fast中的_bbox_pred函数和faster中的bbox_transform_inv是一样的，是将框进行4个坐标变换得到新的框坐标。fast中是将selective search生成的框坐标进行回归变换，faster中用了两个地方，一个是把根据rpn滑动机制生成的anchor框进行回归变换，另一个是在fast rcnn网络中把rpn生成的region proposal进行回归变换。

def _bbox_pred(boxes, box_deltas):    """Transform the set of class-agnostic boxes into class-specific boxes    by applying the predicted offsets (box_deltas)    """    if boxes.shape[0] == 0:        return np.zeros((0, box_deltas.shape[1]))    boxes = boxes.astype(np.float, copy=False)    widths = boxes[:, 2] - boxes[:, 0] + cfg.EPS    heights = boxes[:, 3] - boxes[:, 1] + cfg.EPS    ctr_x = boxes[:, 0] + 0.5 * widths    ctr_y = boxes[:, 1] + 0.5 * heights    dx = box_deltas[:, 0::4]    dy = box_deltas[:, 1::4]    dw = box_deltas[:, 2::4]    dh = box_deltas[:, 3::4]    pred_ctr_x = dx * widths[:, np.newaxis] + ctr_x[:, np.newaxis]    pred_ctr_y = dy * heights[:, np.newaxis] + ctr_y[:, np.newaxis]    pred_w = np.exp(dw) * widths[:, np.newaxis]    pred_h = np.exp(dh) * heights[:, np.newaxis]    pred_boxes = np.zeros(box_deltas.shape)    # x1    pred_boxes[:, 0::4] = pred_ctr_x - 0.5 * pred_w    # y1    pred_boxes[:, 1::4] = pred_ctr_y - 0.5 * pred_h    # x2    pred_boxes[:, 2::4] = pred_ctr_x + 0.5 * pred_w    # y2    pred_boxes[:, 3::4] = pred_ctr_y + 0.5 * pred_h    return pred_boxes