# --------------------------------------------------------
# Faster R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick and Sean Bell
# --------------------------------------------------------
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
# Verify that we compute the same anchors as Shaoqing's matlab implementation:
#
# >> load output/rpn_cachedir/faster_rcnn_VOC2007_ZF_stage1_rpn/anchors.mat
# >> anchors
#
# anchors =
#
# -83 -39 100 56
# -175 -87 192 104
# -359 -183 376 200
# -55 -55 72 72
# -119 -119 136 136
# -247 -247 264 264
# -35 -79 52 96
# -79 -167 96 184
# -167 -343 184 360
# array([[ -83., -39., 100., 56.],
# [-175., -87., 192., 104.],
# [-359., -183., 376., 200.],
# [ -55., -55., 72., 72.],
# [-119., -119., 136., 136.],
# [-247., -247., 264., 264.],
# [ -35., -79., 52., 96.],
# [ -79., -167., 96., 184.],
# [-167., -343., 184., 360.]])
# base_size=16,因为经过卷积之后，M*N的矩阵对应的特征图为M/16*N/16，（4个pooling）不知道是不是这样
# 所以feature map上一点对应到原图就是16*16的区域
# ratios表示宽高比为：1:2,1:1,2:1
# 2**x表示: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 # [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) # 对已经进行宽高比改变的，在进行3种尺度改变
for i in range(ratio_anchors.shape[0])])
return anchors
# _whctrs返回一个anchor的中心点(x,y)和w,h
def _whctrs(anchor):
"""
Return width, height, x center, and y center for an anchor (window).
"""
w = anchor[2] - anchor[0] + 1
h = anchor[3] - anchor[1] + 1
x_ctr = anchor[0] + 0.5 * (w - 1)
y_ctr = anchor[1] + 0.5 * (h - 1)
return w, h, x_ctr, y_ctr
# 输出各个anchors
def _mkanchors(ws, hs, x_ctr, y_ctr):
"""
Given a vector of widths (ws) and heights (hs) around a center
(x_ctr, y_ctr), output a set of anchors (windows).
"""
ws = ws[:, np.newaxis] # newaxis:将数组转置
hs = hs[:, np.newaxis]
anchors = np.hstack((x_ctr - 0.5 * (ws - 1),
y_ctr - 0.5 * (hs - 1),
x_ctr + 0.5 * (ws - 1),
y_ctr + 0.5 * (hs - 1)))
return anchors
def _ratio_enum(anchor, ratios):
"""
Enumerate a set of anchors for each aspect ratio wrt an anchor.
"""
# 列举关于一个anchor的三种宽高比 1:2,1:1,2:1
w, h, x_ctr, y_ctr = _whctrs(anchor) # _whctrs返回一个anchor的中心点(x,y)和w,h
size = w * h # 16*16
size_ratios = size / ratios # 16*16=256/[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)) # [23,16,11]
hs = np.round(ws * ratios) # [12,16,22]
# 就是将中心(x,y),w,h转换为左上和右下坐标
anchors = _mkanchors(ws, hs, x_ctr, y_ctr) # 输出各个预测窗口
return anchors
def _scale_enum(anchor, scales):
"""
Enumerate a set of anchors for each scale wrt an anchor.
"""
# 列举关于一个anchor的三种尺度 128*128,256*256,512*512
# 3种尺度，3种宽高比，所有9种
w, h, x_ctr, y_ctr = _whctrs(anchor)
ws = w * scales
hs = h * scales
anchors = _mkanchors(ws, hs, x_ctr, y_ctr)
return anchors
if __name__ == '__main__':
import time
t = time.time()
a = generate_anchors()
print(time.time() - t)
print(a)
from IPython import embed;
embed()
