face_recognition/face_detect/vision/utils/box_utils_numpy.py

import numpy as np


def convert_locations_to_boxes(locations, priors, center_variance,
                               size_variance):
    """Convert regressional location results of SSD into boxes in the form of (center_x, center_y, h, w).

    The conversion:
        $$predicted\_center * center_variance = \frac {real\_center - prior\_center} {prior\_hw}$$
        $$exp(predicted\_hw * size_variance) = \frac {real\_hw} {prior\_hw}$$
    We do it in the inverse direction here.
    Args:
        locations (batch_size, num_priors, 4): the regression output of SSD. It will contain the outputs as well.
        priors (num_priors, 4) or (batch_size/1, num_priors, 4): prior boxes.
        center_variance: a float used to change the scale of center.
        size_variance: a float used to change of scale of size.
    Returns:
        boxes:  priors: [[center_x, center_y, h, w]]. All the values
            are relative to the image size.
    """
    # priors can have one dimension less.
    if len(priors.shape) + 1 == len(locations.shape):
        priors = np.expand_dims(priors, 0)
    return np.concatenate([
        locations[..., :2] * center_variance * priors[..., 2:] + priors[..., :2],
        np.exp(locations[..., 2:] * size_variance) * priors[..., 2:]
    ], axis=len(locations.shape) - 1)


def convert_boxes_to_locations(center_form_boxes, center_form_priors, center_variance, size_variance):
    # priors can have one dimension less
    if len(center_form_priors.shape) + 1 == len(center_form_boxes.shape):
        center_form_priors = np.expand_dims(center_form_priors, 0)
    return np.concatenate([
        (center_form_boxes[..., :2] - center_form_priors[..., :2]) / center_form_priors[..., 2:] / center_variance,
        np.log(center_form_boxes[..., 2:] / center_form_priors[..., 2:]) / size_variance
    ], axis=len(center_form_boxes.shape) - 1)


def area_of(left_top, right_bottom):
    """Compute the areas of rectangles given two corners.

    Args:
        left_top (N, 2): left top corner.
        right_bottom (N, 2): right bottom corner.

    Returns:
        area (N): return the area.
    """
    hw = np.clip(right_bottom - left_top, 0.0, None)
    return hw[..., 0] * hw[..., 1]


def iou_of(boxes0, boxes1, eps=1e-5):
    """Return intersection-over-union (Jaccard index) of boxes.

    Args:
        boxes0 (N, 4): ground truth boxes.
        boxes1 (N or 1, 4): predicted boxes.
        eps: a small number to avoid 0 as denominator.
    Returns:
        iou (N): IoU values.
    """
    overlap_left_top = np.maximum(boxes0[..., :2], boxes1[..., :2])
    overlap_right_bottom = np.minimum(boxes0[..., 2:], boxes1[..., 2:])

    overlap_area = area_of(overlap_left_top, overlap_right_bottom)
    area0 = area_of(boxes0[..., :2], boxes0[..., 2:])
    area1 = area_of(boxes1[..., :2], boxes1[..., 2:])
    return overlap_area / (area0 + area1 - overlap_area + eps)


def center_form_to_corner_form(locations):
    return np.concatenate([locations[..., :2] - locations[..., 2:] / 2,
                           locations[..., :2] + locations[..., 2:] / 2], len(locations.shape) - 1)


def corner_form_to_center_form(boxes):
    return np.concatenate([
        (boxes[..., :2] + boxes[..., 2:]) / 2,
        boxes[..., 2:] - boxes[..., :2]
    ], len(boxes.shape) - 1)


def hard_nms(box_scores, iou_threshold, top_k=-1, candidate_size=200):
    """

    Args:
        box_scores (N, 5): boxes in corner-form and probabilities.
        iou_threshold: intersection over union threshold.
        top_k: keep top_k results. If k <= 0, keep all the results.
        candidate_size: only consider the candidates with the highest scores.
    Returns:
         picked: a list of indexes of the kept boxes
    """
    scores = box_scores[:, -1]
    boxes = box_scores[:, :-1]
    picked = []
    # _, indexes = scores.sort(descending=True)
    indexes = np.argsort(scores)
    # indexes = indexes[:candidate_size]
    indexes = indexes[-candidate_size:]
    while len(indexes) > 0:
        # current = indexes[0]
        current = indexes[-1]
        picked.append(current)
        if 0 < top_k == len(picked) or len(indexes) == 1:
            break
        current_box = boxes[current, :]
        # indexes = indexes[1:]
        indexes = indexes[:-1]
        rest_boxes = boxes[indexes, :]
        iou = iou_of(
            rest_boxes,
            np.expand_dims(current_box, axis=0),
        )
        indexes = indexes[iou <= iou_threshold]

    return box_scores[picked, :]