YOLOv5 训练自己的数据集
1.下载 yolo v5 源码
搜索 yolov5，下载.zip 文件，这里我下载的是 5.0 版本，
2.使用 Anaconda 创建虚拟环境
若无 anaconda 环境，也可直接使用 python 环境
在 Anaconda Prompt 中输入 conda create --name yolov5 python=3.8
输入 y 回车，然后输入命令 conda activate yolov5 进入虚拟环境。
yoloV5 要求在 Python>= 3.7.0 环境中，包括 PyTorch> = 1.7。
然后我们进入解压后的 YOLO V5 项目文件夹，使用 pip install -r
requirements.txt 命令下载项目所需依赖包（无 anaconda 可直接使用本命令安
装依赖库，默认你安装好了 python）
安装完成后,我们进入 PyTorch 官网,这里我选择以下配置:
PyTorch Build 选择 Stable (1.10.2)
Your OS 选择 Windows 系统
Package 选择 Pip 注意这里最好选用 pip,conda 会一直出现报错
Language 选择 Python
Compute Platform 选择 CUDA 10.2 有显卡建议选这个,没有显卡选择 CPU
Run this Command:显示
pip3 install torch==1.10.2+cu102 torchvision==0.11.3+cu102
torchaudio===0.10.2+cu102 -f
https://download.pytorch.org/whl/cu102/torch_stable.html
将上面命令复制到控制台,安装 pytorch,显示 Successful 即可
3.建立 VOC 格式标准文件夹
在 yolov5-5.0\下创建 make_voc_dir.py
import os
os.makedirs('VOCdevkit/VOC2007/Annotations')
os.makedirs('VOCdevkit/VOC2007/JPEGImages')
运行 make_voc_dir.py
在\yolov5-5.0\VOCdevkit\VOC2007\Annotations 中存放 xml 格式文件
在\yolov5-5.0\VOCdevkit\VOC2007\JPEGImages 中存放 JPG 格式文件
4.将 xml 格式转换成 yolo 格式
在 yolov5-5.0\下创建 voc_to_yolo.py
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
import random
from shutil import copyfile
classes = ["crack","helmet"] # 这个列表里存放的是你的类别
TRAIN_RATIO = 90 # 训练的比例
# 遍历文件夹
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)
# 对宽高进行归一化操作 size:原图的宽和高
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)
# 解析 XML
def convert_annotation(image_id):
in_file = open('VOCdevkit/VOC2007/Annotations/%s.xml' % image_id,'rb')
out_file = open('VOCdevkit/VOC2007/YOLOLabels/%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()
data_base_dir = os.path.join(wd, "VOCdevkit/")
if not os.path.isdir(data_base_dir):
os.mkdir(data_base_dir)
work_sapce_dir = os.path.join(data_base_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)
yolo_labels_dir = os.path.join(work_sapce_dir, "YOLOLabels/")
if not os.path.isdir(yolo_labels_dir):
os.mkdir(yolo_labels_dir)
clear_hidden_files(yolo_labels_dir)
yolov5_images_dir = os.path.join(data_base_dir, "images/")
if not os.path.isdir(yolov5_images_dir):
os.mkdir(yolov5_images_dir)
clear_hidden_files(yolov5_images_dir)
yolov5_labels_dir = os.path.join(data_base_dir, "labels/")
if not os.path.isdir(yolov5_labels_dir):
os.mkdir(yolov5_labels_dir)
clear_hidden_files(yolov5_labels_dir)
yolov5_images_train_dir = os.path.join(yolov5_images_dir, "train/")
if not os.path.isdir(yolov5_images_train_dir):
os.mkdir(yolov5_images_train_dir)
clear_hidden_files(yolov5_images_train_dir)
yolov5_images_test_dir = os.path.join(yolov5_images_dir, "val/")
if not os.path.isdir(yolov5_images_test_dir):
os.mkdir(yolov5_images_test_dir)
clear_hidden_files(yolov5_images_test_dir)
yolov5_labels_train_dir = os.path.join(yolov5_labels_dir, "train/")
if not os.path.isdir(yolov5_labels_train_dir):
os.mkdir(yolov5_labels_train_dir)
clear_hidden_files(yolov5_labels_train_dir)
yolov5_labels_test_dir = os.path.join(yolov5_labels_dir, "val/")
if not os.path.isdir(yolov5_labels_test_dir):
os.mkdir(yolov5_labels_test_dir)
clear_hidden_files(yolov5_labels_test_dir)
train_file = open(os.path.join(wd, "yolov5_train.txt"), 'w')
test_file = open(os.path.join(wd, "yolov5_val.txt"), 'w')
train_file.close()
test_file.close()
train_file = open(os.path.join(wd, "yolov5_train.txt"), 'a')
test_file = open(os.path.join(wd, "yolov5_val.txt"), 'a')
list_imgs = os.listdir(image_dir) # list image_one files
prob = random.randint(1, 100)
print("Probability: %d" % prob)
for i in range(0, len(list_imgs)):
path = os.path.join(image_dir, list_imgs[i])
if os.path.isfile(path):
image_path = image_dir + list_imgs[i]
voc_path = list_imgs[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)
label_name = nameWithoutExtention + '.txt'
label_path = os.path.join(yolo_labels_dir, label_name)
prob = random.randint(1, 100)
print("Probability: %d" % prob)
if (prob < TRAIN_RATIO): # train dataset
if os.path.exists(annotation_path):
train_file.write(image_path + '\n')
convert_annotation(nameWithoutExtention) # convert label
copyfile(image_path, yolov5_images_train_dir + voc_path)
copyfile(label_path, yolov5_labels_train_dir + label_name)
else: # test dataset
if os.path.exists(annotation_path):
test_file.write(image_path + '\n')
convert_annotation(nameWithoutExtention) # convert label
copyfile(image_path, yolov5_images_test_dir + voc_path)
copyfile(label_path, yolov5_labels_test_dir + label_name)
train_file.close()
test_file.close()
执行一下 voc_to_yolo.py
(yoloV5) E:\PythonCode\yoloV5_toukui\yolov5-5.0>python voc_to_yolo.py
Probability: 6
Probability: 79
Probability: 26
Probability: 19
Probability: 64
Probability: 5
Probability: 80
Probability: 40
Probability: 46
