Coder Social home page Coder Social logo

models's Introduction

Kipoi models

CircleCI

This repository hosts predictive models for genomics and serves as a model source for Kipoi. Each folder containing the following files is considered to be a single model:

├── dataloader.py     # implements the dataloader
├── dataloader.yaml   # describes the dataloader
├── dataloader_files/      #/ files required by the dataloader
│   └── ...
├── model.yaml        # describes the model
├── model_files/           #/ files required by the model (like weights.h5 and arch.json)
│   └── ...
└── example_files/         #/ small example files used to test the model
    └── ...

Folders named *_files are tracked by Git Large File Storage (LFS). New models are added by simply submitting a pull-request to https://github.com/kipoi/models.

Contributing models

1. Install Kipoi

  1. Install git-lfs
  2. Install kipoi
    • pip install kipoi
  3. Run kipoi ls (this will checkout the kipoi/models repo to ~/.kipoi/models)

2. Add the model

  1. cd ~/.kipoi/models
  2. Write the model: Create a new folder <my new model> containing all the required files
    • Option 1: Copy the existing model: cp -R <existing model> <my new model> & edit the copied files
    • Option 2: Run kipoi init, answer the questions & edit the created files
    • Option 3: mkdir <my new model> & write all the files from scratch
  3. Test the model
    • Step 1: kipoi test ~/.kipoi/models/my_new_model
    • Step 2: kipoi test-source kipoi --all -k my_new_model
  4. Commit your changes
    • cd ~/.kipoi/models && git commit -m "Added <my new model>"

3. Submit the pull-request

  1. Fork the https://github.com/kipoi/models repo on github (click on the Fork button)
  2. Add your fork as a git remote to ~/.kipoi/models
    • cd ~/.kipoi/models && git remote add fork https://github.com/<username>/models.git
  3. Push to your fork
    • git push fork master
  4. Submit a pull-request (click the New pull request button on your github fork - https://github.com/<username>/models>)

See docs/contributing getting started and docs/tutorials/contributing/models for more information.

Using models (to predict, score variants, build new models)

To explore available models, visit http://kipoi.org/models. See kipoi/README.md and docs/using getting started for more information on how to programatically access the models from this repository using CLI, python or R.

Configuring local storage location

This model source (https://github.com/kipoi/models) is included in the Kipoi config file (~/.kipoi/config.yaml) by default:

# ~/.kipoi/config.yaml
model_sources:
    kipoi:
        type: git-lfs
        remote_url: [email protected]:kipoi/models.git
        local_path: ~/.kipoi/models/

If you wish to keep the models stored elsewhere, edit the local_path accordingly.

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.