Match each prior box with the ground truth box of the highest jaccard overlap, encode the bounding boxes, then return the matched indices corr

return iof of a and b, numpy version for data augenmentation

Compute the jaccard overlap of two sets of boxes. The jaccard overlap is simply the intersection over union of two boxes. E.g.: A ∩ B

Convert prior_boxes to (xmin, ymin, xmax, ymax) representation for comparison to point form ground truth data. Args: boxes: (tensor)

Convert prior_boxes to (xmin, ymin, xmax, ymax) representation for comparison to point form ground truth data. Args: boxes: (tensor)

Pure Python NMS baseline.

Run P-Net, generate bounding boxes, and do NMS. Arguments: image: an instance of PIL.Image. net: an instance of pytorch's nn.Modu

Soft NMS implementation. References: https://arxiv.org/abs/1704.04503 https://github.com/facebookresearch/Detectron/blob/master/d

Function: ---------- apply the inverse of affine transform 'trans' to uv Parameters: ---------- @trans: 3x3 np.array

Function: ---------- apply affine transform 'trans' to uv Parameters: ---------- @src_img: 3x3 np.array i

Args: image (Tensor): image tensor to be transformed Return: a tensor with channels swapped according to swap

Args: img: the output of cv.imread in RGB layout. boxes: boundding boxes in the form of (x1, y1, x2, y2).

:param cfg: Network related settings. :param phase: train or test.

paths is a distionary with {name:filepath} pair