资源分类
》 资源 》算法》RNN-Transducer(RNNT loss using CPP)

RNN-Transducer(RNNT loss using CPP)

2019-09-19 | |  55 |   0 |   0

mxnet-transducer

A fast parallel implementation of RNN Transducer (Graves 2013 joint network), on CPU for mxnet.

GPU version is now available for Graves2012 add network !

Compilation

First get mxnet and the code:

git clone --recursive https://github.com/apache/incubator-mxnet
git clone https://github.com/HawkAaron/mxnet-transducer

Copy all files into mxnet dir:

cp -r mxnet-transducer/rnnt* incubator-mxnet/src/operator/contrib/

Then follow the installation instructions of mxnet:

https://mxnet.incubator.apache.org/install/index.html

Reference


上一篇：Loss Surfaces

下一篇：SuperResolutionCNN

用户评价
全部评价

热门资源

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • 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 ...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

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