This shows you the differences between two versions of the page.
dsm:assignments:02 [2024/11/04 14:22] andrei.niculae1004 |
dsm:assignments:02 [2025/01/13 19:49] (current) andrei.niculae1004 |
||
---|---|---|---|
Line 1: | Line 1: | ||
====== Competition ====== | ====== Competition ====== | ||
+ | Competition baseline beaters, complete this[[https://forms.gle/LGYQFUZgMGScBhK9A|name form]]! | ||
+ | |||
The competition is hosted on Kaggle at [[https://www.kaggle.com/t/2d3d10cda52f4fadb43658af5fed9e3c|this link]]. | The competition is hosted on Kaggle at [[https://www.kaggle.com/t/2d3d10cda52f4fadb43658af5fed9e3c|this link]]. | ||
- | Each competitor will participate individually. Please login using your student mail (@stud.acs.upb.ro). | + | Each competitor will participate individually. Please login using your **student mail** (@stud.acs.upb.ro) and check this box. |
+ | |||
+ | {{:dsm:assignments:kaggle_mail_share.png?500|}} | ||
We provide a [[https://www.kaggle.com/code/andreiniculae/dsm-2024-starting-code|starter code]] which demonstrates how to read the data, train a network and make a submission. You are encouraged to start your work from this notebook. | We provide a [[https://www.kaggle.com/code/andreiniculae/dsm-2024-starting-code|starter code]] which demonstrates how to read the data, train a network and make a submission. You are encouraged to start your work from this notebook. | ||
+ | Beating the baseline on the private leaderboard will reward **1p**, top 3 on the private leaderboard will have their final exam grade equal to 10 (4p). | ||
===== Description ===== | ===== Description ===== | ||
Traditional image classification models heavily rely on accurately labeled data for training, but in real-world scenarios, acquiring large quantities of labeled images can be costly and time-consuming. | Traditional image classification models heavily rely on accurately labeled data for training, but in real-world scenarios, acquiring large quantities of labeled images can be costly and time-consuming. |