Giter Club home page Giter Club logo

cgm-ml's Introduction

codecov Python package Supported Python Versions Binder CodeFactor

Child Growth Monitor Machine Learning

Child Growth Monitor (CGM) is a game-changing app to detect malnutrition. If you have questions about the project, reach out to [email protected].

This is the Machine Learnine repository associated with the CGM project.

Introduction

This project uses machine learning to identify malnutrition from 3D scans of children under 5 years of age. This one-minute video explains.

Getting started

Requirements

You will need:

  • Python 3.7
  • TensorFlow version 2
  • other libraries

To install, run:

pip install -r requirements.txt

We use Microsoft Azure ML to manage our datasets, experiments, and models internally. You can also run most of the code without AzureML though.

Dataset access

Data access is provided on as-needed basis following signature of the Welthungerhilfe Data Privacy & Commitment to Maintain Data Secrecy Agreement. If you need data access (e.g. to train your machine learning models), please contact Markus Matiaschek for details.

If you have access to scan data, you can use: cgmml/data_utils to understand and visualize the data.

Repository structure

The source code is in cgmml/.

Due to AzureML, all code for a single experiment run needs to reside in one directory. Example: All code for one specific training, e.g. a ResNet training, needs to be in this training directory.

However, many of our trainings (and also evaluation runs) share large portions of code. In order to reduce code duplication, we copy shared(a.k.a. common) utility code with copy_dir() from cgmml/common/ into the training/evaluation directory. This way, during the experiment run, the code is in the directory and can be used during the run.

Run linting / tests

# Make sure to be in the root dir of this repository
flake8 cgmml/
pytest

Release cgm-ml-common

Common functionalities of this repo are released on pypi: https://pypi.org/project/cgm-ml-common/

To release a new version of cgm-ml-common:

  • Configure the version you wish to release in setup.py
  • Publish the release using the pipeline .github/workflows/pypi-release.yml

Contributing

Please see CONTRIBUTING.md for details.

Versioning

Our releases use semantic versioning. You can find a chronologically ordered list of notable changes in CHANGELOG.md.

License

This project is licensed under the GNU General Public License v3.0. See LICENSE for details and refer to NOTICE for additional licensing notes and use of third-party components.

cgm-ml's People

Contributors

ai-guru avatar anubhav-bhargava avatar ashish-bagri avatar bulrich avatar chrispfiohm avatar christianpfitzner avatar dependabot[bot] avatar gangooteli avatar jasminziegler avatar lvonasek avatar markus-hinsche avatar mmatiaschek avatar padronlv avatar prajurock avatar pranavashok avatar prashant905 avatar prithviraj-maurya avatar shanky0009 avatar whyshreddy avatar xmartin avatar

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.