Architecture Exploration and Customization Tool of Deep Neural Networks for Edge Devices

Lim, Seung-Ho; Kang, Shin-Hyeok; Ko, Byeong-Hyun; Roh, Jae Won; Lim, Chaemin; Cho, Sang-Young

doi:10.1109/icce53296.2022.9730351

Cited by 1 publication

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DLA VP is based on RISC-V embedded processor and has a dedicated acceleration module for convolutional neural network, so hardware exploration is possible by executing the customized neural network models through DLA platform and inferring the performance of the deep learning model on edge device. This is an extended version of the previous paper published as an abstract at ICCE 2022 [25], in which this paper is focused on the integrated framework with GUI interface, inference engine, and hardware virtual platform for edge device which is also our previous work [15], and additionally gives experimental results. The organization of this paper is as follows.…”

Section: Introductionmentioning

confidence: 99%

An Integrated Analysis Framework of Convolutional Neural Network for Embedded Edge Devices

Lim

Kang

et al. 2022

Electronics

View full text Add to dashboard Cite

Recently, IoT applications using Deep Neural Network (DNN) to embedded edge devices are increasing. Generally, in the case of DNN applications in the IoT system, training is mainly performed in the server and inference operation is performed on the edge device. The embedded edge devices still take a lot of loads in inference operations due to low computing resources, so proper customization of DNN with architectural exploration is required. However, there are few integrated frameworks to facilitate exploration and customization of various DNN models and their operations in embedded edge devices. In this paper, we propose an integrated framework that can explore and customize DNN inference operations of DNN models on embedded edge devices. The framework consists of the GUI interface part, the inference engine part, and the hardware Deep Learning Accelerator (DLA) Virtual Platform (VP) part. Specifically it focuses on Convolutional Neural Network (CNN), and provides integrated interoperability for convolutional neural network models and neural network customization techniques such as quantization and cross-inference functions. In addition, performance estimation is possible by providing hardware DLA VP for embedded edge devices. Those features are provided as web-based GUI interfaces, so users can easily utilize them.

show abstract

Section: Introductionmentioning

confidence: 99%