原文中rcnn部分的截图
黑色是滑动窗口的区域，就是上图的红色区域的sliding window其他颜色 9种窗口 就是anchor机制生成的9种区域。
def generate_anchor_base(base_size=16, ratios=[0.5, 1, 2],
anchor_scales=[8, 16, 32]):
py = base_size / 2.
px = base_size / 2.
anchor_base = np.zeros((len(ratios) * len(anchor_scales), 4),
dtype=np.float32)
for i in six.moves.range(len(ratios)):
for j in six.moves.range(len(anchor_scales)):
h = base_size * anchor_scales[j] * np.sqrt(ratios[i])
w = base_size * anchor_scales[j] * np.sqrt(1. / ratios[i])
index = i * len(anchor_scales) + j
anchor_base[index, 0] = py - h / 2.
anchor_base[index, 1] = px - w / 2.
anchor_base[index, 2] = py + h / 2.
anchor_base[index, 3] = px + w / 2.
return anchor_base
生成了9个锚点坐标。
def _enumerate_shifted_anchor_torch(anchor_base, feat_stride, height, width):
# 将所有的锚点坐标存储并且将数组转为torch.cudatensor
# Enumerate all shifted anchors:
#
# add A anchors (1, A, 4) to
# cell K shifts (K, 1, 4) to get
# shift anchors (K, A, 4)
# reshape to (K*A, 4) shifted anchors
# return (K*A, 4)
# !TODO: add support for torch.CudaTensor
# xp = cuda.get_array_module(anchor_base)
import torch as t
shift_y = t.arange(0, height * feat_stride, feat_stride)
shift_x = t.arange(0, width * feat_stride, feat_stride)
shift_x, shift_y = xp.meshgrid(shift_x, shift_y)
shift = xp.stack((shift_y.ravel(), shift_x.ravel(),
shift_y.ravel(), shift_x.ravel()), axis=1)
A = anchor_base.shape[0]
K = shift.shape[0]
anchor = anchor_base.reshape((1, A, 4)) + \
shift.reshape((1, K, 4)).transpose((1, 0, 2))
anchor = anchor.reshape((K * A, 4)).astype(np.float32)
return anchor