## Metric 
The evaluation metric for this competition is [Mean F1-Score](https://en.wikipedia.org/wiki/F-score). The F1 score, commonly used in information retrieval, measures classification performance using the statistics precision (P) and recall (R).

The F1 score is not biased by class frequencies and is more suitable for the long-tailed class distributions observed in nature.

Precision is the ratio of true positives (TP) to all predicted positives (TP + FP). Recall is the ratio of true positives (TP) to all actual positives (TP + FN).

The F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favoured over extremely good performance on one and poor performance on the other.

## Submission Format

For each image in the test set, you must predict 1 class label. The CSV file have to contain a header and have the following format:
```
ObservationId,ClassId
3305985310,307
3305985311,597
3305985312,1060
3305985315,860
3305985316,200
```

The *ObservationId* column corresponds to the observation ID. 
The *ClassId* column corresponds to one category id.

**For out-of-the-scope classes use -1 as ClassId.**

You should have one row for each test observation.