yolov5训练voc数据集

1.数据集

下载好voc数据集，以2007为例，把数据集（VOCtrainval_06-Nov-2007和VOCtest_06-Nov-2007）都解压同一个文件夹里，记住解压后的图片是从000001.jpg-009963.jpd的。
在VOCdevkit/目录下 运行voc2yolo.py代码

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
 
# 这里就体现出来了咱们在1.2步骤的时候我说的尽量按照那个目录名进行操作的优势，
# 在这可以剩下很多去修改名称的精力
# sets=[('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
sets=[ ('2007', 'train'), ('2007', 'val'), ('2007', 'test')]  # 我只用了VOC2007
 
classes = ["aeroplane", "bicycle", "bird", "boat", "bottle",
           "bus", "car", "cat", "chair", "cow",
           "diningtable", "dog", "horse", "motorbike", "person",
           "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
#classes = ["face"]  # 修改为自己的label
 
def convert(size, box):
    dw = 1./(size[0])  # 有的人运行这个脚本可能报错，说不能除以0什么的，你可以变成dw = 1./((size[0])+0.1)
    dh = 1./(size[1])  # 有的人运行这个脚本可能报错，说不能除以0什么的，你可以变成dh = 1./((size[0])+0.1)
    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(year, image_id):
    in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
    out_file = open('VOCdevkit/VOC%s/labels/%s.txt'%(year, 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')
 
wd = getcwd()
 
for year, image_set in sets:
    if not os.path.exists('VOCdevkit/VOC%s/labels/'%(year)):
        os.makedirs('VOCdevkit/VOC%s/labels/'%(year))
    image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
    list_file = open('%s_%s.txt'%(year, image_set), 'w')
    for image_id in image_ids:
        list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg\n'%(wd, year, image_id))
        convert_annotation(year, image_id)
    list_file.close()
 
# 这块是路径拼接，暂时用不上，先都注释了
# os.system("cat 2007_train.txt 2007_val.txt 2012_train.txt 2012_val.txt > train.txt")
# os.system("cat 2007_train.txt 2007_val.txt 2007_test.txt 2012_train.txt 2012_val.txt > train.all.txt")

之后会生成三个.txt文件和一个labels文件夹。labels文件夹在VOCdevkit\VOC2007里


yolov5训练需要的就是JPEGImages下的所有图片以及labels下的所有标签。主要通过train.txt和val.txt里面的内容查找images和labels去训练。所以在yolov5里，images和labels的目录结构和名字最好以下面格式出现。

.
├── images
│   ├── 000001.jpg
│   ├── 000002.jpg
│   └── 000003.jpg
├── labels
│   ├── 000001.txt
│   ├── 000002.txt
│   └── 000003.txt

图片文件放在images，标签放在labels。images和labels需要在同一个根目录里。否则训练时找不到标签。如下

Traceback (most recent call last):
  File "train.py", line 669, in <module>
    train(hyp, opt, device, tb_writer)
  File "train.py", line 246, in train
    image_weights=opt.image_weights, quad=opt.quad, prefix=colorstr('train: '))
  File "/home/yolov5/yolov5/utils/datasets.py", line 72, in create_dataloader
    prefix=prefix)
  File "/home/yolov5/yolov5/utils/datasets.py", line 396, in __init__
    assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {help_url}'
AssertionError: train: No labels in /home/yolov5/yolov5/data/2007_train.cache. Can not train without labels. See https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data

所以可以把JPEGImages的名字修改为images，同时也要修改train.txt,val.txt和test.text里面的目录，这里在windos下打开train.txt然后使用替换就行非常方便。