Running problems of part segmentation

[chenMouRen1231]

When I run part segmentation, the program reports an error. def get_transform(point_cloud, is_training, bn_decay=None, K = 3): """ Transform Net, input is BxNx3 gray image Return: Transformation matrix of size 3xK """ batch_size = point_cloud.get_shape()[0].value num_point = point_cloud.get_shape()[1].value

Traceback (most recent call last): File "c:/Users/lenovo/Desktop/pointnet-master/part_seg/train.py", line 393, in train() File "c:/Users/lenovo/Desktop/pointnet-master/part_seg/train.py", line 127, in train labels_pred, seg_pred, end_points = model.get_model(pointclouds_ph, input_label_ph, \ File "c:\Users\lenovo\Desktop\pointnet-master\part_seg\pointnet_part_seg.py", line 82, in get_model transform = get_transform(point_cloud, is_training, bn_decay, K = 3) File "c:\Users\lenovo\Desktop\pointnet-master\part_seg\pointnet_part_seg.py", line 47, in get_transform batch_size = point_cloud.get_shape()[0].value AttributeError: 'int' object has no attribute 'value'

[tosa-no-onchan]

You should be better to check its value.

print('>>> point_cloud.get_shape()=',point_cloud.get_shape())

point_cloud.get_shape()= (16, 2048, 3)

Are there Integer value?