Write PLY data to a writeable file-like object or filename.

Return the numpy dtype of the in-memory representation of the data. (If there are no list properties, and the PLY format is

Helper to create a Variable stored on CPU memory. Args: name: name of the variable shape: list of ints initializer: initializer for Vari

Helper to create an initialized Variable with weight decay. Note that the Variable is initialized with a truncated normal distribution. A weight

Batch normalization on convolutional maps and beyond... Ref.: http://stackoverflow.com/questions/33949786/how-could-i-use-batch-normalization-in-te

Return the numpy dtype description for this property (as a tuple of strings).

Return the pair (len_dtype, val_dtype) (both numpy-friendly strings).

Render point cloud to image with alpha channel. Input: points: Nx3 numpy array (+y is up direction) Output: g

ConvNet baseline, input is BxNx3 gray image

Read PLY data from a readable file-like object or filename.

elements: sequence of PlyElement instances. text: whether the resulting PLY file will be text (True) or binary (False).

Batch normalization on 2D convolutional maps. Args: inputs: Tensor, 4D BHWC input maps is_training: boolean tf.Varialbe, true i

Construct a PlyElement from an array's metadata. len_types and val_types can be given as mappings from list property names t

Feature Transform Net, input is BxNx1xK Return: Transformation matrix of size KxK

pred: B,N,13 label: B,N

Input (XYZ) Transform Net, input is BxNx3 gray image Return: Transformation matrix of size 3xK

Discover Euler angle vector from 3x3 matrix Uses the conventions above. Parameters ---------- M : array-like, shape (3,3) cy_th

Prepare block training data. Args: data: N x 6 numpy array, 012 are XYZ in meters, 345 are RGB in [0,1] assumes the data is s

Parse from generator. Raise StopIteration if the property could not be read.

Parse a PLY header from a readable file-like stream.

Parse a list of PLY element definitions.

Consume one element definition. The unconsumed input is returned along with a PlyElement instance.

Read the actual data from a PLY file.

Load a PLY element from a binary PLY file. The element may contain list properties.

Load a PLY element from an ASCII-format PLY file. The element may contain list properties.

Return generator over one item.

Write the data to a PLY file.

Save a PLY element to a binary PLY file. The element may contain list properties.

Save a PLY element to an ASCII-format PLY file. The element may contain list properties.

Batch normalization on 1D convolutional maps. Args: inputs: Tensor, 3D BLC input maps is_training: boolean tf.Varialbe, true in

Batch normalization on 3D convolutional maps. Args: inputs: Tensor, 5D BDHWC input maps is_training: boolean tf.Varialbe, true

Batch normalization on FC data. Args: inputs: Tensor, 2D BxC input is_training: boolean tf.Varialbe, true indicates training ph

Return matrix for rotations around z, y and x axes Uses the z, then y, then x convention above Parameters ---------- z : scalar

Return quaternion corresponding to these Euler angles Uses the z, then y, then x convention above Parameters ---------- z : scalar

ops: dict mapping from string to tf ops

ops: dict mapping from string to tf ops

Classification PointNet, input is BxNx3, output Bx40

Classification PointNet, input is BxNx3, output BxNx50

Classification PointNet, input is BxNx3, output Bx40

Transform Net, input is BxNx3 gray image Return: Transformation matrix of size 3xK

Transform Net, input is BxNx1xK gray image Return: Transformation matrix of size KxK

input points Nx3 numpy array (+y is up direction). return an numpy array gray image of size 500x1500.

Demo for draw_point_cloud function

input is Nx3 points. output is vsize*vsize*vsize assumes points are in range [-radius, radius]

points is a Nx3 numpy array

read XYZ point cloud from filename PLY file

room2block with input filename and RGB preprocessing.

room2block, with input filename and RGB preprocessing. for each block centralize XYZ, add normalized XYZ as 678 channels

Prepare whole room samples. Args: data: N x 6 numpy array, 012 are XYZ in meters, 345 are RGB in [0,1] assumes the data is s

room2sample, with input filename and RGB preprocessing. for each block centralize XYZ, add normalized XYZ as 678 channels

data is in N x ... we want to keep num_samplexC of them. if N > num_sample, we will randomly keep num_sample of them. if N <

ops: dict mapping from string to tf ops

ops: dict mapping from string to tf ops

vol is occupancy grid (value = 0 or 1) of size vsize*vsize*vsize return Nx3 numpy array.