sharatkatz / mcfly-tutorial Goto Github PK

This repository contains notebooks that show how to use the mcfly software. Mcfly is deep learning tool for time series classification..

Currently we here offer two tutorials. Our main tutorial can be found in the notebook notebooks/tutorial/tutorial.ipynb. This tutorial will let you train deep learning models with mcfly on the PAMAP2 dataset for activity recognition.

A comparable, slightly quicker tutorial can be found in the notebook notebooks/tutorial/tutorial_quick.ipynb. This tutorial will let you train deep learning models with mcfly on the RacketSports dataset for activity recognition.

Prerequisites:

• Python 3.6, 3.7 or 3.8
• Have the following python packages installed:
  • mcfly
  • jupyter
  • pandas
  • matplotlib

Mcfly can be installed through pypi:

pip install mcfly

See https://github.com/NLeSC/mcfly for alternative installation instructions

The tutorials are provided in Jupyter notebooks, which can be found in the folder notebooks. To use a notebook, first install Jupyter:

pip install jupyter

For more documentation on Jupyter: See the official documentation

Windows users can best use Anaconda 3.6.

• Create a new environment (Environments > Create…)
• Click the play button next to your environment and select ‘Open terminal’
• Type conda install numpy scipy jupyter and then pip install mcfly
• Click the play button again and select ‘open with Jupyter notebook’
• Navigate to the directory where you cloned this repository, where you can open the notebooks

The tutorials can be run using Jupyter. From the tutorial root folder run:

jupyter notebook

There are two versions of the tutorial. The standard tutorial is for self-learning. There is also a version for workshops which is only expected to be used with the aid of an instructor.