faster rcnn代码解读（二）anchor的生成

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15

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 range(ratio_anchors.shape[0])
    ])
    return anchors

1
2
3
4
5
6
7
8
9
10
11
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)#计算anchor的宽高和中心点坐标
    size = w * h                        #计算size
    size_ratios = size / ratios         #将size进行ratios放缩
    ws = np.round(np.sqrt(size_ratios)) #计算放缩有的w，多个w
    hs = np.round(ws * ratios)          #计算放缩后的h，多个h
    anchors = _mkanchors(ws, hs, x_ctr, y_ctr)#根据计算的ws、hs生成多个anchor，左下角和右上角坐标
    return anchors

1
2
3
4
5
6
7
8
9
10
def _whctrs(anchor):
    """
  Return width, height, x center, and y center for an anchor (window).
  返回滑动窗口anchor的宽、高、中心点坐标
  """
    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

1
2
3
4
5
6
7
8
9
10
11
12
13

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).
  # 在ctr为中心点生成多个以ws、hs为宽高的anchor
  """
    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

1
2
3
4
5
6
7
8
9
def _scale_enum(anchor, scales):
    """
  Enumerate a set of anchors for each scale wrt an anchor.
  """
    w, h, x_ctr, y_ctr = _whctrs(anchor)#计算anchor的宽高和中心点坐标
    ws = w * scales #将w进行scales放缩，多个ws
    hs = h * scales #将h进行scales放缩，多个hs
    anchors = _mkanchors(ws, hs, x_ctr, y_ctr)#根据计算的ws、hs生成多个anchor，左下角和右上角坐标
    return anchors

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
def generate_anchors_pre(height,
                         width,
                         feat_stride,
                         anchor_scales=(8, 16, 32),
                         anchor_ratios=(0.5, 1, 2)):
    """ A wrapper function to generate anchors given different scales
    Also return the number of anchors in variable 'length'
  """
    # 生成标准的len(anchor_ratios)*len(anchor_scales)为一组的anchors
    anchors = generate_anchors( ratios=np.array(anchor_ratios), scales=np.array(anchor_scales))
    A = anchors.shape[0]
    shift_x = np.arange(0, width) * feat_stride #计算x坐标移动长度
    shift_y = np.arange(0, height) * feat_stride#计算y坐标移动长度
    shift_x, shift_y = np.meshgrid(shift_x, shift_y)#生成采样网格，即映射到原height、width上的anchor中心点坐标
    shifts = np.vstack((shift_x.ravel(), shift_y.ravel(), shift_x.ravel(),
                        shift_y.ravel())).transpose()
    K = shifts.shape[0]
    # width changes faster, so here it is H, W, C
    anchors = anchors.reshape((1, A, 4)) + shifts.reshape((1, K, 4)).transpose((1, 0, 2))
    anchors = anchors.reshape(( K * A, 4)).astype(np.float32, copy=False)
    length = np.int32(anchors.shape[0])

    return anchors, length