Mapcalc for images with no bbox_gt

[pidoux7]

Hi Klimaschkas,

I'm currently working on a detection project that uses only one class. Some images are positive for this class and others are not. Is it possible to have an image with a ground_truth box empty if there is no class to detect?
for instance:
``

ground_truth = {

"boxes":
    [[60., 80., 66., 92.],
     [],
     [],
     [8., 34., 10., 36.]],

"labels":
    [1, 0, 0, 1]}

result_dict = {

"boxes":
    [[],
     [58., 94., 68., 95.],
     [],
     [10., 37., 17., 40.]],

"labels":
    [0, 1, 0, 1],

"scores":
    [0, 0.50 , 1, 0.9157755]}  

``
=> the first detection is a false negative, the second a false positive , the third a true negative and the last one a true positive.

if it is possible to do that, is it the right way to do it ?

thank you for your work !