Giter Site home page Giter Site logo

sleep-staging's Introduction

Description

This repository represents the sleep staging classification work done using neural networks at Stanford University, and is intended primarily for research and historical reference.

Those interested in using the sleep staging classification methods that were developed from this should use the primary, Stanford-STAGES repository.

Branches

Git provides support for multiple branches of development. Notable branches for this repository include:

  1. Master (default)

    The master branch.

  2. Historical

    The historical branch contains some of the initial sleep staging classification work down using neural networks at Stanford University, and is intended primarily for research and historical reference.

  3. Dev

    The dev branch is the development branch for updating and testing changes to the master branch and is not always stable.

    NOTE: Only Python 3.6 and later is supported. Previous versions of Python have been shown to yield erroneous results.

Instructions

sc_train.py is run by adding an option with the following format:

Example:

python sc_train.py --model ac_lh_ls_lstm

The ac specifies the CC model configuration, the lh specifies the complexity - high in this case, the ls specifies the window length - 15 seconds in this case, and lstm specifies that the model has memory.

To train a model, the sc_config.py should be changed to match the destination for training files, and similarly, to test a model (which has the same option as training) the destination for testing files should be changed.

sleep-staging's People

Contributors

informaton avatar jensstephansen avatar

Stargazers

Emran Ali avatar Mohit Bagaria avatar luca avatar Leo Ota avatar Benjamin Yetton avatar Stanislas Chambon avatar

Watchers

James Cloos avatar  avatar  avatar Alexander Neergaard Zahid avatar Leo Ota avatar Zhiyong Zhang avatar

Forkers

slasnista leoota

sleep-staging's Issues

data preprocessing and features extraction

Hello,

Thank you for sharing your code, I look forward playing with it !

Yet I would like to know: do you plan to release the code to preprocess the data and to extract the features you feed the neural nets with ? You have described a very interesting pipeline in your paper and I would like to investigate it in details.

Thank you in advance.

can't find environment.yaml

Dear all,
I'm trying to play with your code but I can't find the environment.yaml file you mentioned in the first paragraph of your readme (dev branch).
Could you please indicate me where to find it?
BR,
Marco
[email protected]

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.