win10下用yolov3训练WiderFace数据集来实现人脸检测（TensorFlow版本，darkface作为测试集）

Posted 2023-02-28 告白少年

数据集准备工作

• 训练集 Wider Face格式转换
  下载人脸数据集wider face，解压到同一个文件夹下
  
  在同一个目录下，新建convert.py文件（把下面程序放入）运行程序得到图像和其对应的xml文件。

# -*- coding: utf-8 -*-

import shutil
import random
import os
import string
from skimage import io

headstr = """\\
<annotation>
    <folder>VOC2012</folder>
    <filename>%06d.jpg</filename>
    <source>
        <database>My Database</database>
        <annotation>PASCAL VOC2012</annotation>
        <image>flickr</image>
        <flickrid>NULL</flickrid>
    </source>
    <owner>
        <flickrid>NULL</flickrid>
        <name>company</name>
    </owner>
    <size>
        <width>%d</width>
        <height>%d</height>
        <depth>%d</depth>
    </size>
    <segmented>0</segmented>
"""
objstr = """\\
    <object>
        <name>%s</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>%d</xmin>
            <ymin>%d</ymin>
            <xmax>%d</xmax>
            <ymax>%d</ymax>
        </bndbox>
    </object>
"""

tailstr = '''\\
</annotation>
'''




def writexml(idx, head, bbxes, tail):
    filename = ("Annotations/%06d.xml" % (idx))
    f = open(filename, "w")
    f.write(head)
    for bbx in bbxes:
        f.write(objstr % ('face', bbx[0], bbx[1], bbx[0] + bbx[2], bbx[1] + bbx[3]))
    f.write(tail)
    f.close()


def clear_dir():
    if shutil.os.path.exists(('Annotations')):
        shutil.rmtree(('Annotations'))
    if shutil.os.path.exists(('ImageSets')):
        shutil.rmtree(('ImageSets'))
    if shutil.os.path.exists(('JPEGImages')):
        shutil.rmtree(('JPEGImages'))

    shutil.os.mkdir(('Annotations'))
    shutil.os.makedirs(('ImageSets/Main'))
    shutil.os.mkdir(('JPEGImages'))


def excute_datasets(idx, datatype):

    f = open(('ImageSets/Main/' + datatype + '.txt'), 'a')
    f_bbx = open(('wider_face_split/wider_face_' + datatype + '_bbx_gt.txt'), 'r')

    while True:
        filename = f_bbx.readline().strip('\\n')

        if not filename:
            break


        im = io.imread(('WIDER_' + datatype + '/images/' + filename))
        head = headstr % (idx, im.shape[1], im.shape[0], im.shape[2])
        nums = f_bbx.readline().strip('\\n')
        bbxes = []
        if nums=='0':
            bbx_info= f_bbx.readline()
            continue
        for ind in range(int(nums)):
            bbx_info = f_bbx.readline().strip(' \\n').split(' ')
            bbx = [int(bbx_info[i]) for i in range(len(bbx_info))]
            # x1, y1, w, h, blur, expression, illumination, invalid, occlusion, pose
            if bbx[7] == 0:
                bbxes.append(bbx)
        writexml(idx, head, bbxes, tailstr)
        shutil.copyfile(('WIDER_' + datatype + '/images/' + filename), ('JPEGImages/%06d.jpg' % (idx)))
        f.write('%06d\\n' % (idx))
        idx += 1
    f.close()
    f_bbx.close()
    return idx


if __name__ == '__main__':
    clear_dir()
    idx = 1
    idx = excute_datasets(idx, 'train')
    idx = excute_datasets(idx, 'val')
    print('Complete...')

