Closed ansabsheikh9 closed 6 years ago
how to handle when there is no object in scene while training, what should be the default regression values for reference?
if there is no object, there are no positive anchor proposals (iou > threshold) and no regression is done. only detection error is backpropagated.
Thank you for you reply.
how to handle when there is no object in scene while training, what should be the default regression values for reference?