訓練的標註資料格式如下：

[
    {
        "name": "235_2_t20201127123021723_CAM2.jpg",
        "image_height": 6000,
        "image_width": 8192,
        "category": 5,
        "bbox": [
            1876.06,
            998.04,
            1883.06,
            1004.04
        ]
    },
    {
        "name": "235_2_t20201127123021723_CAM2.jpg
 
",
        "image_height": 6000,
        "image_width": 8192,
        "category": 5,
        "bbox": [
            1655.06,
            1094.04,
            1663.06,
            1102.04
        ]
    }
]

聚類anchorbox只需要 bbox 中的左上角與右下角的 x,y 資料

k-means 聚類程式碼：

import numpy as np
import json


def iou(box, clusters):
    
 
"""
   計算 IOU
    param:
        box: tuple or array, shifted to the origin (i. e. width and height)
        clusters: numpy array of shape (k, 2) where k is the number of clusters
    return:
        numpy array of shape (k, 0) where k is the number of clusters
    """
    x = np.minimum(clusters[:, 0], box[0])
    y 
 
= np.minimum(clusters[:, 1], box[1])
    if np.count_nonzero(x == 0) > 0 or np.count_nonzero(y == 0) > 0:
        raise ValueError("Box has no area")

    intersection = x * y
    box_area = box[0] * box[1]
    cluster_area = clusters[:, 0] * clusters[:, 1]

    iou_ = intersection / (box_area + cluster_area - intersection + 1e-10)

    return iou_


#  計算框的 numpy 陣列和 k 個簇之間的平均並集交集（IoU）。
def avg_iou(boxes, clusters):
    """
    param:
        boxes: numpy array of shape (r, 2), where r is the number of rows
        clusters: numpy array of shape (k, 2) where k is the number of clusters
    return:
        average IoU as a single float
    """
    return np.mean([np.max(iou(boxes[i], clusters)) for i in range(boxes.shape[0])])


# 將所有框轉換為原點。
def translate_boxes(boxes):
    """
    param:
        boxes: numpy array of shape (r, 4)
    return:
    numpy array of shape (r, 2)
    """
    new_boxes = boxes.copy()
    for row in range(new_boxes.shape[0]):
        new_boxes[row][2] = np.abs(new_boxes[row][2] - new_boxes[row][0])
        new_boxes[row][3] = np.abs(new_boxes[row][3] - new_boxes[row][1])
    return np.delete(new_boxes, [0, 1], axis=1)


# 使用聯合上的交集（IoU）度量計算k均值聚類。
def kmeans(boxes, k, dist=np.median):
    """
    param:
        boxes: numpy array of shape (r, 2), where r is the number of rows
        k: number of clusters
        dist: distance function
    return:
        numpy array of shape (k, 2)
    """
    rows = boxes.shape[0]

    distances = np.empty((rows, k))
    last_clusters = np.zeros((rows,))

    np.random.seed()

    # the Forgy method will fail if the whole array contains the same rows
    clusters = boxes[np.random.choice(rows, k, replace=False)]  # 初始化k個聚類中心（方法是從原始資料集中隨機選k個）

    while True:
        for row in range(rows):
            # 定義的距離度量公式：d(box,centroid)=1-IOU(box,centroid)。到聚類中心的距離越小越好，但IOU值是越大越好，所以使用 1 - IOU，這樣就保證距離越小，IOU值越大。
            distances[row] = 1 - iou(boxes[row], clusters)
        # 將標註框分配給“距離”最近的聚類中心（也就是這裡程式碼就是選出（對於每一個box）距離最小的那個聚類中心）。
        nearest_clusters = np.argmin(distances, axis=1)
        # 直到聚類中心改變數為0（也就是聚類中心不變了）。
        if (last_clusters == nearest_clusters).all():
            break
        # 更新聚類中心（這裡把每一個類的中位數作為新的聚類中心）
        for cluster in range(k):
            clusters[cluster] = dist(boxes[nearest_clusters == cluster], axis=0)

        last_clusters = nearest_clusters

    return clusters


# 讀取 json 檔案中的標註資料
def parse_anno(annotation_path):
    with open(annotation_path, 'r') as f:
        anno = json.load(f)
    result = []
    for line in anno:
        bbox = line['bbox']
        x_min, y_min, x_max, y_max = bbox[0], bbox[1], bbox[2], bbox[3]
        # 計算邊框的大小
        width = x_max - x_min
        height = y_max - y_min
        assert width > 0
        assert height > 0
        result.append([width, height])
    result = np.asarray(result)
    return result


def get_kmeans(anno, cluster_num=9):

    anchors = kmeans(anno, cluster_num)
    ave_iou = avg_iou(anno, anchors)

    anchors = anchors.astype('int').tolist()

    anchors = sorted(anchors, key=lambda x: x[0] * x[1])

    return anchors, ave_iou


if __name__ == '__main__':
    annotation_path = "tile_round1_train_20201231/train_annos.json"
    anno_result = parse_anno(annotation_path)

    anchors, ave_iou = get_kmeans(anno_result, 9)

    anchor_string = ''
    for anchor in anchors:
        anchor_string += '{},{}, '.format(anchor[0], anchor[1])
    anchor_string = anchor_string[:-2]

　　 print(f'anchors are: {anchor_string}')
　　 print(f'the average iou is: {ave_iou}')

每次執行的結果都會有點不大一樣

參考：https://blog.csdn.net/zuliang001/article/details/90551798