YOLOV5 训练自己数据集记录

• splitTrainVal.py：划分数据集，为后面训练YOLO网络使用
• --xml_path '/path/to/label/labels'
• --txt_path '/path/to/Main'

• # coding:utf-8
  
  import os
  import random
  import argparse
  
  parser = argparse.ArgumentParser()
  #xml文件的地址，根据自己的数据进行修改 xml一般存放在Annotations下
  parser.add_argument('--xml_path', default='/path/to/label/labels', type=str, help='input xml label path')
  #数据集的划分，地址选择自己数据下的ImageSets/Main
  parser.add_argument('--txt_path', default='/path/to/Main', type=str, help='output txt label path')
  # parser.add_argument('--jpg_path', default='images', type=str, help='output txt label path')
  opt = parser.parse_args()
  
  trainval_percent = 0.9  # 训练集和验证集所占比例。 这里没有划分测试集
  train_percent = 0.9     # 训练集所占比例，可自己进行调整
  #xml文件保存地址
  xmlfilepath = opt.xml_path
  total_xml = os.listdir(xmlfilepath)
  #数据集划分后文件保存地址
  txtsavepath = opt.txt_path
  if not os.path.exists(txtsavepath):
      os.makedirs(txtsavepath)
  
  num = len(total_xml)
  list_index = range(num)
  tv = int(num * trainval_percent)
  tr = int(tv * train_percent)
  trainval = random.sample(list_index, tv)
  train = random.sample(trainval, tr)
  file_trainval = open(txtsavepath + '/trainval.txt', 'w')
  file_test = open(txtsavepath + '/test.txt', 'w')
  file_train = open(txtsavepath + '/train.txt', 'w')
  file_val = open(txtsavepath + '/val.txt', 'w')
  
  for i in list_index:
      name = total_xml[i][:-4] + '\n'
      if i in trainval:
          file_trainval.write(name)
          if i in train:
              file_train.write(name)
          else:
              file_val.write(name)
      else:
          file_test.write(name)
  
  file_trainval.close()
  file_train.close()
  file_val.close()
  file_test.close()
  

• text2yolo.py：根据划分好的数据集，将xml文件转化为YOLO数据集格式txt，并生成train val test.txt用来指定图片路径
• --Main_path '/path/to/Main/%s.txt'
• --dataset_path '/path/to/dataset/%s.txt'
• --images_path '/path/to/images/%s.jpg\n'

• # -*- coding: utf-8 -*-
  import xml.etree.ElementTree as ET
  import os
  from os import getcwd
  import argparse
  
  sets = ['train', 'val', 'test', 'train val']
  classes = ['person', 'smoke', 'train']  # 改成自己的类别
  abs_path = os.getcwd()
  print(abs_path)
  
  
  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]
      x = x * dw
      w = w * dw
      y = y * dh
      h = h * dh
      return x, y, w, h
  
  
  def convert_annotation(img_id):
      out_file = open('labels/%s.txt' % img_id, 'w')
      try:
          in_file = open('Annotations/%s.xml' % img_id, encoding='UTF-8')
          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))
              b1, b2, b3, b4 = b
              xc = (b1 + b2) / 2 / w
              yc = (b3 + b4) / 2 / h
              wc = (b2 - b1) / w
              hc = (b4 - b3) / h
              out_file.write(str(cls_id) + " " + str(xc) + " " + str(yc) + " " + str(wc) + " " + str(hc) + '\n')
      except:
          text = img_id + 'not_find'
          print(text)
  
  
  parser = argparse.ArgumentParser()
  parser.add_argument('--Main_path', default='/path/to/Main/%s.txt', type=str, help='/path/to/Main/%s.txt')
  parser.add_argument('--dataset_path', default='/path/to/dataset/%s.txt', type=str, help='/path/to/dataset/%s.txt')
  parser.add_argument('--images_path', default='/path/to/images/%s.jpg\n', type=str, help='/path/to/images/%s.jpg\n')
  opt = parser.parse_args()
  
  wd = getcwd()
  for image_set in sets:
      r = open(opt.Main_path % image_set, 'r')
      image_ids = []
      for line in r.readlines():
          line = line.strip()
          image_ids.append(str(line))
  
      print(sets, image_ids)
  
      list_file = open(opt.dataset_path % image_set, 'w')
      for image_id in image_ids:
          list_file.write(opt.images_path % image_id)
      list_file.close()
  

• 修改data.yaml文件
• Path: 对应为数据集根目录
• train: 对应为第二部中生成的train.txt
• val和test同理
• 修改为自己的class names：

• path: ../datasets/smoke  # dataset root dir
  train: val.txt  # train images (relative to 'path') 128 images
  val: val.txt # val images (relative to 'path') 128 images
  test:  # test images (optional)
  
  # Classes
  names:
    0: person
    1: smoke

• 训练YOLOv5网络，修改train.py
• --weights 预训练权重
• --imgsz 图片大小
• --project 'runs/train 保存路径'

def parse_opt(known=False):
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='initial weights path')
    parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
    parser.add_argument('--data', type=str, default=ROOT / 'data/cloud.yaml', help='dataset.yaml path')
    parser.add_argument('--hyp', type=str, default=ROOT / 'data/hyps/hyp.scratch-low.yaml', help='hyperparameters path')
    parser.add_argument('--epochs', type=int, default=20, help='total training epochs')
    parser.add_argument('--batch-size', type=int, default=4, help='total batch size for all GPUs, -1 for autobatch')
    parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='train, val image size (pixels)')
    parser.add_argument('--rect', action='store_true', help='rectangular training')
    parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
    parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
    parser.add_argument('--noval', action='store_true', help='only validate final epoch')
    parser.add_argument('--noautoanchor', action='store_true', help='disable AutoAnchor')
    parser.add_argument('--noplots', action='store_true', help='save no plot files')
    parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations')
    parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
    parser.add_argument('--cache', type=str, nargs='?', const='ram', help='image --cache ram/disk')
    parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
    parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
    parser.add_argument('--optimizer', type=str, choices=['SGD', 'Adam', 'AdamW'], default='SGD', help='optimizer')
    parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
    parser.add_argument('--workers', type=int, default=8, help='max dataloader workers (per RANK in DDP mode)')
    parser.add_argument('--project', default=ROOT / 'runs/train', help='save to project/name')
    parser.add_argument('--name', default='exp', help='save to project/name')
    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
    parser.add_argument('--quad', action='store_true', help='quad dataloader')
    parser.add_argument('--cos-lr', action='store_true', help='cosine LR scheduler')
    parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
    parser.add_argument('--patience', type=int, default=100, help='EarlyStopping patience (epochs without improvement)')
    parser.add_argument('--freeze', nargs='+', type=int, default=[0], help='Freeze layers: backbone=10, first3=0 1 2')
    parser.add_argument('--save-period', type=int, default=-1, help='Save checkpoint every x epochs (disabled if < 1)')
    parser.add_argument('--seed', type=int, default=0, help='Global training seed')
    parser.add_argument('--local_rank', type=int, default=-1, help='Automatic DDP Multi-GPU argument, do not modify')

    # Logger arguments
    parser.add_argument('--entity', default=None, help='Entity')
    parser.add_argument('--upload_dataset', nargs='?', const=True, default=False, help='Upload data, "val" option')
    parser.add_argument('--bbox_interval', type=int, default=-1, help='Set bounding-box image logging interval')
    parser.add_argument('--artifact_alias', type=str, default='latest', help='Version of dataset artifact to use')

    return parser.parse_known_args()[0] if known else parser.parse_args()