做deep-sort多目标跟踪需要结合yolo_v3进行检测行人
由于我的项目中需要对人脸进行检测，所以需要训练针对人脸的模型
训练样本是来自WIDER-FACE人脸库。(有3w+的图片和标注框)
deep-sort结合yolo-v3的博客分享
https://blog.csdn.net/weixin_42755375/article/details/85723239
分享一篇博客(按照博客要求 可以完美训练自己的人脸模型)
https://blog.csdn.net/caroline_wendy/article/details/80924371
图一 使用原始模型， 图二使用新训练人脸模型
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
如果不是使用人脸数据，而是自己的数据或voc格式数据，步骤其实差不多，只是得到train.txt的过程不一样，这里给出方法。
首先需要得到train.txt的py文件 voc_annotation.py
1 import xml.etree.ElementTree as ET
2 from os import getcwd
3
4 import sys
5 sys.path.append("/var/Data/pcr/ljf/project/rubbish_faster_rcnn/data/VOCself")
6 print(sys.path)
7 root_data="/var/Data/pcr/ljf/project/rubbish_faster_rcnn/data/"
8 sets=[('self', 'train'), ('self', 'val'), ('self', 'test')]
9
10 classes = ["trash"]
11
12
13 def convert_annotation(year, image_id, list_file):
14 in_file = open(root_data+'VOC%s/Annotations/%s.xml'%(year, image_id))
15 tree=ET.parse(in_file)
16 root = tree.getroot()
17
18 for obj in root.iter('object'):
19 difficult = obj.find('difficult').text
20 cls = obj.find('name').text
21 if cls not in classes or int(difficult)==1:
22 continue
23 cls_id = classes.index(cls)
24 xmlbox = obj.find('bndbox')
25 b = (int(xmlbox.find('xmin').text), int(xmlbox.find('ymin').text), int(xmlbox.find('xmax').text), int(xmlbox.find('ymax').text))
26 list_file.write(" " + ",".join([str(a) for a in b]) + ',' + str(cls_id))
27
28 wd = getcwd()
29
30 for year, image_set in sets:
31 image_ids = open(root_data+'VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
32 list_file = open('%s_%s.txt'%(year, image_set), 'w')
33 for image_id in image_ids:
34 # list_file.write('%s/VOC%s/JPEGImages/%s.jpg' % (wd, year, image_id))
35 list_file.write('%sVOC%s/JPEGImages/%s.jpg'%(root_data, year, image_id))
36 convert_annotation(year, image_id, list_file)
37 list_file.write('\n')
38 list_file.close()
注意：一开始VOC2007，也可以叫VOC2008之类，这样此处的txt就会成为2008_xxx.txt。此外，有一个很关键的地方需要注意，必须修改，不然此处生成的三个新的txt文件中仅仅比前面Main下的txt中多了图片路径而已，并不包含框box的信息，这样的话在后面的训练步骤，由于没有框的信息，仅仅是图片路径和名称信息，是训练不好的，即使可以得到训练后的h5文件，但是当用这样的h5文件去执行类似前面所说的测试图片识别，效果就是将整幅图框住，而不是框住你所要识别的部分。
故所要做的是：在执行voc_annotation.py之前，打开它，进行修改。将其中最上面的sets改为你自己的，比如2012改为我得2007，要和前面的目录年份保持一致。还需要将最上面的classes中的内容，改为你自己xml文件中object属性中name属性的值。你有哪些name值，就改为哪些，不然其中读取xml框信息的代码就不会执行。
-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
最后是anchor值得获取，在训练自己得数据集时，不同的数据集有不同的anchor值，为9对数字。
在得到上一步的train.txt的基础上， 使用kmeans.py文件就可以得到anchor值
1 import numpy as np
2
3
4 class YOLO_Kmeans:
5
6 def __init__(self, cluster_number, filename):
7 self.cluster_number = cluster_number
8 self.filename = r"./self_train.txt"
9
10 def iou(self, boxes, clusters): # 1 box -> k clusters
11 n = boxes.shape[0]
12 k = self.cluster_number
13
14 box_area = boxes[:, 0] * boxes[:, 1]
15 box_area = box_area.repeat(k)
16 box_area = np.reshape(box_area, (n, k))
17
