## How is testing done
The AG-ReID2023 competition evaluates submissions by computing mean Average Precision (mAP) at Rank-1. Participants' algorithms are tested on 8,499 pictures depicting 808 people who were not included in the training sample. For each picture in the test sample (query), the rest of the test dataset must be ranked, and the top result selected (the query itself should not be included in the output). For further information on submission requirements, refer to the `sample_submission.csv` file and the Dataset Description [here](https://www.kaggle.com/competitions/ag-reid2023/data). 

Baseline code guide can be found  [here](https://github.com/agreid23/AG-ReID).

## Metrics
This competition employs mean average precision with k=1 as the metric. For each query, the average precision is calculated on the first result, then averaged across all queries. More information on the metric can be found [here](https://towardsdatascience.com/breaking-down-mean-average-precision-map-ae462f623a52).

## Submission File
Participants must provide a submission file containing the top-1 matching image from the `bounding_box_test` folder for each image in the test set. Each match is described using the following format:

>image_id, person_id
ImageID, ImageID[13 chars]

## Note
>**IMPORTANT**: The person_id in the query set is marked and hidden from participants, which means that participants will not know the identity of the person in the query set. As a result, participants will not know whether their algorithm has correctly identified the target person at rank 1 until they submit their results and receive the evaluation feedback.