The data consists of images of block structures.  Some of these structures are stable; while, others are unstable.  You must create a binary classifier that determines if a building is stable (1) or unstable (0).
![](https://data.heatonresearch.com/images/wustl/kaggle/2020-fall/2.png)
Not all images are it as well as others.  For example, the following image might be much more difficult due to lighting.
![](https://data.heatonresearch.com/images/wustl/kaggle/2020-fall/108.png)
Not all buildings will be of the same structure; consider the following image.
![](https://data.heatonresearch.com/images/wustl/kaggle/2020-fall/314.png)
The following blocks are used to create the buildings that you are predicting.  All blocks have different colors except for the two yellow blocks.  These are the only blocks that you will see in this data set. The colors define the shape of the blocks. 
 All blocks of the same type will always be the same size.
![](https://data.heatonresearch.com/images/wustl/kaggle/2020-fall/all-blocks.png)
This overhead view shows the relative sizes of the blocks.
![](https://data.heatonresearch.com/images/wustl/kaggle/2020-fall/block_sizes.png)
File descriptions
train.csv
- the training set
test.csv
- the test set
sampleSubmission.csv
- a sample submission file in the correct format
Data fields
id
- A unique ID for each image. This ID corresponds to the filename of each image.  For example, ID of 1 would be 1.png
stable
- The label, 1 means a stable structure, 0 is unstable.