Publication type: Conference paper
Type of review: Peer review (abstract)
Title: Framework to port neural networks to FPGA, suitable for realtime signal processing
Authors : Welti, Tobias
Moser, Aaron
Gelke, Hans-Joachim
et. al : No
Conference details: Embedded World Conference 2020, Nürnberg, 25.-27. Februar 2020
Issue Date: 2020
Publisher / Ed. Institution : WEKA
Language : English
Subjects : Artificial Intelligence; Convolutional neural network; Native FPGA implementation; Low latency inference; TensorFlow; Keras
Subject (DDC) : 004: Computer science
Abstract: Due to their hardware architecture, Field Programmable Gate Arrays (FPGAs) are optimally suited for the implementation of machine learning algorithms. So far, it is cumbersome to port a neural network (NN) to an FPGA. A frequently used solution is the implementation of NNs using the Open Compute Language (OpenCL) which can be converted to HDL code for use in the FPGA. While OpenCL supports the development of NN algorithms, it also adds unnecessary overhead to the FPGA netlist, limiting the performance of the FPGA. We have developed a framework for the conversion of fully connected, 1D- and 2D-convolutional NN layers to VHDL ode. The framework converts NN models that are trained in TensorFlow or Keras to a synthesizable VHDL code and creates a C model and testbench for verification. This enables nonlinear signal processing with NNs in real-time directly in the FPGA without the use of an embedded CPU.
URI: https://digitalcollection.zhaw.ch/handle/11475/19666
Fulltext version : Published version
License (according to publishing contract) : Licence according to publishing contract
Departement: School of Engineering
Organisational Unit: Institute of Embedded Systems (InES)
Appears in Collections:Publikationen School of Engineering

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.