Your models will be evaluated based on classification accuracy. The competition allows you to make multiple submissions, enabling you to fine-tune your models and improve your performance throughout the competition. However, only the final submission will be marked at the end.

## Metric:

The primary evaluation metric for this competition is **classification accuracy**.

## Submission Format:

Participants are required to submit a CSV file that contains two columns:

**"image_name":** A unique identifier for each test image.
**"label":** The predicted label or identity associated with each test image.
The "label" should be a representation corresponding to the identity you predict for each image in the test dataset.

## Scoring:

The score on the leaderboard is calculated based on the accuracy of your model's predictions on the test dataset. The higher the accuracy of your model, the better your leaderboard score.

## Final Ranking:

The final competition rankings will be based on the scores from the leaderboard as well as your code / notebook submissions. These will be revealed at the end of the competition. You are encouraged to fine-tune your models, experiment with different architectures, and optimize your approaches to achieve the highest classification accuracy possible. Make sure your submissions adhere to the specified format to ensure accurate evaluation and ranking.

Best of Luck!