[Python知识库]如何配置yolov5并训练自己的模型

提前准备

• Pycharm
• python3.8
• yolov5源码 官网链接

1. 环境搭建并运行官方案例

• 下载yolov5源码，推荐使用最新版，如下图，直接下载master分支即可
  

• 解压下载的zip文件，使用pycharm打开项目，接着添加解释器
  

• 这里使用新环境，没有用anaconda，因为使用pycharm自带的python环境可以让虚拟环境跟随项目，在其他电脑运行时候就不用重新配置环境了。
  

• 使用pycharm的终端安装requirements.txt中需要的环境，直接在终端

pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple/

• 使用国内源可以下载快些。
• 提前下载yolov5s.pt预训练权重GitHub链接，（也可以不下载，运行detect.py的时候会自动下载，但是容易下载出错，因为GitHub网络问题），下载好后放在yolov5-master文件夹里面

• 右键运行detect.py文件，如果出现下图即表示环境搭建成功（运行的是自带的模型，识别人，汽车等），此时生成run文件夹，结果存放在yolov5-master/run/detect/exp文件内

• 没有使用cuda进行加速，因为有些小伙伴可能没有N卡，所以使用的CPU版本，想使用GPU加速只需要安装GPU版本的pytorch即可，但是要看看自己显卡支持的cuda版本，参考这篇博文https://blog.csdn.net/didiaopao/article/details/119787139 链接直达

2. 创建并划分数据集

参考下面博文即可
https://blog.csdn.net/didiaopao/article/details/120022845

• VOC标签格式转yolo格式并划分训练集和测试集

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 = ["hat", "person"] # 自定义类
 
TRAIN_RATIO = 80 # 8：2 训练集和验证集比率
 
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
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()

• 需要注意划分的代码和数据集应在同一目录下

3. 训练自己的数据集

• 参考下面博文 https://blog.csdn.net/didiaopao/article/details/119954291 链接直达
• 上面博文中复制出来的hat.yaml与我下载yolov5中新版voc.yaml的不一样，推荐使用新版(新版还有一个download，删除即可，它是下载voc数据集)

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC
# Example usage: python train.py --data VOC.yaml
# parent
# ├── yolov5
# └── datasets
#     └── VOC  ← downloads here


# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: C:/Users/zgy/Downloads/Compressed/yolov5-master/VOCdevkit
train: # train images (relative to 'path')  16551 images
  - images/train

val: # val images (relative to 'path')  4952 images
  - images/val
test: # test images (optional)

# Classes
nc: 2  # number of classes
names: ['hat', 'person']  # class names

• 新版voc.yaml如下

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC
# Example usage: python train.py --data VOC.yaml
# parent
# ├── yolov5
# └── datasets
#     └── VOC  ← downloads here


# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: ../datasets/VOC
train: # train images (relative to 'path')  16551 images
  - images/train2012
  - images/train2007
  - images/val2012
  - images/val2007
val: # val images (relative to 'path')  4952 images
  - images/test2007
test: # test images (optional)
  - images/test2007

# Classes
nc: 20  # number of classes
names: ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog',
        'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor']  # class names


# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
  import xml.etree.ElementTree as ET

  from tqdm import tqdm
  from utils.general import download, Path


  def convert_label(path, lb_path, year, image_id):
      def convert_box(size, box):
          dw, dh = 1. / size[0], 1. / size[1]
          x, y, w, h = (box[0] + box[1]) / 2.0 - 1, (box[2] + box[3]) / 2.0 - 1, box[1] - box[0], box[3] - box[2]
          return x * dw, y * dh, w * dw, h * dh

      in_file = open(path / f'VOC{year}/Annotations/{image_id}.xml')
      out_file = open(lb_path, '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'):
          cls = obj.find('name').text
          if cls in yaml['names'] and not int(obj.find('difficult').text) == 1:
              xmlbox = obj.find('bndbox')
              bb = convert_box((w, h), [float(xmlbox.find(x).text) for x in ('xmin', 'xmax', 'ymin', 'ymax')])
              cls_id = yaml['names'].index(cls)  # class id
              out_file.write(" ".join([str(a) for a in (cls_id, *bb)]) + '\n')


  # Download
  dir = Path(yaml['path'])  # dataset root dir
  url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
  urls = [url + 'VOCtrainval_06-Nov-2007.zip',  # 446MB, 5012 images
          url + 'VOCtest_06-Nov-2007.zip',  # 438MB, 4953 images
          url + 'VOCtrainval_11-May-2012.zip']  # 1.95GB, 17126 images
  download(urls, dir=dir / 'images', delete=False)

  # Convert
  path = dir / f'images/VOCdevkit'
  for year, image_set in ('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test'):
      imgs_path = dir / 'images' / f'{image_set}{year}'
      lbs_path = dir / 'labels' / f'{image_set}{year}'
      imgs_path.mkdir(exist_ok=True, parents=True)
      lbs_path.mkdir(exist_ok=True, parents=True)

      image_ids = open(path / f'VOC{year}/ImageSets/Main/{image_set}.txt').read().strip().split()
      for id in tqdm(image_ids, desc=f'{image_set}{year}'):
          f = path / f'VOC{year}/JPEGImages/{id}.jpg'  # old img path
          lb_path = (lbs_path / f.name).with_suffix('.txt')  # new label path
          f.rename(imgs_path / f.name)  # move image
          convert_label(path, lb_path, year, id)  # convert labels to YOLO format