yolo_v3训练自己的模型（人脸及deep-sort)（或自己数据集）

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

import xml.etree.ElementTree as ET
from os import getcwd

import sys
sys.path.append("/var/Data/pcr/ljf/project/rubbish_faster_rcnn/data/VOCself")
print(sys.path)
root_data="/var/Data/pcr/ljf/project/rubbish_faster_rcnn/data/"
sets=[('self', 'train'), ('self', 'val'), ('self', 'test')]

classes = ["trash"]


def convert_annotation(year, image_id, list_file):
    in_file = open(root_data+'VOC%s/Annotations/%s.xml'%(year, image_id))
    tree=ET.parse(in_file)
    root = tree.getroot()

    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult)==1:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (int(xmlbox.find('xmin').text), int(xmlbox.find('ymin').text), int(xmlbox.find('xmax').text), int(xmlbox.find('ymax').text))
        list_file.write(" " + ",".join([str(a) for a in b]) + ',' + str(cls_id))

wd = getcwd()

for year, image_set in sets:
    image_ids = open(root_data+'VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
    list_file = open('%s_%s.txt'%(year, image_set), 'w')
    for image_id in image_ids:
        # list_file.write('%s/VOC%s/JPEGImages/%s.jpg' % (wd, year, image_id))
        list_file.write('%sVOC%s/JPEGImages/%s.jpg'%(root_data, year, image_id))
        convert_annotation(year, image_id, list_file)
        list_file.write('
')
    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

import numpy as np


class YOLO_Kmeans:

    def __init__(self, cluster_number, filename):
        self.cluster_number = cluster_number
        self.filename = r"./self_train.txt"

    def iou(self, boxes, clusters):  # 1 box -> k clusters
        n = boxes.shape[0]
        k = self.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(" ")
            print(infos)
            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()
        print(all_boxes)
        result = self.kmeans(all_boxes, k=self.cluster_number)
        result = result[np.lexsort(result.T[0, None])]
        self.result2txt(result)
        print("K anchors:
 {}".format(result))
        print("Accuracy: {:.2f}%".format(
            self.avg_iou(all_boxes, result) * 100))


if __name__ == "__main__":
    cluster_number = 9
    filename = r"../self_trainval.txt"
    kmeans = YOLO_Kmeans(cluster_number, filename)
    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