资源分类
》 资源 》算法》BinaryNet-on-tensorflow

BinaryNet-on-tensorflow

2020-02-04 | |  48 |   0 |   0

BinaryNet-on-tensorflow

binary weight neural network implementation on tensorflow

This is an implementation code for reproducing BNN

How to run

python mnist.py
python cifar10.py

Accuracy

DataSetaccuracy
MNIST99.04%
Cifar1086.18%

Different between paper

layer-wise learning rate, paper is layer_lr = 1./sqrt(1.5 / (num_inputs + num_units)), my implement is layer_lr / 4

Ref

[BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1"](http://arxiv.org/abs/1602.02830),
Matthieu Courbariaux, Yoshua Bengio

and An implemtation of binaryNet for Keras


上一篇：BinaryNet_and_XNORNet

下一篇：Accurate-Binary-Convolution-Network

用户评价
全部评价

热门资源

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...