SensatUrban数据集（RandLA-Net）——问题记录（win10）

SensatUrban数据集（RandLA-Net）——问题记录（win10）

1.环境

open3d-python用最新的

2.编译

用 git Bash编译，要切换环境，否则在base下生成的是3.9的，具体方法可以看这里git切换conda环境

3.坑

在tool.py中

import nearest_neighbors.lib.python.nearest_neighbors as nearest_neighbors

这就是个坑，哎，正确的是

import utils.nearest_neighbors.lib.python.KNN_NanoFLANN.nearest_neighbors as nearest_neighbors

cpp_subsampling.cpmpute在哪？？？

    def grid_sub_sampling(points, features=None, labels=None, grid_size=0.1, verbose=0):
        """
        CPP wrapper for a grid sub_sampling (method = barycenter for points and features
        :param points: (N, 3) matrix of input points
        :param features: optional (N, d) matrix of features (floating number)
        :param labels: optional (N,) matrix of integer labels
        :param grid_size: parameter defining the size of grid voxels
        :param verbose: 1 to display
        :return: sub_sampled points, with features and/or labels depending of the input
        """

        if (features is None) and (labels is None):
            return cpp_subsampling.compute(points, sampleDl=grid_size, verbose=verbose)
        elif labels is None:
            return cpp_subsampling.compute(points, features=features, sampleDl=grid_size, verbose=verbose)
        elif features is None:
            return cpp_subsampling.compute(points, classes=labels, sampleDl=grid_size, verbose=verbose)
        else:
            return cpp_subsampling.compute(points, features=features, classes=labels, sampleDl=grid_size,
                                           verbose=verbose)

今天先记到这，待更。。。

AttributeError: module ‘tensorflow’ has no attribute ‘py_func’

tf.py_func 改成 tf.compat.v1.py_func

iter = tf.data.Iterator.from_structure(train_ds.output_types, train_ds.output_shapes)改成

iter = tf.compat.v1.data.Iterator.from_structure(tf.compat.v1.data.get_output_types(train_dataset),tf.compat.v1.data.get_output_shapes(train_dataset))