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.

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

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

Capotondi A.
;
Rusci M.;Benini L.
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.
2020
Capotondi A., Rusci M., Fariselli M., Benini L. (2020). CMix-NN: Mixed Low-Precision CNN Library for Memory-Constrained Edge Devices. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS. II, EXPRESS BRIEFS, 67(5), 871-875 [10.1109/TCSII.2020.2983648].
Capotondi A.; Rusci M.; Fariselli M.; Benini L.
File in questo prodotto:
File Dimensione Formato  
cmix_nn_tcas_II_disclaimer.pdf

Open Access dal 28/09/2020

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 974.22 kB
Formato Adobe PDF
974.22 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/762836
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 96
  • ???jsp.display-item.citation.isi??? 76
social impact