faster rcnn中anchor的生成

faster rcnn anchor

anchors 值的含义为

总共有9个anchor，对于每一个anchor，其四个数值分别代表矩形框的左下角x,y，右上角x,y.

anchor的预设值为

# 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

anchor的值是由如下步骤计算得来的:

1. 先设置基础anchor，默认为[0,0,15,15],计算基础anchor的宽(16)和高(16)，anchor中心(7.5,7.5)，以及面积(256)
2. 计算基础anchor的面积，分别除以[0.5,1,2],得到[512,256,128]
3. anchor的宽度w由三个面积的平方根值确定,得到[23,16,11]
4. anchor的高度h由[23,16,11]*[0.5,1,2]确定,得到[12,16,22].
5. 由anchor的中心以及不同的宽和高可以得到此时的anchors.即

array([    [ -3.5,   2. ,  18.5,  13. ],
           [  0. ,   0. ,  15. ,  15. ],
           [  2.5,  -3. ,  12.5,  18. ]])

6. 再利用三种不同的scales[8,16,32]分别去扩大anchors，扩大的方法是先计算出来上一步的anchor的中心以及宽高，使宽高分别乘以scale，然后再利用中心和新的宽高计算出最终所要的anchors

anchors生成过程如下: (python2)

来源于: https://github.com/smallcorgi/Faster-RCNN_TF/blob/master/lib/rpn_msr/generate_anchors.py

# --------------------------------------------------------
# Faster R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick and Sean Bell
# --------------------------------------------------------

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.]])

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)
    anchors = np.vstack([scale_enum(ratio_anchors[i, :], scales)
                         for i in xrange(ratio_anchors.shape[0])])
    return anchors

# def _whctrs(anchor):
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):
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):
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)
    size = w * h
    size_ratios = size / ratios
    ws = np.round(np.sqrt(size_ratios))
    hs = np.round(ws * ratios)
    anchors = mkanchors(ws, hs, x_ctr, y_ctr)
    return anchors

# def _scale_enum(anchor, scales):
def scale_enum(anchor, scales):
    """
    Enumerate a set of anchors for each scale wrt an anchor.
    """

    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()