This is not part of the public interface. The preferred methods of obtaining PlyElement instances are PlyData.read (to read from

Read data from a binary stream. Raise StopIteration if the property could not be read.

Return generator over the (numerical) PLY representation of the list data (length followed by actual data).

Write data to a binary stream.

Write data to a binary stream.

Convert angle, axis pair to Euler angles Parameters ---------- theta : scalar angle of rotation vector : 3 element sequence

2D avg pooling. Args: inputs: 4-D tensor BxHxWxC kernel_size: a list of 2 ints stride: a list of 2 ints Returns: Variable ten

3D avg pooling. Args: inputs: 5-D tensor BxDxHxWxC kernel_size: a list of 3 ints stride: a list of 3 ints Returns: Variable t

Visualization of bounding boxes. Args: input_filename: each line is x1 y1 z1 x2 y2 z2 label out_filename_prefix: OBJ filenam

Visualization of bounding boxes. Args: input_filename: each line is x1 y1 z1 x2 y2 z2 label out_filename_prefix: OBJ filenam

Compute bounding boxes from each instance in original dataset files on one room. **We assume the bbox is aligned with XYZ coordinate.**

Compute bounding boxes from each instance in original dataset files on one room. **We assume the bbox is aligned with XYZ coordinate.**

Convert original dataset files to data_label file (each line is XYZRGBL). We aggregated all the points from each instance in the room. A

1D convolution with non-linear operation. Args: inputs: 3-D tensor variable BxLxC num_output_channels: int kernel_size: int scope:

2D convolution with non-linear operation. Args: inputs: 4-D tensor variable BxHxWxC num_output_channels: int kernel_size: a list of 2

2D convolution transpose with non-linear operation. Args: inputs: 4-D tensor variable BxHxWxC num_output_channels: int kernel_size: a

3D convolution with non-linear operation. Args: inputs: 5-D tensor variable BxDxHxWxC num_output_channels: int kernel_size: a list of

Dropout layer. Args: inputs: tensor is_training: boolean tf.Variable scope: string keep_prob: float in [0,1] noise_shape: list

List properties always have a numpy dtype of "object".

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

Fully connected layer with non-linear operation. Args: inputs: 2-D tensor BxN num_outputs: int Returns: Variable tensor of size

pred: B*NUM_CLASSES, label: B,

pred: BxNxC, label: BxN,

pred: B*NUM_CLASSES, label: B,

ConvNet baseline, input is BxNx3 gray image

Provide PLY-formatted metadata for the instance.

Format this element's metadata as it would appear in a PLY header.

Randomly jitter points. jittering is per point. Input: BxNx3 array, original batch of point clouds Return: BxNx3

Make a 2D array from an array of arrays. The `cols' and `dtype' arguments can be omitted if the array is not empty.

2D max pooling. Args: inputs: 4-D tensor BxHxWxC kernel_size: a list of 2 ints stride: a list of 2 ints Returns: Variable ten

3D max pooling. Args: inputs: 5-D tensor BxDxHxWxC kernel_size: a list of 3 ints stride: a list of 3 ints Returns: Variable t

Input is BxNx3 batch of point cloud Output is Bx(vsize^3)

For visualization of a room from data_label file, input_filename: each line is X Y Z R G B L out_filename: OBJ filename, visualize inpu

vol is of size vsize*vsize*vsize output an image to output_filename

Return Euler angles corresponding to quaternion `q` Parameters ---------- q : 4 element sequence w, x, y, z of quaternion Re

Randomly rotate the point clouds to augument the dataset rotation is per shape based along up direction Input: BxNx3 array,

Rotate the point cloud along up direction with certain angle. Input: BxNx3 array, original batch of point clouds Return:

Shuffle data and labels. Input: data: B,N,... numpy array label: B,... numpy array Return: shuffled dat

input: Nx3, write points to filename as PLY format.