YOLOv2训练自己的数据来实现人脸检测详细步骤

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join

# sets=[(2012, train), (2012, val), (2007, train), (2007, val), (2007, test)]
sets = [(2017, train)]

# classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
classes = ["Face"]


def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = (box[0] + box[1]) / 2.0 - 1
    y = (box[2] + box[3]) / 2.0 - 1
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return (x, y, w, h)


def convert_annotation(year, image_id):
    in_file = open(VOCdevkit/VOC%s/Annotations/%s.xml % (year, image_id))
    out_file = open(VOCdevkit/VOC%s/labels/%s.txt % (year, image_id), w)
    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find(size)
    w = int(size.find(width).text)
    h = int(size.find(height).text)

    for obj in root.iter(object):
        difficult = 100
        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 = (float(xmlbox.find(xmin).text), float(xmlbox.find(xmax).text), float(xmlbox.find(ymin).text),
             float(xmlbox.find(ymax).text))
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + 
)


wd = getcwd()

for year, image_set in sets:
    if not os.path.exists(VOCdevkit/VOC%s/labels/ % (year)):
        os.makedirs(VOCdevkit/VOC%s/labels/ % (year))
    image_ids = open(VOCdevkit/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/VOCdevkit/VOC%s/JPEGImages/%s.jpg
 % (wd, year, image_id))
        convert_annotation(year, image_id)
    list_file.close()

四、修改YOLOv2相关配置文件 （1）在darknet-masterdata 下新建 obj.data和obj.names 两个文件。 obj.data内容如下，classes=1，train等于上文2017_train.txt文件的绝对路径。obj.names里面只写一个Face

classes= 1
train  = D:/yoloV2/darknet/scripts/2017_train.txt
names = data/obj.names
backup = D:/yoloV2/darknet/result/

（2）拷贝cfg文件夹下的yolo-voc.2.0.cfg，重命名为yolo-obj.cfg，修改里面的一些内容： 五、开始训练 编写.cmd文件，下载官网的预训练模型darknet.conv.weights做初始化，训练命令为如下（注意路径）：

D:yoloV2darknetuilddarknetx64darknet.exe detector train ./data/obj.data yolo-obj.cfg darknet19_448.conv.23

六、测试 在result文件中保存了权重文件，如：yolo-obj_500.weights 编写测试命令：

D:yoloV2darknetuilddarknetx64darknet.exe detector test ./data/obj.data yolo-obj.cfg ./result/yolo-obj_500.weights -i 0 -thresh 0.1  ./data/Face/1.jpg

pause