1. 程式人生 > 其它 >win10下用yolov3訓練WiderFace資料集來實現人臉檢測(TensorFlow版本,darkface作為測試集)

win10下用yolov3訓練WiderFace資料集來實現人臉檢測(TensorFlow版本,darkface作為測試集)

技術標籤:人臉檢測

資料集準備工作

  • 訓練集 Wider Face格式轉換
    下載人臉資料集wider face,解壓到同一個資料夾下
    在這裡插入圖片描述
    在同一個目錄下,新建convert.py檔案(把下面程式放入)執行程式得到影象和其對應的xml檔案。
# -*- 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...')

執行後得到以下的檔案(訓練會重新打亂,所以只需要管Annotations,JPEGImages兩個資料夾):
在這裡插入圖片描述
Annotations:存放影象對應的xml
ImageSets:包含train.txt ,val.txt(分別包含對應的影象名字)
JPEGImages:存放影象

  • 測試集Dark Face格式轉換
    (若只用WilderFace作為訓練集,測試集,忽略這一步)
    下載夜間人臉資料集Dark Face,我使用的是它的訓練集6000張影象作為測試。
    執行下面的程式得到影象和對應的xml檔案。
# -*- 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')
    #影象名稱
    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)  # 格式化顯示,該換行的換行
    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__":
    #影象資料夾所在位置
    img_path = r"E:\BaiduNetdiskDownload\DarkFace_Train_new\images"
    #標註資料夾所在位置
    txt_path=r"E:\BaiduNetdiskDownload\DarkFace_Train_new\label"
    #txt轉化成xml格式後存放的資料夾
    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訓練

  • 下載訓練程式碼和預訓練模型,並搭建好環境
    專案程式碼:tensorflow-serving-yolov3
    基於vgg的coco預訓練模型百度雲地址,密碼:vw9x
  • 把預訓練模型解壓到專案的checkpoint資料夾下,然後執行convert_weight.py,得到yolov3_coco_demo.ckpt模型
  • 修改vis.names裡的內容,只新增face這一個類別
  • 把tensorflow-serving-yolov3/VOC2007/資料夾下的Annotations,JPEGImages兩個資料夾換成第一步生成的wilderface的資料夾,接著修改split.py的60行內容
fi = open('./data/classes/voc.names', 'r')
修改為
fi = open('./data/classes/vis.names', 'r')

執行split.py,根目錄下得到以下三個檔案:
在這裡插入圖片描述

  • 修改core/config.py的以下內容:
__C.TRAIN.BATCH_SIZE  = 2#根據自己電腦情況自行修改
__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#根據自己需要自行修改
__C.TRAIN.SECOND_STAGE_EPOCHS   = 30
__C.TRAIN.INITIAL_WEIGHT  = "./checkpoint/yolov3_coco_demo.ckpt"
  • 執行train.py進行訓練
  • 執行convert_weight.py儲存模型

評估階段

  • 我用的是darkface的訓練集全部作為測試,複製voc2007資料夾並重命名為DARK_face,並把Annotations,JPEGImages兩個資料夾替換成darkface的xml和影象(這一步就是為生成YOLOv3所需要格式做準備)
  • 修改split.py的內容
# -*- 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檔案儲存目錄
    total_xml = os.listdir(r'./DARK_face/Annotations')   # 獲取標註檔案(file_name.xml)

    # 劃分資料集為(訓練,驗證,測試集 = 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)

    # 打亂訓練檔案(洗牌)
    trainval = random.sample(range(len(total_xml)), tv)
    train = random.sample(trainval, tr)

    print("訓練集圖片數量:", tr)
    print("驗證集圖片數量:", ta)
    print("測試集圖片數量:", 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)):                # 遍歷所有 file_name.xml 檔案
        name = total_xml[i][:-4] + '\n'            # 獲取 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')      # 按資料夾裡面的檔案修改好
txt = fi.readlines()
voc_class = []
for w in txt:
    w = w.replace('\n', '')
    voc_class.append(w)
print('資料集裡面的類別:', 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()

執行split.py,得到face_test.txt檔案(內容如下)
格式: image_path x_min, y_min, x_max, y_max, class_id x_min, y_min ,…, class_id
在這裡插入圖片描述

  • 評估資料集,修改config.py
__C.TEST.ANNOT_PATH  = "./face_test.txt"
你之前訓練儲存的模型
__C.TEST.WEIGHT_FILE = "./checkpoint/yolov3_train_loss=14.6886.ckpt-50"
  • 執行evaluate.py,在data/detection/下檢視評估的結果
  • 計算mAP,在終端執行
cd mAP
python main.py -na

ps:訓練自己的資料集

1.先把vis.names檔案內容修改為自己所需要的類別。
2.把自己資料集轉換成影象+xml形式,替換掉專案中的voc2007資料夾對應的部分。
3.根據自己需要修改split.py裡面的內容,劃分資料集。
4.修改config.py內容,執行train.py訓練。
5.執行evaluate.py評估結果。
6.執行mAP資料夾下的 main.py計算mAP。