在Object detection里，faster rcnn可以说是两步检测方法中被普遍使用的了。

下面以vgg16为base network的结构来介绍一下。

图片链接

可以参考知乎上的这篇文章和[这篇文章]（https://zhuanlan.zhihu.com/p/29400164）。

下图来源于上面的文章。

def calc_rpn(C, img_data, width, height, resized_width, resized_height, img_length_calc_function):

    downscale = float(C.rpn_stride)
    anchor_sizes = C.anchor_box_scales
    anchor_ratios = C.anchor_box_ratios
    num_anchors = len(anchor_sizes) * len(anchor_ratios)    

    # calculate the output map size based on the network architecture

    (output_width, output_height) = img_length_calc_function(resized_width, resized_height)

    n_anchratios = len(anchor_ratios)

    # initialise empty output objectives
    y_rpn_overlap = np.zeros((output_height, output_width, num_anchors))
    y_is_box_valid = np.zeros((output_height, output_width, num_anchors))
    y_rpn_regr = np.zeros((output_height, output_width, num_anchors * 4))

    num_bboxes = len(img_data['bboxes'])

    num_anchors_for_bbox = np.zeros(num_bboxes).astype(int)
    best_anchor_for_bbox = -1*np.ones((num_bboxes, 4)).astype(int)
    best_iou_for_bbox = np.zeros(num_bboxes).astype(np.float32)
    best_x_for_bbox = np.zeros((num_bboxes, 4)).astype(int)
    best_dx_for_bbox = np.zeros((num_bboxes, 4)).astype(np.float32)

    # get the GT box coordinates, and resize to account for image resizing
    gta = np.zeros((num_bboxes, 4))
    for bbox_num, bbox in enumerate(img_data['bboxes']):
        # get the GT box coordinates, and resize to account for image resizing
        gta[bbox_num, 0] = bbox['x1'] * (resized_width / float(width))
        gta[bbox_num, 1] = bbox['x2'] * (resized_width / float(width))
        gta[bbox_num, 2] = bbox['y1'] * (resized_height / float(height))
        gta[bbox_num, 3] = bbox['y2'] * (resized_height / float(height))