Layer-Wise Filter Thresholding Based CNN Pruning for Efficient IoT Edge Implementations
作者:
Kalyanam L.K.;Joshi R.;Katkoori S.
通讯作者:
Kalyanam, L.K.
作者机构:
University of South Florida, Tampa, FL, United States
通讯机构:
University of South FloridaUnited States
语种:
英文
关键词:
Convolutional Neural Networks,IoT edge devices,Resource optimization,Threshold-based pruning
期刊:
IFIP Advances in Information and Communication Technology
ISSN:
1868-422X
年:
2024
卷:
683 AICT
页码:
76-93
会议名称:
6th IFIP International Conference on Internet of Things, IFIP IoT 2023
会议时间:
2 November 2023 through 3 November 2023
摘要:
This paper presents a novel approach for efficiently running convolutional neural networks (CNNs) on Internet of Things (IoT) edge devices. The proposed method utilizes threshold-based pruning to optimize pre-trained CNN models, enabling inference on resource-constrained IoT and edge devices. The pruning thresholds for each layer are iteratively adjusted using a range-based threshold pruning technique. The pre-trained network evaluates the accuracy of the pruned model and dynamically adjusts the pruning thresholds to maximize accuracy. The effectiveness of the proposed approach is validated on the widely-used LeNet benchmark network, with MNIST, Fashion-MNIST, and SVHN d...