## Evaluation Metric
The evaluation metric for this competition is **Average Precision** at IoU thresholds of 0.5(AP@0.5) and 0.75(AP@0.75). We provide an authoritative [tool](https://github.com/rafaelpadilla/Object-Detection-Metrics) for AP calculation. You can download the file ``evaluate.zip`` in the 'data' column to get the tool.
### How to use the evaluation tool?
- Step1: Download and unzip the ``evaluate.zip`` file. 
- Step2: For each test image, output a list of bounding boxes ``classlabel confidencescore xmin ymin width height`` for objects, and save them as a ``.txt`` file. For example:

``190001.txt``:
```
person .98 1000 300 120 260
person .89 1200 300 80 220
```
``190002.txt``:
```
person .95 260 570 120 300
```
- Step3: Put your predicted ``.txt`` files in the folder ``evaluate/detections``.
- Step4: Run the python script ``pascalvoc.py`` and you will get the AP value of your predicted results.
```
python pascalvoc.py --threshold 0.5
```
```
python pascalvoc.py --threshold 0.75
```

## Submission Format
Your score will be obtained by calculating the Mean Absolute Error between your AP values and 1.
The submission file should contain a header and have the following format:
```
ID,value
AP@0.5,0.871
AP@0.75,0.455

```