Parse groundtruth labels to OBB parameters. Args: end_points: dict {center_label, heading_class_label, heading_residual_

Parse predictions to OBB parameters and suppress overlapping boxes Args: end_points: dict {point_clouds, center, heading

Input is BxNx3 a batch of point cloud Output is BxIxIxnum_samplex3 Added on Feb 19

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

Input is BxNx3 a batch of point cloud Output is BxVxVxVxnum_samplex3 Added on Feb 19

Checks whether new_pts ly in the frustum defined by the coordinates of the corners coner_coords :param corner_coords: torch tensor o

Ref: http://stackoverflow.com/questions/24467972/calculate-area-of-polygon-given-x-y-coordinates

Ref: http://stackoverflow.com/questions/24467972/calculate-area-of-polygon-given-x-y-coordinates

poly learning rate policy

same output as PIL.ImageOps.posterize

pre-compute text features, labelset, palette, and mapper.

forward pass of backprojection for 2d features onto 3d points :param label: image features (shape: (num_input_channels, proj_image_d

projects hidden states correctly to key/query states

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

read XYZ for each vertex.

read XYZ RGB for each vertex. Note: RGB values are in 0-255

read XYZ RGB normals point cloud from filename PLY file

read XYZ point cloud from filename PLY file

r"""Register a dataset builder to registry with key 'name' Args: name: Key with which the builder will be registered. Us

r"""Register a model to registry with key 'name' Args: name: Key with which the task will be registered. Usage:

r"""Register a task to registry with key 'name' Args: name: Key with which the task will be registered. Usage:

r"""Register a processor to registry with key 'name' Args: name: Key with which the task will be registered. Usage:

r"""Register a model to registry with key 'name' Args: name: Key with which the task will be registered. Usage:

r"""Register a task to registry with key 'name' Args: name: Key with which the task will be registered. Usage:

Do spatial cropping and resizing to the video clip Args: clip (torch.tensor): Video clip to be cropped. Size is (C, T, H, W)

like PIL, rotate by degree, not radians

Input ps is NxC points with first 3 channels as XYZ z is facing forward, x is left ward, y is downward

Input: (n,3), Output: (n,3)

Rotation about the y-axis. t: (x1,x2,...xn) return: (x1,x2,...,xn,3,3)

Create share memory.

Common i/o utility to handle saving data to various file formats. Supported: .pkl, .pickle, .npy, .json Specifically for .json, u

Initialize the detectron2 logger and set its verbosity level to "INFO". Args: output (str): a file name or a directory to save log. I

projection

The differences the this result and PIL are all on the 4 boundaries, the center areas are same