yolov-GPU/CPU安装:https://mp.csdn.net/mdeditor/97410700#
labelImg标注工具安装:https://mp.csdn.net/mdeditor/97416966#
训练自己的单一数据集:
- 修改labelImg/data/predefined_class.txt文件
由于训练单一的数据集,只需将原文件修改成自己的类:
mark
-
使用labelImg进行图像标注
用labelImg标注生成PASCAL VOC格式的xml标记文件;再将xml标记文件转换为yolo的txt文件:
可以用python代码实现两种标记格式的转换:def convert(size, box): dw = 1./size[0] dh = 1./size[1] x = (box[0] + box[1])/2.0 y = (box[2] + box[3])/2.0 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)
-
建立目录格式
使用PACSAL VOC目录格式:
建立文件夹层次为 darknet / VOCdevkit / VOC2007 VOC2007
下面建立两个文件夹:Annotations和JPEGImages
JPEGImages放所有的训练和测试图片,Annotations放所有的xml标记文件; -
生成训练和测试文件
执行:python gen_files.py
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
import random
classes=[“ball”,“messi”]
def clear_hidden_files(path):
dir_list = os.listdir(path)
for i in dir_list:
abspath = os.path.join(os.path.abspath(path), i)
if os.path.isfile(abspath):
if i.startswith("._"):
os.remove(abspath)
else:
clear_hidden_files(abspath)
def convert(size, box):
dw = 1./size[0]
dh = 1./size[1]
x = (box[0] + box[1])/2.0
y = (box[2] + box[3])/2.0
w = box[1] - box[0]
h = box[3] - box[2]
x = xdw
w = wdw
y = ydh
h = hdh
return (x,y,w,h)
def convert_annotation(image_id):
in_file = open(‘VOCdevkit/VOC2007/Annotations/%s.xml’ %image_id)
out_file = open(‘VOCdevkit/VOC2007/labels/%s.txt’ %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 = 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 = (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]) + '\n') in_file.close() out_file.close() wd = os.getcwd() wd = os.getcwd() work_sapce_dir = os.path.join(wd, "VOCdevkit/") if not os.path.isdir(work_sapce_dir): os.mkdir(work_sapce_dir) work_sapce_dir = os.path.join(work_sapce_dir, "VOC2007/") if not os.path.isdir(work_sapce_dir): os.mkdir(work_sapce_dir) annotation_dir = os.path.join(work_sapce_dir, "Annotations/") if not os.path.isdir(annotation_dir): os.mkdir(annotation_dir) clear_hidden_files(annotation_dir) image_dir = os.path.join(work_sapce_dir, "JPEGImages/") if not os.path.isdir(image_dir): os.mkdir(image_dir) clear_hidden_files(image_dir) VOC_file_dir = os.path.join(work_sapce_dir, "ImageSets/") if not os.path.isdir(VOC_file_dir): os.mkdir(VOC_file_dir) VOC_file_dir = os.path.join(VOC_file_dir, "Main/") if not os.path.isdir(VOC_file_dir): os.mkdir(VOC_file_dir) train_file = open(os.path.join(wd, "2007_train.txt"), 'w') test_file = open(os.path.join(wd, "2007_test.txt"), 'w') train_file.close() test_file.close() VOC_train_file = open(os.path.join(work_sapce_dir,"ImageSets/Main/train.txt"), 'w') VOC_test_file = open(os.path.join(work_sapce_dir,"ImageSets/Main/test.txt"), 'w') VOC_train_file.close() VOC_test_file.close() if not os.path.exists('VOCdevkit/VOC2007/labels'): os.makedirs('VOCdevkit/VOC2007/labels') train_file = open(os.path.join(wd, "2007_train.txt"), 'a') test_file = open(os.path.join(wd, "2007_test.txt"), 'a') VOC_train_file = open(os.path.join(work_sapce_dir,"ImageSets/Main/train.txt"), 'a') VOC_test_file = open(os.path.join(work_sapce_dir,"ImageSets/Main/test.txt"), 'a') list = os.listdir(image_dir) # list image files probo = random.randint(1, 100) print("Probobility: %d" % probo) for i in range(0,len(list)): path = os.path.join(image_dir,list[i]) if os.path.isfile(path): image_path = image_dir + list[i] voc_path = list[i] (nameWithoutExtention, extention) = os.path.splitext(os.path.basename(image_path)) (voc_nameWithoutExtention, voc_extention) = os.path.splitext(os.path.basename(voc_path)) annotation_name = nameWithoutExtention + '.xml' annotation_path = os.path.join(annotation_dir, annotation_name) probo = random.randint(1, 100) print("Probobility: %d" % probo) if(probo < 75): if os.path.exists(annotation_path): train_file.write(image_path + '\n') VOC_train_file.write(voc_nameWithoutExtention + '\n') convert_annotation(nameWithoutExtention) else: if os.path.exists(annotation_path): test_file.write(image_path + '\n') VOC_test_file.write(voc_nameWithoutExtention + '\n') convert_annotation(nameWithoutExtention) train_file.close() test_file.close() VOC_train_file.close() VOC_test_file.close()
(1)在VOCdevkit / VOC2007目录下可以看到生成了文件夹labels ,同时在darknet下生成了两个文件 2007_train.txt和2007_test.txt。2007_train.txt和2007_test.txt分别给出了训练图片文件和测试图片文 件的列表,含有每个图片的路径和文件名。另外,在VOCdevkit / VOC2007/ImageSets/Main目录下生 成了两个文件test.txt和train.txt,分别给出了训练图片文件和测试图片文件的列表,但只含有每个图片 的文件名(不含路径和扩展名)
(2)最终训练只需要:2007_train.txt,2007_test.txt,labels下的标注文件和 VOCdevkit / VOC2007/JPEGImages下的图像文件;
-
修改配置文件
(1)新建data/voc.names文件 可以复制data/voc.names再根据自己情况的修改;
(2)新建 cfg/voc.data文件 可以复制cfg/voc.data再根据自己情况的修改;
(3)新建cfg/yolov3-voc.cfg
在cfg/yolov3-voc.cfg文件中,三个yolo层和各自前面的conv层的参数需要修改: 三个yolo层都要改:yolo层中的class为类别数,每一个yolo层前的conv层中的filters =(类别+5)* 3
我的修改为:yolo层 classes=1, conv层 filters=18
-
训练自己的数据集
(1)在 darknet 目录下载权重文件:wget https://pjreddie.com/media/files/darknet53.conv.74
这里的训练使用迁移学习,所以下载的yolo预训练的权重文件(不含全连接层)
(2)训练
./darknet detector train cfg/voc-ball.data cfg/yolov3-voc-ball.cfg
darknet53.conv.74
如需要存储训练日志,先在darknet下建立visualization目录,再执行
./darknet detector train cfg/voc-ball.data cfg/yolov3-voc-ball.cfg
darknet53.conv.74 2>1 | tee visualization/train_yolov3_ball.log
到这里为止已完成训练部分,训练需花费几小时(GPU);请耐心等待,我一般晚上走之前训练,第二天早上就训练好了,哈哈哈,可以大大节省时间。
- 测试训练出的网络模型
训练好后可以在backup看到权重文件 尝试test前要修改cfg文件,切换到test模式。 可以重新建立一个测试cfg文件, 如yolov3-voc-ball-test.cfg 测试图片:
./darknet detector test cfg/voc-ball.data cfg/yolov3-voc-ball-test.cfg
backup/yolov3-voc-ball_final.weights testfiles/img1.jpg
到此为止可以通过测试,来检测目标物识别的精准度,后期将对yolo模型原理+代码进行解析,敬请期待!