Towards Enabling Dynamic Convolution Neural Network Inference for Edge Intelligence Article Swipe

MAKE IMPACT

Adewale Adeyemo , Travis Sandefur , Tolulope A. Odetola , Syed Rafay Hasan · YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2202.09461

Deep learning applications have achieved great success in numerous real-world applications. Deep learning models, especially Convolution Neural Networks (CNN) are often prototyped using FPGA because it offers high power efficiency and reconfigurability. The deployment of CNNs on FPGAs follows a design cycle that requires saving of model parameters in the on-chip memory during High-level synthesis (HLS). Recent advances in edge intelligence require CNN inference on edge network to increase throughput and reduce latency. To provide flexibility, dynamic parameter allocation to different mobile devices is required to implement either a predefined or defined on-the-fly CNN architecture. In this study, we present novel methodologies for dynamically streaming the model parameters at run-time to implement a traditional CNN architecture. We further propose a library-based approach to design scalable and dynamic distributed CNN inference on the fly leveraging partial-reconfiguration techniques, which is particularly suitable for resource-constrained edge devices. The proposed techniques are implemented on the Xilinx PYNQ-Z2 board to prove the concept by utilizing the LeNet-5 CNN model. The results show that the proposed methodologies are effective, with classification accuracy rates of 92%, 86%, and 94% respectively

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2202.09461

PDF

https://arxiv.org/pdf/2202.09461

OA Status

green

Cited By

2

Related Works

10

OpenAlex ID

https://openalex.org/W4226188219

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4226188219

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2202.09461

Digital Object Identifier

Title

Towards Enabling Dynamic Convolution Neural Network Inference for Edge Intelligence

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2022

Year of publication

Publication date

2022-02-18

Full publication date if available

Authors

Adewale Adeyemo, Travis Sandefur, Tolulope A. Odetola, Syed Rafay Hasan

List of authors in order

Landing page

https://arxiv.org/abs/2202.09461

Publisher landing page

PDF URL

https://arxiv.org/pdf/2202.09461

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2202.09461

Direct OA link when available

Concepts

Reconfigurability, Computer science, Control reconfiguration, Field-programmable gate array, Computer architecture, Inference, Deep learning, Edge device, Scalability, Convolutional neural network, Flexibility (engineering), Edge computing, Distributed computing, Enhanced Data Rates for GSM Evolution, Embedded system, Artificial intelligence, Computer engineering, Cloud computing, Database, Telecommunications, Operating system, Mathematics, Statistics

Top concepts (fields/topics) attached by OpenAlex

Cited by

2

Total citation count in OpenAlex

Citations by year (recent)

2023: 1, 2022: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload