Skip to content
Projects

allenai/XNOR-Net has 874 GitHub stars and 235 forks. GitHot measured 0 stars in 24 hours and 0 in 7 days. Last checked 2026-11-22 22:40 UTC. Last push 2017-12-05.

How these counts are measured

Measured star growth

in 24h
0
in 7 days
0
in 15 days
Collecting history
in 1 month
Collecting history

Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.

About

ImageNet classification using binary Convolutional Neural Networks

Machine Learning

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

Explore related projects

Loading…