# Jupyter Notebooks

The Jupyter Notebook implements a minimal subset of *bonito* functionality to enable the training of a Quartznet neural network basecaller within a [Google Colaboratory](https://colab.research.google.com/notebooks/welcome.ipynb) session.

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1m-M6cmjsl2LRk9In3tzomqEwXMDUCZHF)

A subset of the data provided with *bonito* (100,000 signal chunks) is accessible within the session. A full model can be trained (exploiting a GPU), and parameters including the data volume and training hyperparameters can be adjusted to see their effect.