The evaluation pages describe how submissions will be scored and how students should format their submissions. 

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 accuracy using the precision and recall of the statistics.

![img](https://miro.medium.com/max/875/1*OhEnS-T54Cz0YSTl_c3Dwg.jpeg)
![img](https://miro.medium.com/max/555/1*7J08ekAwupLBegeUI8muHA.png)

Precision is the ratio of true positives to all predicted positives. The recall is the ratio of true positives to all actual positives. 

The F1 score is given by:

![img](https://miro.medium.com/max/353/1*T6kVUKxG_Z4V5Fm1UXhEIw.png)

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
Each video present in the test folder must be mapped to a binary label (**0 for fake and 1 for real**). The submission will be in form of a csv file consisting of 2 columns which is shown below as a header.

The file should contain a header and have the following format:
```
id,label
```
The **id** column contains the video name for example, 0.mp4 and the **label** column contains the video's binary mapping/classification 0 or 1.