Arvutiteaduse instituut
  1. Kursused
  2. 2023/24 kevad
  3. Sügavõpe masinnägemises (LTAT.02.028)
EN
Logi sisse

Sügavõpe masinnägemises 2023/24 kevad

  • Main
  • Classes
  • Homeworks
  • Projects
  • Grades
  • Links

Homework submission

Please review the following rules before submitting your assignment:

  1. Please, submit only .ipynb that you extract from the Colaboratory.
  2. Run your homework exercises before submitting (output should be present, preferably restart the kernel and press run all the cells).
  3. Do not change the description of tasks in red (even if there is a typo|mistake|etc).
  4. Please, make sure to avoid unnecessary long printouts.
  5. Each task should be solved right under the question of the task and not elsewhere.
  6. Solutions to both regular and bonus exercises should be submitted in one IPYNB file.

Note: The late days will be used automatically if you submit after the deadline unless you let us know in advance.

The following is the schedule for homeworks

This schedule can change (check Slack for the updates):

Homework #Assignment dateDeadline (23:59)
HW01February 21March 10
HW02March 13March 31
HW03April 3April 21

HW1 - CNNs in depth (Deadline: 10.03.2024)

the submission has been closed

Project: dataset (Deadline: 24.03.2024)

The task description is here: https://courses.cs.ut.ee/2024/DL4CV/spring/Main/Projects. Please, below submit your 2-page report describing the dataset you have created, motivation, sources, preprocessing techniques, labeling methods, and any challenges faced. Please highlight very clearly if the dataset is new or a modification of the existing dataset. If it is a modification, how was it modified? If it is a new dataset, how was it collected and labeled? Describe train and test splits. Add examples of images and labels to your report. Provide relevant summary statistics.

the submission has been closed

HW2 - Hands-on object detection and segmentation (Deadline: 31.03.2024)

the submission has been closed

HW3 - Vision Transformers (Deadline: 21.04.2024)

the submission has been closed

Project: Participation in Kaggle competitions (Deadline: 12.05.2024)

the submission has been closed

  • Arvutiteaduse instituut
  • Loodus- ja täppisteaduste valdkond
  • Tartu Ülikool
Tehniliste probleemide või küsimuste korral kirjuta:

Kursuse sisu ja korralduslike küsimustega pöörduge kursuse korraldajate poole.
Õppematerjalide varalised autoriõigused kuuluvad Tartu Ülikoolile. Õppematerjalide kasutamine on lubatud autoriõiguse seaduses ettenähtud teose vaba kasutamise eesmärkidel ja tingimustel. Õppematerjalide kasutamisel on kasutaja kohustatud viitama õppematerjalide autorile.
Õppematerjalide kasutamine muudel eesmärkidel on lubatud ainult Tartu Ülikooli eelneval kirjalikul nõusolekul.
Courses’i keskkonna kasutustingimused