Result Details

XNOR net report

HRADIŠ, M.; KOHÚT, J. XNOR net report. Brno: Fingera s.r.o., 2017. 22 p.
Type
summary research report
Language
English
Authors
Hradiš Michal, Ing., Ph.D., DCGM (FIT)
Kohút Jan, Ing.
Abstract

This document summarizes implementations of XNOR nets and related experimental results. Training implementation is provided in CAFFE. For inference of the trained networks, a custom standalone C++ code is available. The inference code has minimal dependencies, is well optimized, and supports wide range of network architectures.

Keywords

XNOR nets, convolutional networks, neural networks, object detection, image classification

Published
2017
Pages
22
Publisher
Fingera s.r.o.
Place
Brno
BibTeX 
@misc{BUT144771,
  author="Michal {Hradiš} and Jan {Kohút}",
  title="XNOR net report",
  year="2017",
  pages="22",
  publisher="Fingera s.r.o.",
  address="Brno",
  url="https://www.fit.vut.cz/research/publication/11618/",
  note="Summary research report"
}
Files
Projects
Caffe XNOR-nets, Innovatrics, start: 2017-03-01, end: 2017-06-30, completed
Research groups
Computer Graphics Research Group (RG GRAPH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top