yolov5快速使用

  1. 快速开始项目:

    • 准备自己的数据集
    • 创建对应的配置文件: 'data/xx.yaml'
    • 修改预训练的配置文件:'models/yolov5s.yaml'
    • 下载最新预训练模型到weights目录下
    • 开始训练:
      python train.py --img 640 --batch 16 --epochs 500 --data go.yaml --weights weights/yolov5s.pt
      (可以修改train.py中的相关参数的默认配置,方便下次训练)
    • 测试:

      python test.py  --data data/go.yaml --weights  E:\GDUT\python_project\ObjectDection\Yolov5\runs\train\exp13\weights\best.pt --augment
    • 检测:

      python detect.py --weight runs\train\exp14\weights\best.pt--source data/testImg
    • tensbard查看:

      tensorboard --logdir=runs
  2. 数据集的准备:

    • 认识voc与yolo两种格式的数据集:
      voc数据的格式 :参考

    • yolo标签的格式(需要归一化) 参考

          

      x,y是目标的中心坐标,width,height是目标的宽和高

  3. 训练集、验证集与测试集的选择:

  4. 相关脚本:

    • 文件统一命名

      ## 将目录下面的图片从起始编号开始按顺序命名
      import os
      path=os.getcwd()
      print("当前所在路径:"+path)
      path=input("输入文件路径:")
      if(path[-1]!="\\"):
      path=path+"\\"
      # C:/Users/zh/Desktop/围棋数据集补充/数据集图片/
      a=input("输入起始编号:")
      type=input("文件后缀:")
      ##创建文件夹
      # if not os.path.exists(res_path):
      #     os.makedirs(res_path)
      f=os.listdir(path)
      for index,i in enumerate(f):
      if os.path.isfile(path+i) and  (path+i).endswith("."+type):
      ## 重命名并删除
      if  (os.path.exists(path+str(int(a)+index)+"."+type)):
           print("文件名冲突")
      else:
           os.rename(path+i,path+str(int(a)+index)+"."+type)
    • voc训练集与验证集以及测试集的划分

      # 参考:https://my.oschina.net/u/4870686/blog/4803148
      # 作用: 划分xml文件名到四个txt文件去
      # 说明: 数据集全部拿来训练(其中80%作为训练集20%作为验证集),不留测试集
      train_and_valid=1.0
      train_percent = 0.8
      
      ##输入xml文件路径:
      xml_file_path=input("请输入xml文件路径:")
      txt_save_path=input("将要保存的路径:")
      
      if(xml_file_path==""):
      xml_file_path='Annotations'
      if(txt_save_path==""):
      txt_save_path='ImageSets/Main'
      
      # xml文件对象
      total_xml = os.listdir(xml_file_path)
      
      if not os.path.exists(txt_save_path):
      os.makedirs(txt_save_path)
      
      num = len(total_xml)
      list_index = range(num)
      
      num_train_and_valid = int(num*train_and_valid)
      num_train = int(num_train_and_valid * train_percent)
      
      ## 从数据集中选择出用于训练的部分
      index_train_and_valid = random.sample(list_index,num_train_and_valid)
      ##  训练集的编号(在上一步随机的基础上在随机挑选)
      index_train = random.sample(index_train_and_valid,num_train)
      
      file_train_and_valid = open(txt_save_path + '/trainval.txt', 'w')
      file_test = open(txt_save_path + '/test.txt', 'w')
      file_train = open(txt_save_path + '/train.txt', 'w')
      file_val = open(txt_save_path + '/val.txt', 'w')
      
      ##
      for i in list_index:
      ## 获取每个文件名(去除后缀)
      name = total_xml[i][:-4] + '\n'
      if i in index_train_and_valid :
      ## 训练+验证
      file_train_and_valid.write(name)
      if i in index_train:
           ## 训练
           file_train.write(name)
      else:
           ## 验证
           file_val.write(name)
      ## 测试集
      else:
      file_test.write(name)
      
      file_train_and_valid .close()
      file_train.close()
      file_val.close()
      file_test.close()
    • voc格式转yolo格式

      import xml.etree.ElementTree as ET
      import os
      from os import getcwd
      
      dir_type = ['train', 'val']
      classes = ["wdj"]   # 改成自己的类别
      abs_path = os.getcwd()
      print(abs_path)
      
