roidb2.py 文件源码

def _compute_targets(rois, overlaps, labels, num_classes):
    """Compute bounding-box regression targets for an image."""
    # Ensure ROIs are floats
    rois = rois.astype(np.float, copy=False)

    # Indices of ground-truth ROIs
    gt_inds = np.where(overlaps == 1)[0]
    # Indices of examples for which we try to make predictions
    ex_inds = []
    for i in xrange(1, num_classes):
        ex_inds.extend( np.where((labels == i) & (overlaps >= cfg.TRAIN.BBOX_THRESH))[0] )

    # Get IoU overlap between each ex ROI and gt ROI
    ex_gt_overlaps = utils.cython_bbox.bbox_overlaps(rois[ex_inds, :],
                                                     rois[gt_inds, :])

    # Find which gt ROI each ex ROI has max overlap with:
    # this will be the ex ROI's gt target
    if ex_gt_overlaps.shape[0] != 0:
        gt_assignment = ex_gt_overlaps.argmax(axis=1)
    else:
        gt_assignment = []
    gt_rois = rois[gt_inds[gt_assignment], :]
    ex_rois = rois[ex_inds, :]

    ex_widths = ex_rois[:, 2] - ex_rois[:, 0] + cfg.EPS
    ex_heights = ex_rois[:, 3] - ex_rois[:, 1] + cfg.EPS
    ex_ctr_x = ex_rois[:, 0] + 0.5 * ex_widths
    ex_ctr_y = ex_rois[:, 1] + 0.5 * ex_heights

    gt_widths = gt_rois[:, 2] - gt_rois[:, 0] + cfg.EPS
    gt_heights = gt_rois[:, 3] - gt_rois[:, 1] + cfg.EPS
    gt_ctr_x = gt_rois[:, 0] + 0.5 * gt_widths
    gt_ctr_y = gt_rois[:, 1] + 0.5 * gt_heights

    targets_dx = (gt_ctr_x - ex_ctr_x) / ex_widths
    targets_dy = (gt_ctr_y - ex_ctr_y) / ex_heights
    targets_dw = np.log(gt_widths / ex_widths)
    targets_dh = np.log(gt_heights / ex_heights)

    targets = np.zeros((rois.shape[0], 5), dtype=np.float32)
    targets[ex_inds, 0] = labels[ex_inds]
    targets[ex_inds, 1] = targets_dx
    targets[ex_inds, 2] = targets_dy
    targets[ex_inds, 3] = targets_dw
    targets[ex_inds, 4] = targets_dh
    return targets