yolo系列训练自己的数据集-数据准备

本文全部数据以及代码下载链接

1、标注数据

主要基于labelimg软件，具体步骤省略。

2、目录组织

目录组织如下：

├─Annotations
├─images
├─ImageSets
│  └─Main
└─labels

其中，Annotations目录下，保存的是XML文件，images保存的是图片，Main保存的是训练集和测试集的txt文件，labels保存的是每个XML文件的标签。

3、生成训练集和测试集

import os  
import random  
  
trainval_percent = 0.8
train_percent = 0.8
xmlfilepath = 'Annotations'  
txtsavepath = 'ImageSets\Main'  
total_xml = os.listdir(xmlfilepath)  
  
num=len(total_xml)  
list=range(num)  
tv=int(num*trainval_percent)  
tr=int(tv*train_percent)  
trainval= random.sample(list,tv)  
train=random.sample(trainval,tr)  
  
ftrainval = open('ImageSets/Main/trainval.txt', 'w')  
ftest = open('ImageSets/Main/test.txt', 'w')  
ftrain = open('ImageSets/Main/train.txt', 'w')  
fval = open('ImageSets/Main/val.txt', 'w')  
  
for i  in list:  
    name=total_xml[i][:-4]+'\n'  
    if i in trainval:  
        ftrainval.write(name)  
        if i in train:  
            ftrain.write(name)  
        else:  
            fval.write(name)  
    else:  
        ftest.write(name)  
  
ftrainval.close()  
ftrain.close()  
fval.close()  
ftest.close()

4、生成labels文件夹

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
 
sets = ['train', 'test','val']
 
classes = ["left_eye","right_eye"]#我们只是检测细胞，因此只有一个类别
 
 
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('data/Annotations/%s.xml' % (image_id))
    out_file = open('data/labels/%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')
 
 
wd = getcwd()
print(wd)
for image_set in sets:
    if not os.path.exists('data/labels/'):
        os.makedirs('data/labels/')
    image_ids = open('data/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
    list_file = open('data/%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write('data/images/%s.jpg\n' % (image_id))
        convert_annotation(image_id)
    list_file.close()

参考

• https://github.com/ultralytics/yolov3