Use the following dataset https://www.kaggle.com/datasets/lakshaymiddha/crack-segmentation-dataset only the train directory is supposed to be used during the training.

## Files

*   **test/images** - the test set
*   **sample_submission.csv** - a sample submission file in the correct format


## Columns

*   `file` - filename
*   `crack` - class: 0 if crack, 1 if there is no crack