Skip to main content

Library for Autoencoder-based Residual Deep Network

Project description

Library of Autoencoder-based Residual Deep Network (resautonet)

Build Status Build status

The python library of autoencoder based residual deep network (resautonet). Current version just supports the KERAS package of deep learning and will extend to the others in the future.

Major modules


  • resAutoencoder: major class to obtain a autoencoder-based residual deep network by setting the arguments. See the class and its member functions' help for details.
  • pmetrics: functions for regression metrics like rsquared and RMSE.


  • mulParPerAnalysis: major class for parallel performance analysis You can setup many configure parameters for each network (a duty) and then run them to the effects in a parallel way. See this class and its member functions' help for details.


  • data: function to access each of two datasets,
    sim': simulated dataset in the format of Pandas's Data Frame, 'pm2.5':string, the name for a real dataset of the 2015 PM2.5 and the relevant covariates for the Beijing-Tianjin-Tangshan area. It is sampled by the fraction of 0.8 from the the original dataset (stratified by the julian day). See this function's help for details.
  • simdata: function to simulate the test dataset,
    The simulated dataset generated according to the formula: y=x1+x2*np.sqrt(x3)+x4+np.power((x5/500),0.3)-x6+ np.sqrt(x7)+x8+noise See this function's help for details.


You can directly install it using the following command for the latest version: pip install resautonet -U
You can also clone the repository and then install:

git clone --recursive
cd package 
pip install ./ install 

With the file included in this example, the pip install command will invoke CMake and build the resautonet module as specified in CMakeLists.txt.

Note for installation and use

Compiler requirements

resautonet requires a C++11 compliant compiler to be available.

Runtime requirements

resautonet requires installation of Keras with support of Tensorflow or other backend system of deep learning (to support Keras). Also Pandas and Numpy should be installed.

Use case

The homepage of the github for the package, resautonet provides two specific examples for use of autoencoder based residual deep network:


The resautonet is provided under a MIT license that can be found in the LICENSE file. By using, distributing, or contributing to this project, you agree to the terms and conditions of this license.

Test call

import resautonet as r
#Load the sample dataset for PM2.5'pm2.5')


Welcome to contact Dr. Lianfa Li (Email:

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for resautonet, version 0.1.1
Filename, size File type Python version Upload date Hashes
Filename, size resautonet-0.1.1.tar.gz (2.6 MB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page