Skip to content
Proyectos

allenai/XNOR-Net has 874 GitHub stars and 235 forks. GitHot measured 0 stars in 24 hours and 0 in 7 days. Last checked 2026-11-21 12:27 UTC. Last push 2017-12-05.

Cómo se miden estas cifras

Crecimiento de estrellas medido

in 24h
0
in 7 days
0
in 15 days
Recopilando historial
in 1 month
Recopilando historial

Cambios netos en períodos que se solapan, no totales diarios. Los datos no disponibles se dejan en blanco. Las estrellas indican interés, no calidad.

Acerca de

ImageNet classification using binary Convolutional Neural Networks

Aprendizaje automático

README.md

Original

XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks.

This is the Torch 7.0 implementation of XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks.

Citation

@inproceedings{rastegariECCV16,
    Author = {Mohammad Rastegari and Vicente Ordonez and Joseph Redmon and Ali Farhadi},
    Title = {XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks},
    Booktitle = {ECCV},
    Year = {2016}
}

Requirements

This software is implemented on top of the implementation of ImageNet-multiGPU and has all the same requirements.

Download the cache files from here and run:

tar -xvf ./cache.tar

Training Binary Weight Network

th main.lua -data [path to ImageNet dataset] -nGPU 1 -batchSize 128 -netType alexnet -binaryWeight -dropout 0.1

Training XNOR-Networks

th main.lua -data [path to ImageNet dataset] -nGPU 4 -batchSize 800 -netType alexnetxnor -binaryWeight -optimType adam -epochSize 1500

Trained Models

To use the trained models use the option -retrain [path to the trained model file] and -testOnly

Binary-Weight-Network(BWN)

XNOR-Network

If you use the same image pre-processing as here by

find . -name "*.JPEG" | xargs -I {} convert {} -resize "256^>" {}

then the accuracies for top-1 should be:

alexnet_BWN %56.8

alexnet_XNOR %43.3

License

By downloading this software you acknowledged that you agreed on the terms and conditions in the SOFTWARE-LICENSE-AGREEMENT.lic

Explorar proyectos relacionados

Cargando…