YOLOV3中关于k-means算法计算聚类中心具体实现方法
首先贴一份资料https://blog.csdn.net/zxyhhjs2017/article/details/83012425，相信大家都应该看过，但是yolov3的代码中并没有使用其中讲解的k-means++算法，而是使用k-means，应为所要得到的n个聚类中心是直接在box中随机选取，然后更新聚类中心。
接下来，附上代码分析！
import numpy as np
class YOLO_Kmeans:
def __init__(self, cluster_number, filename):
self.cluster_number = cluster_number
self.filename = "kmeans.txt"
def iou(self, boxes, clusters): # 1 box -> k clusters
n = boxes.shape[0]
k = self.cluster_number
#把box_area整理成n行k列的形式
box_area = boxes[:, 0] * boxes[:, 1]
box_area = box_area.repeat(k)
box_area = np.reshape(box_area, (n, k))
#把cluster_area整理成n行k列的形式
cluster_area = clusters[:, 0] * clusters[:, 1]
cluster_area = np.tile(cluster_area, [1, n])
cluster_area = np.reshape(cluster_area, (n, k))
#把box和cluster的宽都整理成n行k列的形式，并把两者做比较，最后还是一个n行k列的形式，这个 过程其实在比较box和两个cluster的宽，并选出小的
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)
# 把box和cluster的高都整理成n行k列的形式，并把两者做比较，最后还是一个n行k列的形式，这个过程其实在比较box和两个cluster的高，并选出小的
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)
#把小的宽和高相乘
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)
#distance是一个n行k列的小于1的数组，比较每一行提出来最小的一个，意义是每行中选出一个最合适的聚类中心，比如第一个box和第3个距离最小，第二个和第4个聚类中心距离最小。。。。。。[3,4,5,0,1,。。。。。。。4]
current_nearest = np.argmin(distances, axis=1)
print((last_nearest == current_nearest))
if (last_nearest == current_nearest).all():
break # clusters won't change
#难点是更换中心
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 txt2clusters(self):
all_boxes = self.txt2boxes()
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 = 3
filename = "train.txt"
kmeans = YOLO_Kmeans(cluster_number, filename)
kmeans.txt2clusters()