Compute the mean and std value of dataset.

It used to suppress the presence of a large number of negative prediction. It works on image level not batch level. For any example/image

Args: box_scores (N, 5): boxes in corner-form and probabilities. iou_threshold: intersection over union threshold. top_k

Init layer parameters.

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

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

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

make dir if not exist

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

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

Non-maximum suppression. Arguments: boxes: a float numpy array of shape [n, 5], where each row is (xmin, ymin, xmax, ymax, sc

Subtract mean and normalize, imgs [N, 1, W, H]

Pure Python NMS baseline.

given a face with bbox and landmark, rotate with alpha and return rotated face with bbox, landmark (absolute position)

scale the landmark from [0,1] to [-1,1]

Draw bounding boxes and facial landmarks. Arguments: img: an instance of PIL.Image. bounding_boxes: a float numpy array of shape