After having your ideal result, please save your result in `result_img1` and `result_img2` in the cell below.

We have defined the label for each class in each image. Make sure you use the same settings as us and feel free to use the provided swapping label code to swap labels if needed.

 - for `img1.png`, use k=3, background labels as 0, rectangle labels as 1 and triangle labels as 2
 - for `img2.png`, use k=2, background labels as 0, building labels as 1

After your `result_img1` and `result_img2` are ready, run the cell below to create a `submission.csv`. Please download it from this notebook and submit it in our [Kaggle](https://www.kaggle.com/t/107607dc5f7da97fdfa41d5870ec8bb2) competition.

Please remember to note your Kaggle competition nickname in this notebook. We will use your ranking to grade.

You have 10 submission quota each day to submit your result and get your multi-class classification accuracy and ranking.