Decode locations from predictions using priors to undo the encoding we did for offset regression at train time. Args: loc (tensor): lo

Decode landm from predictions using priors to undo the encoding we did for offset regression at train time. Args: pre (tensor): landm

Pure Python NMS baseline.

Old style model is stored with all names of parameters sharing common prefix 'module.'

Old style model is stored with all names of parameters sharing common prefix 'module.'

Old style model is stored with all names of parameters sharing common prefix 'module.'

Old style model is stored with all names of parameters sharing common prefix 'module.'

Sets the learning rate # Adapted from PyTorch Imagenet example: # https://github.com/pytorch/examples/blob/master/imagenet/main.py

Encode the variances from the priorbox layers into the ground truth boxes we have matched (based on jaccard overlap) with the prior boxes. Arg

Encode the variances from the priorbox layers into the ground truth boxes we have matched (based on jaccard overlap) with the prior boxes. Arg

gt dir: (wider_face_val.mat, wider_easy_val.mat, wider_medium_val.mat, wider_hard_val.mat)

single image evaluation pred: Nx5 gt: Nx4 ignore:

We resize both tensors to [A,B,2] without new malloc: [A,2] -> [A,1,2] -> [A,B,2] [B,2] -> [1,B,2] -> [A,B,2] Then we compute the area of

Compute the jaccard overlap of two sets of boxes. The jaccard overlap is simply the intersection over union of two boxes. Here we operate on

Utility function for computing log_sum_exp while determining This will be used to determine unaveraged confidence loss across all examples in

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

norm score pred {key: [[x1,y1,x2,y2,s]]}

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

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

Convert prior_boxes to (cx, cy, w, h) representation for comparison to center-size form ground truth data. Args: boxes: (tensor) poin

Custom collate fn for dealing with batches of images that have a different number of associated object annotations (bounding boxes). Argument

Multibox Loss Args: predictions (tuple): A tuple containing loc preds, conf preds, and prior boxes from SSD net.

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

Apply non-maximum suppression at test time to avoid detecting too many overlapping bounding boxes for a given object. Args: boxes: (te