看本文之前,请先了解 faster rcnn 的网络结构及原理;
其中 关于 anchor 的部分比较晦涩,不容易搞清楚,本文重点解释下;
先上代码
import numpy as np # 生成anchors总函数:ratios为一个列表,表示宽高比为:1:2,1:1,2:1 # 2**x表示:2^x,scales:[2^3 2^4 2^5],即:[8 16 32] def generate_anchors(base_size=16, ratios=[0.5, 1, 2], scales=2 ** np.arange(3, 6)): """ Generate anchor (reference) windows by enumerating aspect ratios X scales wrt a reference (0, 0, 15, 15) window. """ base_anchor = np.array([1, 1, base_size, base_size]) - 1 # 新建一个数组:base_anchor:[0 0 15 15] ratio_anchors = _ratio_enum(base_anchor, ratios) # 枚举各种宽高比 anchors = np.vstack([_scale_enum(ratio_anchors[i, :], scales) # 枚举各种尺度,vstack:竖向合并数组 for i in range(ratio_anchors.shape[0])]) # shape[0]:读取矩阵第一维长度,其值为3 return anchors # 用于返回width,height,(x,y)中心坐标(对于一个anchor窗口) def _whctrs(anchor): """ Return width, height, x center, and y center for an anchor (window). """ # anchor:存储了窗口左上角,右下角的坐标 w = anchor[2] - anchor[0] + 1 h = anchor[3] - anchor[1] + 1 x_ctr = anchor[0] + 0.5 * (w - 1) # anchor中心点坐标 y_ctr = anchor[1] + 0.5 * (h - 1) return w, h, x_ctr, y_ctr # 给定一组宽高向量,输出各个anchor,即预测窗口,**输出anchor的面积相等,只是宽高比不同** def _mkanchors(ws, hs, x_ctr, y_ctr): # ws:[23 16 11],hs:[12 16 22],ws和hs一一对应。 """ Given a vector of widths (ws) and heights (hs) around a center (x_ctr, y_ctr), output a set of anchors (windows). """ print('ctr', x_ctr, y_ctr) # ctr 7.5 7.5 print('ws1', ws) # 23. 16. 11.] ws = ws[:, np.newaxis] # newaxis:将数组转置 print('ws2', ws) # [[23.] # [16.] # [11.]] hs = hs[:, np.newaxis] anchors = np.hstack((x_ctr - 0.5 * (ws - 1), # hstack、vstack:合并数组 y_ctr - 0.5 * (hs - 1), # anchor:[[-3.5 2 18.5 13] 7.5-0.5*(23-1)=7.5-11=-3.5 x_ctr + 0.5 * (ws - 1), # [0 0 15 15] y_ctr + 0.5 * (hs - 1))) # [2.5 -3 12.5 18]] return anchors # 枚举一个anchor的各种宽高比,anchor[0 0 15 15],ratios[0.5,1,2] def _ratio_enum(anchor, ratios): """ 列举关于一个anchor的三种宽高比 1:2,1:1,2:1 Enumerate a set of anchors for each aspect ratio wrt an anchor. """ w, h, x_ctr, y_ctr = _whctrs(anchor) # 返回宽高和中心坐标,w:16,h:16,x_ctr:7.5,y_ctr:7.5 size = w * h # size:16*16=256 size_ratios = size / ratios # 256/ratios[0.5,1,2]=[512,256,128] # round()方法返回x的四舍五入的数字,sqrt()方法返回数字x的平方根 ws = np.round(np.sqrt(size_ratios)) # ws:[23 16 11] hs = np.round(ws * ratios) # hs:[12 16 22],ws和hs一一对应。as:23&12 anchors = _mkanchors(ws, hs, x_ctr, y_ctr) # 给定一组宽高向量,输出各个预测窗口 return anchors # 枚举一个anchor的各种尺度,以anchor[0 0 15 15]为例,scales[8 16 32] def _scale_enum(anchor, scales): """ 列举关于一个anchor的三种尺度 128*128,256*256,512*512 Enumerate a set of anchors for each scale wrt an anchor. """ w, h, x_ctr, y_ctr = _whctrs(anchor) # 返回宽高和中心坐标,w:16,h:16,x_ctr:7.5,y_ctr:7.5 ws = w * scales # [128 256 512] hs = h * scales # [128 256 512] anchors = _mkanchors(ws, hs, x_ctr, y_ctr) # [[-56 -56 71 71] [-120 -120 135 135] [-248 -248 263 263]] return anchors if __name__ == '__main__': # 主函数 import time t = time.time() a = generate_anchors() # 生成anchor(窗口) print(time.time() - t) # 显示时间 print(a) from IPython import embed embed()
在 经过 backbone 卷积网络 生成 feature map 后,
feature map 每个格子可以对应到原图的一个区域,这个区域的大小 可以自己设定;
然后 以这个区域为 基准,通过 各种长宽比变换、尺度变换,生成多个 anchor;
比较抽象,不容易说清楚,下图有详解,自己体会吧
在 faster rcnn 中,输入 图像需 resize 到 M=800,N=600 大小,anchor 512 scale 大小为 512x512=262144,352x704=247808,736x384=282624
参考资料:
https://blog.csdn.net/sinat_33486980/article/details/81099093 faster R-CNN中anchors 的生成过程
https://blog.csdn.net/xzzppp/article/details/52317863 faster rcnn RPN之anchor(generate_anchors)源码解析