YOLOv5训练目标检测数据集（小白）

一.提前准备工作

1.利用labelimg软件给收集到的图片打标签（具体步骤网上都有）

2.下载好yolov5（v6.1）源码（下载地址：https://github.com/ultralytics/yolov5），用pycharm打开。

在项目目录下新建了一个train文件夹，train里面创建JPEGimages和Annotations两个文件夹

JPEGimages：用以存放我们收集好的需要打标签的图片

Annotations：用以存放用labelImg标注好的xml标签文件

3.xml格式标签转化为txt格式，并划分训练集和验证集。

运行下面代码：

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=['poundLine', 'truckOn']


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('train/Annotations/%s.xml' %image_id,'rb')
    out_file = open('train/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, "train/")
if not os.path.isdir(data_base_dir):
    os.mkdir(data_base_dir)
annotation_dir = os.path.join(data_base_dir, "Annotations/")
if not os.path.isdir(annotation_dir):
        os.mkdir(annotation_dir)
clear_hidden_files(annotation_dir)
image_dir = os.path.join(data_base_dir, "JPEGImages/")
if not os.path.isdir(image_dir):
        os.mkdir(image_dir)
clear_hidden_files(image_dir)
yolo_labels_dir = os.path.join(data_base_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()

运行后train文件变为

image里面存放的是划分为训练集与验证集的图片

labels里面存放的是划分为训练集与验证集的txt标签

YOLOLabels里面存放的是所有数据集的txt标签

二.配置代码参数

1.下载预权重文件。网站预权重下载，这里我们使用yolov5n.pt，下载好放置于项目目录下。

2.data文件夹下的coco128.yaml文件在该目录下复制一份，命名为mydata.yaml。

原先的coco128.yaml:(包含80个类别)

自己创建的mydata.yaml（因为我只有两个类别poundLine、truckOn）:


修改路径和类别

3.model文件夹下的yolov5n.yaml（因为我使用的模型是yolov5n.pt）文件在该目录下复制一份，命名为mydata.yaml

4.train文件参数设置

三.开始训练

运行train.py文件，Run栏如下图所示即表明开始训练了。

完成训练后，Run栏提示项目将出现runs/train/exp11文件夹，里边包含训练好的权重数据和其他参数文件

四.训练可视化

训练时或者训练后可以利用 tensorboard 查看训练可视化
进入pytorch环境，进入yolov5-6.1文件夹执行。