This workshop has been presented at the Data Week Online 2020 organised by the Jean Golding Insitute

The introductory deck of slides to this tutorial is available on my SpeakerDeck profile:

Deep Learning for the Health and Life Sciences with PyTorch.

The full abstract of the workshop is available here: Abstract

• Introduction to ML and DL for the Health and Life Science

  • Short introduction to PyTorch

• Reproducibility and Replicability

  • Replication Case study on Heart Failure

• BioImages

  • Diabetic Retinopathy from fundus images
  • Histopathological Images and Transfer Learning

• Few Notes on Model Interpretability

This tutorial runs on *Python 3* (Py3.4+ should be fine), and requires the following main packages:

• numpy
• scipy
• matplotlib
• scikit-learn
• torch (of course 😄)
• torchvision

The complete list of requirements is available in requirements.txt

Detailed (step-by-step) instructions to setup the Python virtual environment on your local machine are also available here.

If you don't want to bother setting up everything on your local computer (_and also have a pretty good internet connection) you might also consider the following two alternatives:

The material provided in this repository adopts two different licence files, for Lecture notes and Source Code, respectively.

The Lecture notes (and corresponding source notebooks) are licensed under
Creative Commons Attribution-ShareAlike 4.0 International License.

The samples and reference code within this repository is made available under the GNU GPL v3.

See the LICENSE file.

Author: Valerio Maggio, Senior Research Associate @ Dynamic Genetics Lab

Contacts
@leriomaggio
ValerioMaggio
[email protected]