18 cluster_area = clusters[:, 0] * clusters[:, 1]
19 cluster_area = np.tile(cluster_area, [1, n])
20 cluster_area = np.reshape(cluster_area, (n, k))
21
22 box_w_matrix = np.reshape(boxes[:, 0].repeat(k), (n, k))
23 cluster_w_matrix = np.reshape(np.tile(clusters[:, 0], (1, n)), (n, k))
24 min_w_matrix = np.minimum(cluster_w_matrix, box_w_matrix)
25
26 box_h_matrix = np.reshape(boxes[:, 1].repeat(k), (n, k))
27 cluster_h_matrix = np.reshape(np.tile(clusters[:, 1], (1, n)), (n, k))
28 min_h_matrix = np.minimum(cluster_h_matrix, box_h_matrix)
29 inter_area = np.multiply(min_w_matrix, min_h_matrix)
30
31 result = inter_area / (box_area + cluster_area - inter_area)
32 return result
33
34 def avg_iou(self, boxes, clusters):
35 accuracy = np.mean([np.max(self.iou(boxes, clusters), axis=1)])
36 return accuracy
37
38 def kmeans(self, boxes, k, dist=np.median):
39 box_number = boxes.shape[0]
40 distances = np.empty((box_number, k))
41 last_nearest = np.zeros((box_number,))
42 np.random.seed()
43 clusters = boxes[np.random.choice(
44 box_number, k, replace=False)] # init k clusters
45 while True:
46
47 distances = 1 - self.iou(boxes, clusters)
48
49 current_nearest = np.argmin(distances, axis=1)
50 if (last_nearest == current_nearest).all():
51 break # clusters won't change
52 for cluster in range(k):
53 clusters[cluster] = dist( # update clusters
54 boxes[current_nearest == cluster], axis=0)
55
56 last_nearest = current_nearest
57
58 return clusters
59
60 def result2txt(self, data):
61 f = open("yolo_anchors.txt", 'w')
62 row = np.shape(data)[0]
63 for i in range(row):
64 if i == 0:
65 x_y = "%d,%d" % (data[i][0], data[i][1])
66 else:
67 x_y = ", %d,%d" % (data[i][0], data[i][1])
68 f.write(x_y)
69 f.close()
70
71 def txt2boxes(self):
72 f = open(self.filename, 'r')
73 dataSet = []
74 for line in f:
75 infos = line.split(" ")
76 print(infos)
77 length = len(infos)
78 for i in range(1, length):
79 width = int(infos[i].split(",")[2]) - \
80 int(infos[i].split(",")[0])
81 height = int(infos[i].split(",")[3]) - \
82 int(infos[i].split(",")[1])
83 dataSet.append([width, height])
84 result = np.array(dataSet)
85 f.close()
86 return result
87
88 def txt2clusters(self):
89 all_boxes = self.txt2boxes()
90 print(all_boxes)
91 result = self.kmeans(all_boxes, k=self.cluster_number)
92 result = result[np.lexsort(result.T[0, None])]
93 self.result2txt(result)
94 print("K anchors:\n {}".format(result))
95 print("Accuracy: {:.2f}%".format(
96 self.avg_iou(all_boxes, result) * 100))
97
98
99 if __name__ == "__main__":
100 cluster_number = 9
101 filename = r"../self_trainval.txt"
102 kmeans = YOLO_Kmeans(cluster_number, filename)
103 kmeans.txt2clusters()
使用方法：修改第8行 self.filename的值为自己得到的train.txt文件
最后如下 anchor为
[25 14]
[33 20]
[38 27]
[45 34]
[55 24]
[58 37]
[67 48]
[92 34]
[98 63]
参考：https://blog.csdn.net/m0_37857151/article/details/81330699