The material in this page is meant for 3-4 sessions. You should be content if you do one exercise in a day; some may be able to complete two in a day.

• Briefing 10 November
• Briefing 11 November

Reading

• PyTorch Quickstart
• Learn the Basics
  • see also the tutorial under Exercise 1. below
• Szeliski 2022 Chapter 5

Exercise 1. Basic tutorial.

I have added a couple of exercises to the official PyTorch Quickstart.

• Download and open the (augmented) tutorial.
• Please reflect upon and discuss the questions.

Exercise 2. Convolutional Neural Networks

1. Complete the CIFAR-10 Tutorial
2. Compare the approach to Exercise 1. What is different? What is the same?

Exercise 3. Regression.

One in-house project is to classify images of remote galaxies, which are often distorted due to the gravity of dark matter. This effect is known as gravitational lensing.

A sample dataset can be found at github. This directory contains

• A data file, sphere-pm.csv
• 10000 images of distorted galaxies
• A python file Dataset.py defining a subclass of Dataset to manage these data

The CSV file has the form

index,filename,source,lens,chi,x,y,einsteinR,sigma,sigma2,theta,nterms
"00001",image-00001.png,s,p,50,30,40,19,31,0,0,16

The interesting columns are the filename which points to the input image, and the four output variables \(x\), \(y\), einsteinR, and \(\sigma\). The other columns are associated with more advanced problem instances and should be ignored.

1. Study the Dataset class Dataset.py. How is the dataset managed?
2. Use this class to test if you can train a network to determine the four outputs for an image.

Exercise 4. Own Data (Optional)

Making your own training data may be difficult, because of the large quantity of data that you need, but if you want to give it a try, I would recommend this.

1. Team up with everybody else who wants to do this problem.
2. Each team member makes a set of hand-drawn digits, at least ten versions of each digit each.
3. Digitise the digits into image files. Make sure that everybody uses the same resolution.
   • The resolution must be large enough to make digits recognisable, but small enough to save computational power.
   • Somewhere between \(28\times28\) (same as the MIST dataset) and \(64\times64\) may be considered.
4. Gather the images into a dataset with their labels (digit value). You may use Exercise 3 as an example.
5. Merge and share the dataset.
6. Train and test a neural network to read the digits.
7. Try different networks, at least the ones you have used in previous exercises.

Exercise 5. More examples (optional)

Other datases may be found at this collection if you want to try other variants.