### Data analysis competition of the course "Acoustic Events Detection".

### Baseline: https://github.com/Tvicker/itmo-kaggle-inclass

You will get 'passed' grade when you beat the baseline.

Your solutions will be scored with average class-based [ F1-score ](https://en.wikipedia.org/wiki/F1_score).

Public Leaderboard contains 30% of all the data. This means that your score on public leaderboard fo not show the full picture and your solution will be rescored after competition ends.

Please, ensure to set the seed when you do any randomness in your notebook. These lines of code must help:

```
import random
import numpy as np

random.seed(42)
np.random.seed(42)
torch.manual_seed(42)
torch.cuda.manual_seed(42)
torch.backends.cudnn.deterministic = True
```