About XNOR-Net ImageNet Classification

XNOR-Net ImageNet Classification Diagram

We propose two efficient variations of convolutional neural networks. BinaryWeight-Networks, when the weight filters contains binary values. XNOR-Networks, when both weigh and input have binary values. These networks are very efficient in terms of memory and computation, while being very accurate in natural image classification. This offers the possibility of using accurate vision techniques in portable devices with limited resources.


XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, and Ali Farhadi ECCV  2016

Source Code in Torch

You can download the source code and the pre-trained models for AlexNet below: