All files except for the `test.npy` can be found at the repo ([https://github.com/iphysresearch/GWData-Bootcamp/tree/main/2023/deep_learning/baseline](https://github.com/iphysresearch/GWData-Bootcamp/tree/main/2023/deep_learning/baseline))

## Files

*   **data_prep_bbh.py** - script for data generation (credit: [Dr. Hunter Gabbard](https://github.com/hagabbar/cnn_matchfiltering/))
*   **utils.py** - supplemental script containing some useful functions
*   **main.py** - main script for training/evaluation/submission
*   **test.npy** - test data for submission (300MB)

You can use the test data in the Kaggle notebook as follows

```python
import numpy as np
test_dataset = np.load('/kaggle/input/2023-gwdata-bootcamp/test.npy')
```

## Hints

Some useful information about `test.npy` dataset

- SNR: 2 4 5 6 7 8 9 10 15 20 25 30
- num of injections: ~600 of 1200 samples
- `astro_metric`
- positive vs negative ~ 1:1

---

Anyway, just check the top notebook for everything!