Low-precision integer arithmetic is a necessary ingredient for enabling Deep Learning inference on tiny and resource-constrained IoT edge devices. This brief presents CMix-NN, a flexible open-sourceCMix-NN is available at https://github.com/EEESlab/CMix-NN. mixed low-precision (independent tensors quantization of weight and activations at 8, 4, 2 bits) inference library for low bitwidth Quantized Networks. CMix-NN efficiently supports both Per-Layer and Per-Channel quantization strategies of weights and activations. Thanks to CMix-NN, we deploy on an STM32H7 microcontroller a set of Mobilenet family networks with the largest input resolutions ( 224 imes 224 ) and higher accuracies (up to 68% Top1) when compressed with a mixed low precision technique, achieving up to +8% accuracy improvement concerning any other published solution for MCU devices.

CMix-NN: Mixed Low-Precision CNN Library for Memory-Constrained Edge Devices / Capotondi, A.; Rusci, M.; Fariselli, M.; Benini, L.. - In: IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS. II, EXPRESS BRIEFS. - ISSN 1549-7747. - 67:5(2020), pp. 871-875. [10.1109/TCSII.2020.2983648]

CMix-NN: Mixed Low-Precision CNN Library for Memory-Constrained Edge Devices

Capotondi A.
;
2020

Abstract

Low-precision integer arithmetic is a necessary ingredient for enabling Deep Learning inference on tiny and resource-constrained IoT edge devices. This brief presents CMix-NN, a flexible open-sourceCMix-NN is available at https://github.com/EEESlab/CMix-NN. mixed low-precision (independent tensors quantization of weight and activations at 8, 4, 2 bits) inference library for low bitwidth Quantized Networks. CMix-NN efficiently supports both Per-Layer and Per-Channel quantization strategies of weights and activations. Thanks to CMix-NN, we deploy on an STM32H7 microcontroller a set of Mobilenet family networks with the largest input resolutions ( 224 imes 224 ) and higher accuracies (up to 68% Top1) when compressed with a mixed low precision technique, achieving up to +8% accuracy improvement concerning any other published solution for MCU devices.
67
5
871
875
CMix-NN: Mixed Low-Precision CNN Library for Memory-Constrained Edge Devices / Capotondi, A.; Rusci, M.; Fariselli, M.; Benini, L.. - In: IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS. II, EXPRESS BRIEFS. - ISSN 1549-7747. - 67:5(2020), pp. 871-875. [10.1109/TCSII.2020.2983648]
Capotondi, A.; Rusci, M.; Fariselli, M.; Benini, L.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11380/1227269
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 34
  • ???jsp.display-item.citation.isi??? 24
social impact