This page is located in archive. Go to the latest version of this course pages. Go the latest version of this page.

Labs and Seminars

Two types of labs (tutorials) will be proposed for the course (alternating):

  • practical labs in which students will implement selected methods discussed in the course and experiment with them,
  • theoretical labs in which students will discuss solutions of theoretical assignments (made available before the class).


Date Topic Teachers Assignment Notes
17.02.2022 Lab 1: Preparations, Double Descent AS rec 102 rec 103
24.02.2022 Seminar 1 (lecture 1) BF assignments rec 102 rec 103
03.03.2022 Lab 2: Backpropagation, Computational graph AS rec 102 rec 103
10.03.2022 Seminar 2 (lectures 2,3) BF assignments rec 103
17.03.2022 Lab 3: Pytorch, project pipeline, CNN, performance metrics AS rec 102 rec 103
24.03.2022 Seminar 3 (lectures 4,5) AS assignments rec 103
31.03.2022 Lab 4: Pre-trained CNN Fine-tuning with regularization, BN AS rec 102
07.04.2022 Seminar 4 (lectures 6,7) BF assignments rec 102
14.04.2022 Lab 5: CNN visualization & adversarial patterns BF rec 102
21.04.2022 Seminar 5 (lectures 8,9) AS assignments rec 102
28.04.2022 Lab 6: Metric learning AS rec 102
05.05.2022 Seminar 6 (lectures 10,11) AS assignments no record
12.05.2022 Lab 7: VAE BF rec 102
19.05.2022 Seminar 7 (lecture 12) BF assignments no record


The seminar assignments are published 1 week in advance before the seminar. You are expected to prepare for it at home. We discuss the problems and solutions in the class. You are not required to submit you solutions, but if you solved a problem you will be invited to present it in the class. Seminars are not scored by points but they are important for gaining technical understanding, which will be finally evaluated in the written exam.

Examples of problems with solutions: examples.pdf (to be updated)


The solutions of the practical labs have to be submitted using the upload system

  • Your task will be to program a solution of the assigned problems. You have to hand out your code and a report. The report has to contain only answers to the assignments (nothing else).
  • The programming language is Python/PyTorch.
  • The deadline for submitting your solutions will be 4 weeks after the date of assignment. This is a hard deadline.
  • Not submitting a lab is equivalent to getting 0 points. You need at least of 50% of total lab points to pass.

Submission Regulations

You may choose from the following submission variants:

  1. Report in pdf and Python source code
  2. Annotated Jupyter notebook with inline results and Python source code if applicable

Please do not submit data and any other redundant files. Sharing code that is not a required part of the assignment is permitted, for example additional visualization code or test cases for debugging.

courses/bev033dle/labs/start.txt · Last modified: 2022/05/25 11:28 by shekhole