# Can you find the GW signals? — Data

来源：https://www.kaggle.com/competitions/can-you-find-the-gw-signals/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

All files except for the `test.npy` can be found at the repo ([https://github.com/iphysresearch/2023gwml4tianqin](https://github.com/iphysresearch/2023gwml4tianqin))

## 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

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

```python
import numpy as np
test_dataset = np.load('/kaggle/input/can-you-find-the-gw-signals/test.npy')
```

## Hints

Some useful information about `test.npy` dataset

- SNR: 2,4,5,6,7,8,9,10
- num of injections: 800
- `astro_metric`

---

Anyway, just check the top notebook for everything!