pytorch-retinanet
pytorch-retinanet copied to clipboard
loss.py的输入中,loc_preds和loc_targets的anchor数量要一样吗?
出现一个bug:The expanded size of the tensor (120087) must match the existing size (20) at non-singleton dimension 1,请问输入的loc_preds和loc_targets中,anchors数量要一样吗?