## Project Description

 - We’d like to build a high-performance deep learning model for image classification.
 - Using given train/validation set, train and evaluate your model to properly classify images.
 - All information needed for training and testing is provided on LearnUs






## Evaluation

The evaluation metric for this competition is F1-Score. The F1-score measures accuracy using precision and recall.

Precision is the ratio of true positives to all predicted positives. Recall is the ratio of true positives to all actual positives. The F1 score is given by:

![](https://lawtomated.com/wp-content/uploads/2019/10/F1-Score.png)

We use F1-score as it weights recall and precision equally, and a good model will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.





## Submission Format

Submission file consists of two columns: `filename` and `class`. 
The file should contain a header and have the following format:
```
filename,class
0.jpg,0
1.jpg,1
2.jpg,2
```