Why can't train_l1_points and train_l2_points tensors be converted to numpy arrays in this code？I would be grateful if you could take time to answer me！！！
train_l1_xyz, train_l1_points = PointASNLSetAbstraction(train_l0_xyz, train_l0_points, npoint=512, nsample=32, mlp=[64, 64, 128], is_training=True, bn_decay=None, weight_decay=None, scope='layer1', as_neighbor=as_neighbor[0]) train_l2_xyz, train_l2_points = PointASNLSetAbstraction(train_l1_xyz, train_l1_points, npoint=128, nsample=64, mlp=[128, 128, 256], is_training=True, bn_decay=None, weight_decay=None, scope='layer2', as_neighbor=as_neighbor[1])
Why can't train_l1_points and train_l2_points tensors be converted to numpy arrays in this code？I would be grateful if you could take time to answer me！！！
train_l1_xyz, train_l1_points = PointASNLSetAbstraction(train_l0_xyz, train_l0_points, npoint=512, nsample=32, mlp=[64, 64, 128], is_training=True, bn_decay=None, weight_decay=None, scope='layer1', as_neighbor=as_neighbor[0]) train_l2_xyz, train_l2_points = PointASNLSetAbstraction(train_l1_xyz, train_l1_points, npoint=128, nsample=64, mlp=[128, 128, 256], is_training=True, bn_decay=None, weight_decay=None, scope='layer2', as_neighbor=as_neighbor[1])