学习mask rcnn，day4（fpn层与特征提取框）

FPN层

# Image size must be dividable by 2 multiple times
        h, w = config.IMAGE_SHAPE[:2]
        #要先做一个判断，因为要做卷积之类的必须要二的所少次幂形式才可以
        if h / 2**6 != int(h / 2**6) or w / 2**6 != int(w / 2**6):
            raise Exception("Image size must be dividable by 2 at least 6 times "
                            "to avoid fractions when downscaling and upscaling."
                            "For example, use 256, 320, 384, 448, 512, ... etc. ")

        # Inputs
        input_image = KL.Input(
            shape=config.IMAGE_SHAPE.tolist(), name="input_image")
        input_image_meta = KL.Input(shape=[None], name="input_image_meta")
        if mode == "training":
            # RPN GT
            #损失函数的所有标签
            input_rpn_match = KL.Input(
                shape=[None, 1], name="input_rpn_match", dtype=tf.int32)
            input_rpn_bbox = KL.Input(
                shape=[None, 4], name="input_rpn_bbox", dtype=tf.float32)

            # Detection GT (class IDs, bounding boxes, and masks)
            # 1. GT Class IDs (zero padded)
            input_gt_class_ids = KL.Input(
                shape=[None], name="input_gt_class_ids", dtype=tf.int32)
            # 2. GT Boxes in pixels (zero padded)
            # [batch, MAX_GT_INSTANCES, (y1, x1, y2, x2)] in image coordinates
            input_gt_boxes = KL.Input(
                shape=[None, 4], name="input_gt_boxes", dtype=tf.float32)
            # Normalize coordinates
            #做归一化后所有坐标都在0-1之间
            h, w = K.shape(input_image)[1], K.shape(input_image)[2]
            image_scale = K.cast(K.stack([h, w, h, w], axis=0), tf.float32)
            gt_boxes = KL.Lambda(lambda x: x / image_scale)(input_gt_boxes)
            # 3. GT Masks (zero padded)
            # [batch, height, width, MAX_GT_INSTANCES]
            if config.USE_MINI_MASK:
                input_gt_masks = KL.Input(
                    shape=[config.MINI_MASK_SHAPE[0],
                           config.MINI_MASK_SHAPE[1], None],
                    name="input_gt_masks", dtype=bool)
            else:
                input_gt_masks = KL.Input(
                    shape=[config.IMAGE_SHAPE[0], config.IMAGE_SHAPE[1], None],
                    name="input_gt_masks", dtype=bool)

        # Build the shared convolutional layers.
        # Bottom-up Layers
        # Returns a list of the last layers of each stage, 5 in total.
        # Don't create the thead (stage 5), so we pick the 4th item in the list.
        _, C2, C3, C4, C5 = resnet_graph(input_image, config.BACKBONE, stage5=True)  #残差网络
        # Top-down Layers，自顶向下来完成
        # TODO: add assert to varify feature map sizes match what's in config
        P5 = KL.Conv2D(256, (1, 1), name='fpn_c5p5')(C5)  
        P4 = KL.Add(name="fpn_p4add")([
            KL.UpSampling2D(size=(2, 2), name="fpn_p5upsampled")(P5),
            KL.Conv2D(256, (1, 1), name='fpn_c4p4')(C4)])#p5进行了上采样和进过卷积后的自己相加
        P3 = KL.Add(name="fpn_p3add")([
            KL.UpSampling2D(size=(2, 2), name="fpn_p4upsampled")(P4),
            KL.Conv2D(256, (1, 1), name='fpn_c3p3')(C3)])
        P2 = KL.Add(name="fpn_p2add")([
            KL.UpSampling2D(size=(2, 2), name="fpn_p3upsampled")(P3),
            KL.Conv2D(256, (1, 1), name='fpn_c2p2')(C2)])
        # Attach 3x3 conv to all P layers to get the final feature maps.
        P2 = KL.Conv2D(256, (3, 3), padding="SAME", name="fpn_p2")(P2)
        P3 = KL.Conv2D(256, (3, 3), padding="SAME", name="fpn_p3")(P3)
        P4 = KL.Conv2D(256, (3, 3), padding="SAME", name="fpn_p4")(P4)
        P5 = KL.Conv2D(256, (3, 3), padding="SAME", name="fpn_p5")(P5)
        #对刚刚融合的几个图再进行卷积提取特征
        # P6 is used for the 5th anchor scale in RPN. Generated by
        # subsampling from P5 with stride of 2.
        P6 = KL.MaxPooling2D(pool_size=(1, 1), strides=2, name="fpn_p6")(P5)

        # Note that P6 is used in RPN, but not in the classifier heads.
        rpn_feature_maps = [P2, P3, P4, P5, P6]
        mrcnn_feature_maps = [P2, P3, P4, P5]

特征提取框

def generate_anchors(scales, ratios, shape, feature_stride, anchor_stride):
    """
    scales: 1D array of anchor sizes in pixels. Example: [32, 64, 128]框的大小
    ratios: 1D array of anchor ratios of width/height. Example: [0.5, 1, 2]长宽的比例
    shape: [height, width] spatial shape of the feature map over which
            to generate anchors.特征图的大小
    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     也就是说每个特征点会形成三个候选框
    box_widths, box_centers_x = np.meshgrid(widths, shifts_x)
    box_heights, box_centers_y = np.meshgrid(heights, shifts_y)

    # Reshape to get a list of (y, x) and a list of (h, w)
    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)
    return boxes