EIR

EIR is a framework for supervised training of deep learning models on genotype, tabular, sequence, image and binary data. It is designed to provide a high-level, yet modular API that reduces the amount of boilerplate code and pre-processing required to train a model.

Installation

$ pip install eir-dl

Documentation

To get started, please read 01 – Genotype Tutorial: Ancestry Prediction.

• Using EIR
  • 01 – Genotype Tutorial: Ancestry Prediction
  • 02 – Tabular Tutorial: Nonlinear Poker Hands
  • 03 – Sequence Tutorial: Movie Reviews and Peptides
  • 04 – Established Architectures and Pretrained Models
  • 05 – Image Tutorial: Hot Dog or Not?
  • 06 – Training on binary data
• Customizing EIR
  • 01 – Customizing EIR: Customized Fusion Tutorial
• API
  • Global Configurations
  • Input Configurations
  • Feature Extractor Configurations
  • Fusion Configurations
  • Output Configurations
• License
• Acknowledgements