Project Details

Caffe XNOR-nets

Project Period: 1. 3. 2017 – 30. 6. 2017

Project Type: contract

Partner: Innovatrics, s.r.o.

English title
Caffe XNOR-nets
Type
contract
Keywords

convolutional networks, CNN,  NXOR-nets

Abstract

Evaluation of NXOR-nets and opensource tools for training of these
networks.NXOR-nets are defined in Rastegari et al.: XNOR-Net: ImageNet
Classification Using Binary Convolutional Neural Networks.The evaluated
propertties of NXOR-nets are the degradation of classification accuracy due to
transformation to binary networks and the possibilities of compensating this
degradation by enlarging the network.Further, the project will result in free
open source implementations of layers needed to train NXOR-nets in caffe
framework using GPU.

Team members
Hradiš Michal, Ing., Ph.D. (DCGM) – research leader
Publications

2017

  • HRADIŠ, M.; KOHÚT, J. XNOR net report. Brno: Fingera s.r.o., 2017. Detail
Back to top