资源分类
》 资源 》算法》nips2015_vrnn

nips2015_vrnn

2020-02-05 | |  31 |   0 |   0

Variational Recurrent Neural Networks

This is an implementation of the paper "A Recurrent Latent Variable Model for Sequential Data". http://arxiv.org/abs/1506.02216

Dependencies

Most of the script files are written as pure Theano code, modules are implemented in a more general framework. You can find the code at http://github.com/jych/cle.

Notice

The original Blizzard dataset should be downloaded by each user due to the license.
http://www.synsig.org/index.php/Blizzard_Challenge_2013
The original wave files have been read by numpy and saved into '.npz' format. There is a function that reads the numpy formatted files and generate a hdf5 format file.


上一篇：tucker-tensorsketch

下一篇：tensorflow-vrnn

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...