Open wangxiaobai2268 opened 4 years ago
Hi @wangxiaobai2268, You need the 3d label to train the network since our work is fully supervised. After training, the network will generate multiple hypotheses (depends on how many kernels you use during training) for each 2d input.
小姐姐你好! 如果我想拿2d数据输入,没有3d标注,会生成5个假设吗?