      ## voc to Yolo
      def convert(size, box):
      dw = 1. / (size[0])
      dh = 1. / (size[1])
      x = (box[0] + box[1]) / 2.0 - 1
      y = (box[2] + box[3]) / 2.0 - 1
      w = box[1] - box[0]
      h = box[3] - box[2]
      ## 归一化
      x = x * dw
      w = w * dw
      y = y * dh
      h = h * dh
      return x, y, w, h
      
      def convert_annotation(image_id):
      ## 读取xml
      in_file = open('Annotations/%s.xml' % (image_id), encoding='UTF-8')
      ## 创建 将要保存的文件
      out_file = open('labels/%s.txt' % (image_id), 'w')
      # xml工具
      tree = ET.parse(in_file)
      root = tree.getroot()
      size = root.find('size')
      ## 图片的w\h
      w = int(size.find('width').text)
      h = int(size.find('height').text)
      
      ## 多目标检测
      for obj in root.iter('object'):
      
      difficult = obj.find('difficult').text
      ## 类别
      cls = obj.find('name').text
      ## 类别问题 跳过
      if cls not in classes or int(difficult) == 1:
           continue
      cls_id = classes.index(cls)
      # 上下左右边界
      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))
      b1, b2, b3, b4 = b
      # 标注越界修正
      if b2 > w:
           b2 = w
      if b4 > h:
           b4 = h
      b = (b1, b2, b3, b4)
      bb = convert((w, h), b)
      out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
      
      wd = getcwd()
      
      ##   E:\GDUT\python_project\ObjectDection\dataset\wdj2
      
      test_file=open("file.txt","w")
      test_file.write("测试内容")
      
      
      ##分别读取三个划分文件:
      for dir in dir_type:
      
      if not os.path.exists('labels/'):
      os.makedirs('labels/')
      
      ##从划分的txt文件中获取图片id
      image_ids = open('ImageSets/Main/%s.txt' % (dir)).read().strip().split()
      
      ##根目录创建txt文件保存图片绝对路径:
      ##list_file = open('%s.txt' % (dir), 'w')
      
      for image_id in image_ids:
      ## 图片写入指定的目录
      ##list_file.write(abs_path + '\\JPGEImages\\%s.jpg\n' % (image_id))
      convert_annotation(image_id)
      ##list_file.close()
    • yolo数据集中训练集、验证集、测试集的划分

      ## 将yolo数据集的格式 按照比例进行划分 用于训练
      
      # 训练集、验证集和测试集的比例分配
      test_percent = 0
      valid_percent = 0.2
      train_percent = 0.8
      
      # 标注文件的路径
      srcImg_path=input("源图片路径:")
      label_path=input("标签文件路劲:")
      if(srcImg_path==""):
      image_path = 'JPEGImages'
      if(label_path==""):
      label_path = 'labels'
      
      ##目标存储文件夹:
      save_path=input("Yolo数据集存储位置:")
      
      if(save_path[-1]!="\\"):
      save_path=save_path+"\\"
      
      ##获取文件夹下的文件对象
      images_files_list = os.listdir(image_path)
      labels_files_list = os.listdir(label_path)
      
      total_num = len(images_files_list)
      
      test_num = int(total_num * test_percent)
      valid_num = int(total_num * valid_percent)
      train_num = int(total_num * train_percent)
      
      # 对应文件的索引
      test_image_index = random.sample(range(total_num), test_num)
      valid_image_index = random.sample(range(total_num), valid_num)
      train_image_index = random.sample(range(total_num), train_num)
      
      dir=["train","valid","test"]
      sub_dir=["images","labels"]
      for d in dir:
      if not os.path.exists(save_path+d):
      os.makedirs(save_path+d)
      for sd in sub_dir:
      if not os.path.exists(save_path+d+"/"+sd):
           os.makedirs(save_path+d+"/"+sd)
      
      
      for i in range(total_num):
      if i in test_image_index:
      # 将图片和标签文件拷贝到对应文件夹下
      shutil.copyfile('JPEGImages/{}'.format(images_files_list[i]), save_path+'test/images/{}'.format(images_files_list[i]))
      shutil.copyfile('labels/{}'.format(labels_files_list[i]), save_path+'test/labels/{}'.format(labels_files_list[i]))
      elif i in valid_image_index:
      shutil.copyfile('JPEGImages/{}'.format(images_files_list[i]), save_path+'valid/images/{}'.format(images_files_list[i]))
      shutil.copyfile('labels/{}'.format(labels_files_list[i]), save_path+'valid/labels/{}'.format(labels_files_list[i]))
      else:
      shutil.copyfile('JPEGImages/{}'.format(images_files_list[i]), save_path+'train/images/{}'.format(images_files_list[i]))
      shutil.copyfile('labels/{}'.format(labels_files_list[i]), save_path+'train/labels/{}'.format(labels_files_list[i]))
      

你可能感兴趣的:(图像识别pytorch)