『計算機視覺』Mask-RCNN_錨框生成

時間 2019-11-08

原文原文鏈接

1、和SSD錨框對比

Mask_RCNN的錨框本質上來講和SSD的是同樣的（『TensorFlow』SSD源碼學習_其三：錨框生成），python

中心點的個數等於特徵層像素數ios

框體生成是圍繞中心點的git

最終的框體座標須要歸一化到01之間，都是對於輸入圖片的相對大小github

RCNN系列通常都是一個共享特徵，但在Mask_RCNN結構引入了FPN結構後，和SSD同樣，使用了多層特徵，這樣二者的錨框生成算法能夠說是一模一樣了，只不過是生成策略有所微調：算法

SSD中不一樣特徵層對應着不一樣的網格加強比例參數；Mask_RCNN不通層的比例（anchor_ratios）則徹底一致網絡

SSD每一層每個中心點生成該層ratio+2個框；Mask_RCNN生成固定3個框app

SSD中心點爲feat像素偏移0.5步長；Mask_RCNN中心點直接選爲feat像素位置ide

而基本生成方式二者徹底一致：函數

h乘anchor_ratios**0.5
w除anchor_ratios**0.5

h、w初始值爲給定的參考尺寸，即感覺野控制實際依賴的參數爲每一層的anchor_ratios和參考尺寸，對SSD：

anchor_sizes=[(21., 45.), (45., 99.), (99., 153.), (153., 207.), (207., 261.), (261., 315.)]
anchor_ratios=[[2, .5], [2, .5, 3, 1./3], [2, .5, 3, 1./3], [2, .5, 3, 1./3], [2, .5], [2, .5]]

對Mask_RCNN（h、w參考尺寸大小一致）:

self.config.BACKBONE_STRIDES  = [4, 8, 16, 32, 64]      # 特徵層的下采樣倍數，中心點計算使用
self.config.RPN_ANCHOR_RATIOS = [0.5, 1, 2]             # 特徵層錨框生成參數
self.config.RPN_ANCHOR_SCALES = [32, 64, 128, 256, 512] # 特徵層錨框感覺野

2、錨框生成

錨框生成入口函數位於model.py中的get_anchor函數，須要參數image_shape，保證含有[h, w]便可，也能夠包含[h, w, c]，

    def get_anchors(self, image_shape):
        """Returns anchor pyramid for the given image size."""
        # [N, (height, width)]
        backbone_shapes = compute_backbone_shapes(self.config, image_shape)
        # Cache anchors and reuse if image shape is the same
        if not hasattr(self, "_anchor_cache"):
            self._anchor_cache = {}
        if not tuple(image_shape) in self._anchor_cache:
            # Generate Anchors: [anchor_count, (y1, x1, y2, x2)]
            a = utils.generate_pyramid_anchors(
                self.config.RPN_ANCHOR_SCALES,  # (32, 64, 128, 256, 512)
                self.config.RPN_ANCHOR_RATIOS,  # [0.5, 1, 2]
                backbone_shapes,                # with shape [N, (height, width)]
                self.config.BACKBONE_STRIDES,   # [4, 8, 16, 32, 64]
                self.config.RPN_ANCHOR_STRIDE)  # 1
            # Keep a copy of the latest anchors in pixel coordinates because
            # it's used in inspect_model notebooks.
            # TODO: Remove this after the notebook are refactored to not use it
            self.anchors = a
            # Normalize coordinates
            self._anchor_cache[tuple(image_shape)] = utils.norm_boxes(a, image_shape[:2])
        return self._anchor_cache[tuple(image_shape)]

調用函數compute_backbone_shapes計算各個特徵層shape：

def compute_backbone_shapes(config, image_shape):
    """Computes the width and height of each stage of the backbone network.

