A Modular Software Library for Effective High Level Synthesis of Convolutional Neural Networks
| Autor: | Safdar Mahmood, Marcelo Brandalero, Michael Hübner, Hector Gerardo Munoz Hernandez |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
050101 languages & linguistics
business.industry Computer science 05 social sciences 02 engineering and technology Convolutional neural network Facial recognition system Field (computer science) Object detection Software Computer architecture High-level synthesis Modular programming 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing 0501 psychology and cognitive sciences Field-programmable gate array business |
| Zdroj: | Applied Reconfigurable Computing. Architectures, Tools, and Applications ISBN: 9783030445331 ARC |
| Popis: | Convolutional Neural Networks (CNNs) have applications in many valuable domains such as object detection for autonomous cars and security using facial recognition. This vast field of application usually places strict non-functional requirements such as resource-efficient implementations on the hardware devices, while at the same time requiring flexibility. In response, this work presents a C++-based software library of reusable modules to build arbitrary CNNs that support High-Level-Synthesis to be implemented as FPGA hardware accelerators for the inference process. Our work demonstrates how parametrization and modularization of basic building blocks of a CNN enable easier customization of the hardware to match the software model. This project also works with low-precision parameters throughout the CNN to provide a more resource-efficient implementation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|