rpn代码详解

   # coding: UTF-8
from __future__ import absolute_import
import numpy as np
import cv2
import random
import copy
# 这里C代表一个参数类(上面的Config)，C = Config()
def calc_rpn(C, img_data, width, height, resized_width, resized_height, img_length_calc_function):


    # 接下来读取了几个参数，downscale就是从图片到特征图的缩放倍数(默认为16.0) 这里,
    # img_length_calc_function（也就是实际的vgg中的get_img_output_length中整除的值一样。）
    # anchor_size和anchor_ratios是我们初步选区大小的参数，比如3个size和3个ratios，可以组合成9种不同形状大小的选区。
    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
    # 接下来,
    # 通过img_length_calc_function 对VGG16 返回的是一个height和width都整除16的结果这个方法计算出了特征图的尺寸。
    # output_width = output_height = 600 // 16 = 37
    (output_width, output_height) = img_length_calc_function(resized_width, resized_height)


    # 下一步是几个变量初始化可以先不看，后面用到的时候再看。

    # n_anchratios = 3
    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)


    # 因为我们的计算都是基于resize以后的图像的，所以接下来把bbox中的x1,x2,y1,y2分别通过缩放匹配到resize以后的图像。
    # 这里记做gta，尺寸为(num_of_bbox,4)。
    # 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))

    # rpn ground truth
    # 这一段计算了anchor的长宽，然后比较重要的就是把特征图的每一个点作为一个锚点，
    # 通过乘以downscale，映射到图片的实际尺寸&