The metric used is the **mean average precision (mAP)**, which measures the accuracy of the model's predicted bounding boxes compared to the ground truth bounding boxes.


Submission File
For each image in the test set, you must predict a list of boxes describing objects in the image. Each box is described as
   ```python
   ImageID,PredictionString
   apple_77,apple 1 71 60 175 164;apple 1 12 22 105 111;apple 1 134 23 243 115
   apple_78,apple 1 10 8 344 336
   apple_79,apple 1 77 183 641 716
   apple_80,apple 1 155 105 453 436
   apple_81,apple 1 70 398 1388 1731
   apple_82,apple 1 65 122 365 404
```

the **PredictionString** written as 
```python
class_name confidence xmin ymin xmax ymax;class_name confidence xmin ymin xmax ymax ..... and so on.
```