All the training images are uploaded in the train folder with prefix Image and the respective class labels have been mapped in train_label.csv. In train_label.csv, we have normalized the target classes to 0-6(7 classes in total).
You'll be predicting the class of each image in the test folder and submitting the data in the csv format shown in sample_submission.csv.

## Files

*   **train.csv** - the training set
*   **sample_submission.csv** - a sample submission file in the correct format

## Columns

*   `file_name` - Name of the image
*   `label` - Real class label of the image.