Obj.confidence is negative?

[AastaLLL]

Hi,

The negative confidence is from the group rectangles type of clustering method.
This method does not output the confidence values for the clustered boxes and hence all objects will have -0.1 conf at the pgie.

Please check this topic for the detail:

Confidence values from pgie like -0.1?

In deepstream 4.02 we had to patch the nvinfer library and use dbscan for bounding boxes to be able to get confidence values. We never really trusted them however as I would get a lot of false positives with the standard resnet10 with very high confidence values like .997. Now with deepstream 5.0 preview I expected the confidence intervals would work “out of the box”. They seem to but every second or third object detection has a confidence of -0.1. How can we have negative confidence values? …

Thanks.