运行后得到以下的文件（训练会重新打乱，所以只需要管Annotations，JPEGImages两个文件夹）：

Annotations：存放图像对应的xml
ImageSets：包含train.txt ,val.txt（分别包含对应的图像名字）
JPEGImages：存放图像

• 测试集Dark Face格式转换
  （若只用WilderFace作为训练集，测试集，忽略这一步）
  下载夜间人脸数据集Dark Face,我使用的是它的训练集6000张图像作为测试。
  运行下面的程序得到图像和对应的xml文件。

# -*- coding: utf-8 -*-
import os,shutil
import cv2
from lxml.etree import Element, SubElement, tostring
def txt_xml(img_path,img_name,txt_path,img_txt,xml_path,img_xml):
    clas = []
    img=cv2.imread(os.path.join(img_path,img_name))
    imh, imw = img.shape[0:2]
    txt_img=os.path.join(txt_path,img_txt)
    with open(txt_img,"r") as f:
        next(f)
        for line in f.readlines():
            line = line.strip('\\n')
            list = line.split(" ")
            print(list)
            clas.append(list)
    node_root = Element('annotation')
    node_folder = SubElement(node_root, 'folder')
    node_folder.text = '1'
    node_filename = SubElement(node_root, 'filename')
    #图像名称
    node_filename.text = img_name
    node_size = SubElement(node_root, 'size')
    node_width = SubElement(node_size, 'width')
    node_width.text = str(imw)
    node_height = SubElement(node_size, 'height')
    node_height.text = str(imh)
    node_depth = SubElement(node_size, 'depth')
    node_depth.text = '3'
    for i in range(len(clas)):
        node_object = SubElement(node_root, 'object')
        node_name = SubElement(node_object, 'name')
        node_name.text = "face"
        node_pose=SubElement(node_object, 'pose')
        node_pose.text="Unspecified"
        node_truncated=SubElement(node_object, 'truncated')
        node_truncated.text="truncated"
        node_difficult = SubElement(node_object, 'difficult')
        node_difficult.text = '0'
        node_bndbox = SubElement(node_object, 'bndbox')
        node_xmin = SubElement(node_bndbox, 'xmin')
        node_xmin.text = str(clas[i][0])
        node_ymin = SubElement(node_bndbox, 'ymin')
        node_ymin.text = str(clas[i][1])
        node_xmax = SubElement(node_bndbox, 'xmax')
        node_xmax.text = str(clas[i][2])
        node_ymax = SubElement(node_bndbox, 'ymax')
        node_ymax.text = str(clas[i][3])
    xml = tostring(node_root, pretty_print=True)  # 格式化显示，该换行的换行
    img_newxml = os.path.join(xml_path, img_xml)
    file_object = open(img_newxml, 'wb')
    file_object.write(xml)
    file_object.close()

if __name__ == "__main__":
    #图像文件夹所在位置
    img_path = r"E:\\BaiduNetdiskDownload\\DarkFace_Train_new\\images"
    #标注文件夹所在位置
    txt_path=r"E:\\BaiduNetdiskDownload\\DarkFace_Train_new\\label"
    #txt转化成xml格式后存放的文件夹
    xml_path=r"E:\\BaiduNetdiskDownload\\DarkFace_Train_new\\xml"
    for img_name in os.listdir(img_path):
        print(img_name)
        img_xml=img_name.split(".")[0]+".xml"
        img_txt=img_name.split(".")[0]+".txt"
        txt_xml(img_path, img_name, txt_path, img_txt,xml_path, img_xml)

yolov3训练

• 下载训练代码和预训练模型，并搭建好环境
  项目代码：tensorflow-serving-yolov3
  基于vgg的coco预训练模型百度云地址，密码：vw9x
• 把预训练模型解压到项目的checkpoint文件夹下，然后运行convert_weight.py，得到yolov3_coco_demo.ckpt模型
• 修改vis.names里的内容，只添加face这一个类别
• 把tensorflow-serving-yolov3/VOC2007/文件夹下的Annotations，JPEGImages两个文件夹换成第一步生成的wilderface的文件夹，接着修改split.py的60行内容

fi = open('./data/classes/voc.names', 'r')
修改为
fi = open('./data/classes/vis.names', 'r')

运行split.py，根目录下得到以下三个文件：

• 修改core/config.py的以下内容：

__C.TRAIN.BATCH_SIZE  = 2#根据自己电脑情况自行修改
__C.YOLO.CLASSES = "./data/classes/vis.names"
__C.YOLO.ORIGINAL_WEIGHT  = "./checkpoint/yolov3_coco_demo.ckpt"
__C.YOLO.DEMO_WEIGHT  = "./checkpoint/yolov3_coco_demo.ckpt"
__C.TRAIN.FISRT_STAGE_EPOCHS    = 20#根据自己需要自行修改
__C.TRAIN.SECOND_STAGE_EPOCHS   = 30
__C.TRAIN.INITIAL_WEIGHT  = "./checkpoint/yolov3_coco_demo.ckpt"

