Wrote https://arxiv.org/abs/2207.12120 but never published. I think the "metric definition" is a pretty nice explanation of how it works. Process is the same between bounding boxes & segmentation maps aside from the IoU computation.
puppet_pals
joined 1 year ago
Looks good. You probably want something like:
tf.cond(categ==0, dense0(inputs), dense1(inputs))