Detail výsledku s přesahem do praxe

XNOR net report

HRADIŠ, M.; KOHÚT, J.

Originální název

XNOR net report

Anglický název

XNOR net report

Druh

Souhrnná výzkumná zpráva

Originální abstrakt

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.

Anglický abstrakt

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.

Klíčová slova

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

Klíčová slova v angličtině

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

Autoři

HRADIŠ, M.; KOHÚT, J.

Rok RIV

2018

Vydáno

15.06.2017

Nakladatel

Fingera s.r.o.

Místo

Brno

Strany počet

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"
}

Dokumenty

Souhrnná technická zpráva