-99169-2
Online ISBN: 978-3-030-99170-8
eBook Packages: Computer ScienceComputer Science (R0)