Publication detail

XNOR net report

HRADIŠ, M. KOHÚT, J.

Original Title

XNOR net report

Type

summary research report - contract. research

Language

English

Original 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

Authors

HRADIŠ, M.; KOHÚT, J.

Released

15. 6. 2017

Publisher

Fingera s.r.o.

Location

Brno

Pages count

22

URL

https://www.fit.vut.cz/research/publication/11618/

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 - contract. research"
}