更多请参考:
最详细的Faster RCNN解读
首先,RPNnet注意包括两部分,一个是用于预测预测框的前景背景,因此输出为2k,其中k对应的是所有anchor boxes的个数;另一个是用于预测对应的坐标映射关系,输出为4k;
然后RPN net的输出结合上一层的feature map同时送入ROI pooling层,然后做进一步的判别。
scales=[8,16,32]
ratios=[0.5,1,2]
w=[23,16,11]
h=[12,16,22]
1:1,1:2,2:1三种比例,因此可能的[w,h]共有如下9种,
23,12—>[184,96],[368,192],[736384]
16,16—>[128,128],[256,256],[512,512]
11,22—>[88,176],[176,352],[352704]
代码如下:
import numpy as np
# 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.]])
#after test,we found that anchors returned by <generate_anchors> func is a np.array with shape is (9,4),
#which represent the feature map (0,0) position that output 9 anchors with 4 coordinates.
#below is the result we got!
'''
(9, 4)
[[ -84. -40. 99. 55.]
[-176. -88. 191. 103.]
[-360. -184. 375. 199.]
[ -56. -56. 71. 71.]
[-120. -120. 135. 135.]
[-248. -248. 263. 263.]
[ -36. -80. 51. 95.]
[ -80. -168. 95. 183.]
[-168. -344. 183. 359.]]
'''
#notice actually noticing this code is sufficient for you to understand the process of generating anchors!
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
ratio_anchors = _ratio_enum(base_anchor, ratios)
print(ratio_anchors)
print(ratio_anchors.shape)
anchors = np.vstack([_scale_enum(ratio_anchors[i, :], scales)
for i in range(ratio_anchors.shape[0])])
print(anchors)
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
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]
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.
"""
w, h, x_ctr, y_ctr = _whctrs(anchor)
print(anchor)
print(x_ctr,y_ctr,w,h)
size = w * h
size_ratios = size / ratios
print(size_ratios)
print("**********************")
ws = np.round(np.sqrt(size_ratios))
hs = np.round(ws * ratios)
print(ws,hs)
print("======================")
anchors = _mkanchors(ws, hs, x_ctr, y_ctr)
return anchors
def _scale_enum(anchor, scales):
"""
Enumerate a set of anchors for each scale wrt an anchor.
"""
w, h, x_ctr, y_ctr = _whctrs(anchor)
print(w,h,x_ctr,y_ctr)
ws = w * scales
hs = h * scales
print(ws,hs,x_ctr,y_ctr)
anchors = _mkanchors(ws, hs, x_ctr, y_ctr)
return anchors
if __name__ == '__main__':
generate_anchors()