CNN weight sharing based on a fast accuracy estimation metric - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Article Dans Une Revue Microelectronics Reliability Année : 2021

CNN weight sharing based on a fast accuracy estimation metric

Etienne Dupuis
  • Fonction : Auteur
  • PersonId : 1085472
David Novo
Ian O'Connor
Alberto Bosio

Résumé

The computational workload involved in CNNs is typically out of reach for low-power embedded devices. The Approximate Computing paradigm can be exploited to reduce the CNN complexity since it improves performances and energy-efficiency by relaxing the need for fully accurate operations. In this work, we target weight-sharing as an approximate technique to reduce the memory footprint of a CNN. More in detail, we prove that optimizing the number of shared weights can enable significant network memory compression without noticeable accuracy loss without retraining or fine-tuning steps. However, we observe that the exploration time can easily explode in state-of-the-art CNNs. We thus propose the use of a fast accuracy estimation metric to guide the design space exploration and drastically reduce the exploration time up to 12×. Compared with state-of-the-art CNN approximation methods, we obtained more than 4× compression on GoogleNet on the ImageNet dataset with less than 1% accuracy loss in less than 5 h and without any retraining step.
Fichier principal
Vignette du fichier
CNN_WS_for_MR_21.pdf (2.47 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03257748 , version 1 (24-11-2021)

Identifiants

Citer

Etienne Dupuis, David Novo, Ian O'Connor, Alberto Bosio. CNN weight sharing based on a fast accuracy estimation metric. Microelectronics Reliability, 2021, 122, pp.#114148. ⟨10.1016/j.microrel.2021.114148⟩. ⟨hal-03257748⟩
81 Consultations
263 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More