Negative Metric Report

[aymuos15]

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.005 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.019 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.002 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.005 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.018 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.004 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.026 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.057 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.058 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.057 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000

What does negative mean in terms of Precision and Recall?

Sorry if this is already mentioned in the code.

[sovit-123]

This is happening because pycocotools does not find bounding boxes which are large in the dataset. For pycocotools large bunding boxes means at least 96x96 pixel boxes.

[aymuos15]

So essentially then, the model is working. Just that the bounding box sizes are small so that metric is not going to show anything?

Am I right in saying this?

[sovit-123]

@aymuos15 Yes, if a dataset does not contain a specific bounding box shape, pycocotools will report -1 for that size.

[aymuos15]

Thanks a lot!