The topic for the lab is deep learning. The goal of the lab is
- to learn how to build and train a neural network,
- to learn how to improve the neural network model and its training, and
- to get a glimpse of a state-of-the-art software library (PyTorch) for deep learning.
We will look at two applications with image classification, namely
- classification of hand-written digits by training and using a neural network, and
- classification of real world images using a pre-trained deep neural network.
The lab is scheduled for 4 hours and done in the mini-project groups. There are different sessions scheduled, each group should attend one of these. The lab is mandatory and examination will be done during these 4 hours, no report needs to be written.
This year the supervision and grading of the lab will be done via Zoom (we use the same meeting room as for all other teaching activities in this course: https://uu-se.zoom.us/j/65671957631). If you prefer, you can do the lab before the lab session and only attend the session to be graded.
Solutions to the preparatory exercises must be handed in before the lab session.
All instructions are in this file: instructions.pdf
Please read them carefully!
You can either choose to do the lab in your web browser via Google Colab or locally on your computer. If you choose the last option, make sure to have all software (notably PyTorch) installed before the lab session (see the instructions for details).
Every group has to submit the solutions to the preparatory exercises before the lab sessions.
Use this document for queuing for help during the lab.
The deadlines for the lab are as follows:
|Submissions of solutions to preparatory exercises
(submission deadlines are one minute before midnight, i.e., 23.59)
Every group has to register for exactly one of the following three lab sessions in the course calendar:
- Thursday, 10th December, 8:15-12:00
- Friday, 11th December, 8:15-12:00
- Monday, 14th December, 13:15-17:00
You can find the slots via the "Find appointment" button.
If you have any questions regarding the lab, primarily use the Discussion forum - Laboratory work.