A question about the evaluation results！

[FightStone]

This is my evaluation result :

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.808
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.955
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.870
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.850
Average Recall (AR) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.961
Average Recall (AR) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.899
Average Precision (AP) @[ IoU=0.50:0.95 | area= easy | maxDets= 20 ] = -1.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.790
Average Precision (AP) @[ IoU=0.50:0.95 | area= hard | maxDets= 20 ] = -1.000

Why is there a -1 value? My prediction result format is the same as the prediction json format you provided. Looking forward for your response, thank you！

[Z1Wu]

I have the same problem, even when I run the demo.py provided by author.
It looks like when "area == easy | area == hard " the result will be strange.

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.660
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.842
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.715
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.727
Average Recall (AR) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.895
Average Recall (AR) @[ IoU=0.75 | area= all | maxDets= 20 ] = 0.775
Average Precision (AP) @[ IoU=0.50:0.95 | area= easy | maxDets= 20 ] = -1.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets= 20 ] = 0.411
Average Precision (AP) @[ IoU=0.50:0.95 | area= hard | maxDets= 20 ] = -1.000

[albertter]

same problem.

[lyrgwlr]

same problem, have you guys solved this? @albertter @Z1Wu @FightStone

[Aaron20127]

evaluation code has bug.

[XyK0907]

I have the same problem. Is there any solution?

[nikhilchh]

self.areaRngLbl = ['all', 'medium', 'large']

And the code tried to get evaluation result when area_range is easy, medium, hard.

It is supposed to fail.
But how come in their demo.py you get a valid numeric value and not -1.