EIR
EIR
is a framework for
supervised modelling,
sequence generation and
array generation
on genotype, tabular, sequence, image, array, and binary input 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.
Warning
This project is in alpha phase. Expect backwards incompatible changes and API changes.
Installation
Installing EIR via pip
$ pip install eir-dl
Important
The latest version of EIR supports Python 3.11. Using an older version of Python will install an outdated version of EIR, which is likely to be incompatible with the current documentation and may contain bugs. Please make sure that you are installing EIR in a Python 3.11 environment.
Installing EIR via Container Engine
Here’s an example with Docker:
$ docker build -t eir:latest https://raw.githubusercontent.com/arnor-sigurdsson/EIR/master/Dockerfile
$ docker run -d --name eir_container eir:latest
$ docker exec -it eir_container bash
Documentation
To get started, please read 01 – Genotype Tutorial: Ancestry Prediction.
- Supervised Learning
- 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
- 07 – Multimodal Training: Combining Tabular, Text, and Image
- 08 – Training on arrays with CNN, LCL, and Transformer Models
- Sequence Generation
- Array Generation
- Pretraining
- Customizing EIR
- API
- License
- Acknowledgements