Commit d8bf7722 authored by Oliver Kirsebom's avatar Oliver Kirsebom
Browse files

improved readme

parent f4ed8005
# Hands-on Tutorial
# NARW Tutorial
This 90-minute hands-on tutorial formed part the workshop [Detection and Classification in Marine Bioacoustics with Deep Learning](https://www.eventbrite.ca/e/detection-and-classification-in-marine-bioacoustics-with-deep-learning-tickets-72329209613), organized jointly by MERIDIAN and ONC in Victoria BC on 21-22 November 2019.
Welcome to the North Atlantic right whale (NARW) tutorial, where we use the [Ketos package](https://docs.meridian.cs.dal.ca/ketos/) to train a Deep Neural Network to recognize the characteristic NARW `upcall'.
## What will I learn in this tutorial?
This 90-minute hands-on tutorial was run at the workshop [Detection and Classification in Marine Bioacoustics with Deep Learning](https://www.eventbrite.ca/e/detection-and-classification-in-marine-bioacoustics-with-deep-learning-tickets-72329209613), organized jointly by MERIDIAN and ONC in Victoria BC on 21-22 November 2019.
## Who is this tutorial for?
Aim for programming-proficient people:
We have created the tutorial with two recipients in mind, *practitioners* and *developers*. The typical practitioner would be a marine bioacousticians who uses detection and classification (DC) systems to analyze hydrophone data, but has little or no experience with machine learning. The typical developer, on the other hand, would be a machine-learning expert who developes DC systems for use in marine biouacoustics.
Moreover, we expect you to have some previous programming experience, preferably in Python, which is the programming language used in the tutorial. You do not need to be an expert programmer, but familiarity with basic programming concepts such as functions, loops, if statements, etc. would be an advantage.
Group 1:
Someone who is able to program and wants to apply deep-learning tools to underwater acoustics data, say, train a CNN to detect certain calls
## What will I learn in this tutorial?
Group 2:
Deep-Learning developer who is creating and training his/her own models. For this group of people Ketos provides a means to share their tools with users (from Group 1).
We have divided the tutorial in two parts. In the first part, you will learn how to load a pre-trained deep learning model, which has been trained to recognize NARW upcalls, and you will learn how to run the model on a audio file. In the second part, you will learn how create a training dataset and train such a deep learning model yourself!
We hope the tutorial will be of interest to both practitioners and developers, demonstrating how the gap between the two groups can be bridged through the use of toolkits such as Ketos.
## Prerequisites
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment