https://github.com/ultralytics/yolov5 选择yolov5-5.0，并输入以下命令：
pip install -r requirements.txt准备数据集
在根目录下创建以下文件
VOCdevkit --VOC2007 ----Annotations #（放XML标签文件） ----ImageSets ------Main ----JPEGImages # (放原始图片)
在主目录下新建 voc_label.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
# 根据自己的数据标签修改
classes=["person","road roller","paver","dumper","helmet"]
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 = x*dw
w = w*dw
y = y*dh
h = h*dh
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/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 files
probo = random.randint(1, 100)
print("Probobility: %d" % probo)
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)
probo = random.randint(1, 100)
print("Probobility: %d" % probo)
if(probo < 80): # 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()
用python3命令： python3 voc_label.py
运行后会在 VOCdevkit 下生成 images 和 labels 以及在 VOC2007 下生成 YOLOLabels
把 train val nc（类别数） names 都修改成自己的：
注意：trian和val要分别指向VOCdevkit/images下的train/ 和 val/
最后的"/"不能少
yolov5提供了四个模型，分别是s、m、L、X，根据显卡和数据的情况自行选择，我选择 s ，之后则修改models文件夹下的yolov5s.yaml，只需要修改第一行nc后面改为自己的类别就可以
训练模型 下载预权重 需要下载与5.0版对应的权重文件
在 https://github.com/ultralytics/yolov5/releases/tag/v5.0 中找到yolov5s.pt并下载
weights：权重文件路径，将default后面的路径换成下载好的权重路径
cfg：存储模型结构的配置文件，将default后面的文件换成自己使用的模型配置文件
data：存储训练、测试数据的文件，换成data/voc.yaml
epochs：指的就是训练过程中整个数据集将被迭代多少次,显卡不行你就调小点。
batch-size：根据显卡算力调节，如果显卡不行，那就调小
img-size：输入图片的尺寸，默认的是640，需要是32的倍数才可以。
修改后运行
python3 train.py
训练好的模型会被保存在runs/exp0/weights/last.pt和best.pt
详细训练数据保存在runs/exp0/results.txt文件中。
利用tensorboard可视化训练过程，训练开始会在yolov5目录生成一个runs文件夹，利用tensorboard打开即可查看训练日志，命令如下：
tensorboard --logdir=runs
