test.py outputs -1 for Average Precision and Average Recall metrics

[anhminh3105]

I ran the test.py prorgramme on the COCO test2017 dataset with the human_detections_text-dev2017.json renamed to human_detections.json. However, the output results of all the Average Precision and Average Recall metrics are -1. Here is the snapshot:

I am unsure whether the problem is due to the human_detections_text-dev2017.json is not the right file to use.

Could you please help? Thanks in advance.

[mks0601]

For the test set, COCO dataset does not provide groundtruth. You have to evaluate your result using CodaLab. Please read http://cocodataset.org/#guidelines

[anhminh3105]

Thanks for the guide.

I ran the test with COCO val2017 dataset and reproduced the exact same results as you got.

I will try to upload the test2017 dataset outputs to CodaLab to get the results next.

Thank you.