• 运行train.py进行训练
• 运行convert_weight.py保存模型

评估阶段

• 我用的是darkface的训练集全部作为测试，复制voc2007文件夹并重命名为DARK_face，并把Annotations，JPEGImages两个文件夹替换成darkface的xml和图像（这一步就是为生成YOLOv3所需要格式做准备）
• 修改split.py的内容

# -*- coding：utf-8 -*-
# split.py
from __future__ import division
import xml.etree.ElementTree as ET
import random
import os

def base_txt():
    saveBasePath = r"./DARK_face/ImageSets"              # txt文件保存目录
    total_xml = os.listdir(r'./DARK_face/Annotations')   # 获取标注文件（file_name.xml）

    # 划分数据集为（训练，验证，测试集 = 49%,20%,30%）

    val_percent =0                             # 可以自己修改
    test_percent = 1
    trainval_percent = 0

    # print(trainval_percent)

    tv = int(len(total_xml) * trainval_percent)
    #tr = int(len(total_xml) * train_percent)
    ta = int(tv * val_percent)
    tr = int(tv -ta)
    tt = int(len(total_xml) * test_percent)

    # 打乱训练文件（洗牌）
    trainval = random.sample(range(len(total_xml)), tv)
    train = random.sample(trainval, tr)

    print("训练集图片数量：", tr)
    print("验证集图片数量：", ta)
    print("测试集图片数量：", tt)

    # with open('/tmp/VOC2007/split.txt', 'w', encoding='utf-8') as f:
    #     f.write(str(val_percent))

    ftrainval = open(os.path.join(saveBasePath, 'Main/trainval.txt'), 'w')
    ftest = open(os.path.join(saveBasePath, 'Main/test.txt'), 'w')
    ftrain = open(os.path.join(saveBasePath, 'Main/train.txt'), 'w')
    fval = open(os.path.join(saveBasePath, 'Main/val.txt'), 'w')

    for i in range(len(total_xml)):                # 遍历所有 file_name.xml 文件
        name = total_xml[i][:-4] + '\\n'            # 获取 file_name
        if i in trainval:
            ftrainval.write(name)
            if i in train:
                ftrain.write(name)
            else:
                fval.write(name)
        else:
            ftest.write(name)

    ftrainval.close()
    ftrain.close()
    fval.close()
    ftest.close()

base_txt()

fi = open('./data/classes/vis.names', 'r')      # 按文件夹里面的文件修改好
txt = fi.readlines()
voc_class = []
for w in txt:
    w = w.replace('\\n', '')
    voc_class.append(w)
print('数据集里面的类别：', voc_class)
classes = voc_class

def convert_annotation(year, image_id, list_file):

    in_file = open('./DARK_%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 = '.'

# sets=[ ('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
sets=[  ('face', 'test')]
# wd = getcwd()
for year, image_set in sets:
    image_ids = open('./DARK_%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/DARK_%s/JPEGImages/%s.png'%(wd, year, image_id))
        convert_annotation(year, image_id, list_file)
        list_file.write('\\n')
    list_file.close()

运行split.py，得到face_test.txt文件（内容如下）
格式： image_path x_min, y_min, x_max, y_max, class_id x_min, y_min ,…, class_id

• 评估数据集，修改config.py

__C.TEST.ANNOT_PATH  = "./face_test.txt"
你之前训练保存的模型
__C.TEST.WEIGHT_FILE = "./checkpoint/yolov3_train_loss=14.6886.ckpt-50"

• 运行evaluate.py，在data/detection/下查看评估的结果
• 计算mAP,在终端运行

cd mAP
python main.py -na

ps:训练自己的数据集

1.先把vis.names文件内容修改为自己所需要的类别。
2.把自己数据集转换成图像+xml形式，替换掉项目中的voc2007文件夹对应的部分。
3.根据自己需要修改split.py里面的内容，划分数据集。
4.修改config.py内容，运行train.py训练。
5.运行evaluate.py评估结果。
6.运行mAP文件夹下的 main.py计算mAP。