    Returns:
        [N, (height, width)]. Where N is the number of stages
    """
    if callable(config.BACKBONE):
        return config.COMPUTE_BACKBONE_SHAPE(image_shape)

    # Currently supports ResNet only
    assert config.BACKBONE in ["resnet50", "resnet101"]
    return np.array(
        [[int(math.ceil(image_shape[0] / stride)),
            int(math.ceil(image_shape[1] / stride))]
            for stride in config.BACKBONE_STRIDES])  # [4, 8, 16, 32, 64]

調用函數utils.generate_pyramid_anchors生成所有錨框：

def generate_pyramid_anchors(scales, ratios, feature_shapes, feature_strides,
                             anchor_stride):
    """Generate anchors at different levels of a feature pyramid. Each scale
    is associated with a level of the pyramid, but each ratio is used in
    all levels of the pyramid.

    Returns:
    anchors: [N, (y1, x1, y2, x2)]. All generated anchors in one array. Sorted
        with the same order of the given scales. So, anchors of scale[0] come
        first, then anchors of scale[1], and so on.
    """
    # Anchors
    # [anchor_count, (y1, x1, y2, x2)]
    anchors = []
    for i in range(len(scales)):
        anchors.append(generate_anchors(scales[i],
                                        ratios,
                                        feature_shapes[i],
                                        feature_strides[i],
                                        anchor_stride))
    # [anchor_count, (y1, x1, y2, x2)]
    return np.concatenate(anchors, axis=0)

utils.generate_pyramid_anchors會調用utils.generate_anchors來生成每一層的錨框（這一步較多的使用了函數meshgrid，介紹見『Numpy』np.meshgrid）：

def generate_anchors(scales, ratios, shape, feature_stride, anchor_stride):
    """
    scales: 1D array of anchor sizes in pixels. Example: [32, 64, 128]
    ratios: 1D array of anchor ratios of width/height. Example: [0.5, 1, 2]
    shape: [height, width] spatial shape of the feature map over which
            to generate anchors.
    feature_stride: Stride of the feature map relative to the image in pixels.
    anchor_stride: Stride of anchors on the feature map. For example, if the
        value is 2 then generate anchors for every other feature map pixel.
    """
    # Get all combinations of scales and ratios
    scales, ratios = np.meshgrid(np.array(scales), np.array(ratios))
    scales = scales.flatten()
    ratios = ratios.flatten()

    # Enumerate heights and widths from scales and ratios
    heights = scales / np.sqrt(ratios)
    widths = scales * np.sqrt(ratios)

    # Enumerate shifts in feature space
    shifts_y = np.arange(0, shape[0], anchor_stride) * feature_stride
    shifts_x = np.arange(0, shape[1], anchor_stride) * feature_stride
    shifts_x, shifts_y = np.meshgrid(shifts_x, shifts_y)

    # Enumerate combinations of shifts, widths, and heights
    box_widths, box_centers_x = np.meshgrid(widths, shifts_x)    # (n, 3) (n, 3)
    box_heights, box_centers_y = np.meshgrid(heights, shifts_y)  # (n, 3) (n, 3)

    # Reshape to get a list of (y, x) and a list of (h, w)
    # (n, 3, 2) -> (3n, 2)
    box_centers = np.stack([box_centers_y, box_centers_x], axis=2).reshape([-1, 2])
    box_sizes = np.stack([box_heights, box_widths], axis=2).reshape([-1, 2])

    # Convert to corner coordinates (y1, x1, y2, x2)
    boxes = np.concatenate([box_centers - 0.5 * box_sizes,
                            box_centers + 0.5 * box_sizes], axis=1)
    # 框體信息是相對於原圖的, [N, (y1, x1, y2, x2)]
    return boxes

模擬某層的中心點分佈

最後回到get_anchor，調用utils.norm_boxes將錨框座標化爲01之間：

def norm_boxes(boxes, shape):
    """Converts boxes from pixel coordinates to normalized coordinates.
    boxes: [N, (y1, x1, y2, x2)] in pixel coordinates
    shape: [..., (height, width)] in pixels

    Note: In pixel coordinates (y2, x2) is outside the box. But in normalized
    coordinates it's inside the box.

    Returns:
        [N, (y1, x1, y2, x2)] in normalized coordinates
    """
    h, w = shape
    scale = np.array([h - 1, w - 1, h - 1, w - 1])
    shift = np.array([0, 0, 1, 1])
    return np.divide((boxes - shift), scale).astype(np.float32)

最終返回相對座標下的錨框，shape：[anchor_count, (y1, x1, y2, x2)]。