Add config for DETR.

Run all_gather on arbitrary picklable data (not necessarily tensors) Args: data: any picklable object Returns: list[data]

corners: (8,3) no assumption on axis direction

corners: (8,3) no assumption on axis direction

corners: (8,3) no assumption on axis direction

corners: (8,3) no assumption on axis direction

Build a dataset, defined by `dataset_name`. Args: cfg (eDICT): Returns: Dataset: a constructed dataset specified by data

Inverse function to angle2class

volume of enclosing axis-aligned box

volume of enclosing axis-aligned box

Generic functions to compute precision/recall for object detection for a single class. Input: pred: map of {img_id: [(bbox, score)]} w

Generic functions to compute precision/recall for object detection for a single class. Input: pred: map of {img_id: [(bbox, score)]} w

Flip X-right,Y-forward,Z-up to X-right,Y-down,Z-forward Input and output are both (N,3) array

Flip X-right,Y-forward,Z-up to X-right,Y-down,Z-forward Input and output are both (N,3) array

Flip X-right,Y-forward,Z-up to X-right,Y-down,Z-forward Input and output are both (N,3) array

Flip X-right,Y-forward,Z-up to X-right,Y-down,Z-forward Input and output are both (N,3) array

Get root logger and add a keyword filter to it. The logger will be initialized if it has not been initialized. By default a StreamHandler will

imgs: (N, 3, H, W) x: (N, L, patch_size**2 *3)

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

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

Clip a polygon with another polygon. Ref: https://rosettacode.org/wiki/Sutherland-Hodgman_polygon_clipping#Python Args: subjectPolygon:

Clip a polygon with another polygon. Ref: https://rosettacode.org/wiki/Sutherland-Hodgman_polygon_clipping#Python Args: subjectPolygon:

project point cloud from depth coord to camera coordinate Input: (N,3) Output: (N,3)

Input: (N,3) Output: (N,2) UV and (N,) depth

Args: input_dict (dict): all the values will be reduced average (bool): whether to do average or sum Reduce the values in the

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

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

Rotation about the z-axis.

Rotation about the z-axis.

Perform NMS on predicted boxes and threshold them according to score. Convert GT boxes

x: (N, L, patch_size**2 *3) imgs: (N, 3, H, W)