目标检测算法yolo anchors聚类(kmeans)生成

代码下载：https://github.com/pakaqiu/yolov3_simple
视频链接：https://www.bilibili.com/video/BV1MK4y1X74Q?p=1
yolo已经出到了第5代，在CV目标检测领域中yolo一直在速度和精度两者保持着很不错的性能，而且一代比一代更优秀，不得不服作者的良心大作。这段时间在研究yolo，发现anchors生成这块东西网上一堆的相关文章，但是没有多少实践可用，原理的东西就不说太多，以yolov3为主来说明，采用kmeans对目标物体的宽高进行聚类产生anchors用于后续的yolo训练；注意这里的宽高是目标物体相对原图的宽高。下面给出实现代码，代码来源于github，实现如下：

import numpy as np


class YOLO_Kmeans:

    def __init__(self, cluster_number, filename):
        self.cluster_number = cluster_number
        self.filename = filename

    def iou(self, boxes, clusters):  # 1 box -> k clusters
        n = boxes.shape[0]
        k = cluster_number

        box_area = boxes[:, 0] * boxes[:, 1]
        box_area = box_area.repeat(k)
        box_area = np.reshape(box_area, (n, k))

        cluster_area = clusters[:, 0] * clusters[:, 1]
        cluster_area = np.tile(cluster_area, [1, n])
        cluster_area = np.reshape(cluster_area, (n, k))

        box_w_matrix = np.reshape(boxes[:, 0].repeat(k), (n, k))
        cluster_w_matrix = np.reshape(np.tile(clusters[:, 0], (1, n)), (n, k))
        min_w_matrix = np.minimum(cluster_w_matrix, box_w_matrix)

        box_h_matrix = np.reshape(boxes[:, 1].repeat(k), (n, k))
        cluster_h_matrix = np.reshape(np.tile(clusters[:, 1], (1, n)), (n, k))
        min_h_matrix = np.minimum(cluster_h_matrix, box_h_matrix)
        inter_area = np.multiply(min_w_matrix, min_h_matrix)

        result = inter_area / (box_area + cluster_area - inter_area)
        return result

    def avg_iou(self, boxes, clusters):
        accuracy = np.mean([np.max(self.iou(boxes, clusters), axis=1)])
        return accuracy

    def kmeans(self, boxes, k, dist=np.median):
        box_number = boxes.shape[0]
        distances = np.empty((box_number, k))
        last_nearest = np.zeros((box_number,))
        np.random.seed()
        clusters = boxes[np.random.choice(
            box_number, k, replace=False)]  # init k clusters
        while True:

            distances = 1 - self.iou(boxes, clusters)

            current_nearest = np.argmin(distances, axis=1)
            if (last_nearest == current_nearest).all():
                break  # clusters won't change
            for cluster in range(k):
                clusters[cluster] = dist(  # update clusters
                    boxes[current_nearest == cluster], axis=0)

            last_nearest = current_nearest

        return clusters

    def result2txt(self, data):
        f = open("yolo_anchors.txt", 'w')
        row = np.shape(data)[0]
        for i in range(row):
            if i == 0:
                x_y = "%d,%d" % (data[i][0], data[i][1])
            else:
                x_y = ", %d,%d" % (data[i][0], data[i][1])
            f.write(x_y)
        f.close()



    def txt2boxes(self):
        f = open(self.filename, 'r')
        dataSet = []
        for line in f:
            infos = line.split(" ")
            length = len(infos)
            for i in range(1, length):
                width = int(infos[i].split(",")[2]) - \
                    int(infos[i].split(",")[0])
                height = int(infos[i].split(",")[3]) - \
                    int(infos[i].split(",")[1])
                dataSet.append([width, height])
        result = np.array(dataSet)
        f.close()
        return result


    def get_boxes(self): #根据自己的label方式读取box
        f = open(self.filename,'r')
        dataSet = []
        for line in f.readlines():
            line = line.strip().split(' ')
            line = line[1:]
            box = list(map(float,line))
            boxes = np.array(box,dtype = np.float32).reshape(-1,4)

            for b in boxes:
                width = int(b[2] - b[0])
                height = int(b[3] - b[1])
                dataSet.append([width,height])

        result = np.array(dataSet)
        f.close()

        return result


    def txt2clusters(self):
        #all_boxes = self.txt2boxes()
        all_boxes = self.get_boxes()
        result = self.kmeans(all_boxes, k=self.cluster_number)
        result = result[np.lexsort(result.T[0, None])]
        self.result2txt(result)
        print("K anchors:\n {}".format(result))
        print("Accuracy: {:.2f}%".format(
            self.avg_iou(all_boxes, result) * 100))


if __name__ == "__main__":
    cluster_number = 6
    filename = "boxes.txt"

    kmeans = YOLO_Kmeans(cluster_number, filename)
    kmeans.txt2clusters()

我的数据格式如下：

聚类结果：

[[ 20 19]
[ 35 32]
[ 48 46]
[ 73 65]
[117 110]
[216 206]]
Accuracy: 74.46%

不同的数据方式需要根据自己需求修改，希望可以帮助到大家，有不当之处请指教。
最后附上一个视频讲解b站跳转，初次做视频，不妥之处望谅解和指正，谢谢！