voc資料集（xml）轉yolov5資料格式（txt）訓練自己的資料集

阿新 • • 發佈：2022-05-11

#為方便自己檢視，比較囉嗦。。。。。

1、資料集劃分（程式碼來自別人的分享專案中的一個檔案，在專案中能跑通，單獨檔案能否跑通，還沒試）：

import os
import random
import xml.etree.ElementTree as ET
from PIL import Image

import numpy as np

#from utils.utils import get_classes  #為方便單檔案執行，這裡將utils模組中的get_classes方法直接引入
#   獲得類
#---------------------------------------------------# 

def get_classes(classes_path):
    with open(classes_path, encoding='utf-8') as f:
        class_names = f.readlines()
    class_names = [c.strip() for c in class_names]
    return class_names, len(class_names)


#--------------------------------------------------------------------------------------------------------------------------------# 

#   annotation_mode用於指定該檔案執行時計算的內容
#   annotation_mode為0代表整個標籤處理過程，包括獲得VOCdevkit/VOC2007/ImageSets裡面的txt以及訓練用的2007_train.txt、2007_val.txt
#   annotation_mode為1代表獲得VOCdevkit/VOC2007/ImageSets裡面的txt
#   annotation_mode為2代表獲得訓練用的2007_train.txt、2007_val.txt
#--------------------------------------------------------------------------------------------------------------------------------# 

annotation_mode     = 0
#-------------------------------------------------------------------#
#   必須要修改，用於生成2007_train.txt、2007_val.txt的目標資訊
#   與訓練和預測所用的classes_path一致即可
#   如果生成的2007_train.txt裡面沒有目標資訊
#   那麼就是因為classes沒有設定正確
#   僅在annotation_mode為0和2的時候有效
#-------------------------------------------------------------------#
classes_path        = 'model_data/cls_classes.txt'
#--------------------------------------------------------------------------------------------------------------------------------#
#   trainval_percent用於指定(訓練集+驗證集)與測試集的比例，預設情況下 (訓練集+驗證集):測試集 = 9:1
#   train_percent用於指定(訓練集+驗證集)中訓練集與驗證集的比例，預設情況下 訓練集:驗證集 = 9:1
#   僅在annotation_mode為0和1的時候有效
#--------------------------------------------------------------------------------------------------------------------------------#
trainval_percent    = 0.9
train_percent       = 0.9
#-------------------------------------------------------#
#   指向VOC資料集所在的資料夾
#   預設指向根目錄下的VOC資料集
#-------------------------------------------------------#
VOCdevkit_path  = 'VOCdevkit'

VOCdevkit_sets  = [('2007', 'train'), ('2007', 'val')]
classes, _      = get_classes(classes_path)

#-------------------------------------------------------#
#   統計目標數量
#-------------------------------------------------------#
photo_nums  = np.zeros(len(VOCdevkit_sets))
nums        = np.zeros(len(classes))
def convert_annotation(year, image_id, list_file):
    in_file = open(os.path.join(VOCdevkit_path, 'VOC%s/Annotations/%s.xml'%(year, image_id)), encoding='utf-8')
    tree=ET.parse(in_file)
    root = tree.getroot()

    for obj in root.iter('object'):
        difficult = 0 
        if obj.find('difficult')!=None:
            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 = (int(float(xmlbox.find('xmin').text)), int(float(xmlbox.find('ymin').text)), int(float(xmlbox.find('xmax').text)), int(float(xmlbox.find('ymax').text)))
        list_file.write(" " + ",".join([str(a) for a in b]) + ',' + str(cls_id))
        
        nums[classes.index(cls)] = nums[classes.index(cls)] + 1
        
if __name__ == "__main__":
    random.seed(0)
    if " " in os.path.abspath(VOCdevkit_path):
        raise ValueError("資料集存放的資料夾路徑與圖片名稱中不可以存在空格，否則會影響正常的模型訓練，請注意修改。")

    if annotation_mode == 0 or annotation_mode == 1:
        print("Generate txt in ImageSets.")
        xmlfilepath     = os.path.join(VOCdevkit_path, 'VOC2007/Annotations')
        saveBasePath    = os.path.join(VOCdevkit_path, 'VOC2007/ImageSets/Main')
        temp_xml        = os.listdir(xmlfilepath)
        total_xml       = []
        for xml in temp_xml:
            if xml.endswith(".xml"):
                total_xml.append(xml)

        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)  
        
        print("train and val size",tv)
        print("train size",tr)
        ftrainval   = open(os.path.join(saveBasePath,'trainval.txt'), 'w')  
        ftest       = open(os.path.join(saveBasePath,'test.txt'), 'w')  
        ftrain      = open(os.path.join(saveBasePath,'train.txt'), 'w')  
        fval        = open(os.path.join(saveBasePath,'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()
        print("Generate txt in ImageSets done.")

    if annotation_mode == 0 or annotation_mode == 2:
        print("Generate 2007_train.txt and 2007_val.txt for train.")
        type_index = 0
        for year, image_set in VOCdevkit_sets:
            image_ids = open(os.path.join(VOCdevkit_path, 'VOC%s/ImageSets/Main/%s.txt'%(year, image_set)), encoding='utf-8').read().strip().split()
            list_file = open('%s_%s.txt'%(year, image_set), 'w', encoding='utf-8')
            for image_id in image_ids:
                list_file.write('%s/VOC%s/JPEGImages/%s.jpg'%(os.path.abspath(VOCdevkit_path), year, image_id))

                convert_annotation(year, image_id, list_file)
                list_file.write('\n')
            photo_nums[type_index] = len(image_ids)
            type_index += 1
            list_file.close()
        print("Generate 2007_train.txt and 2007_val.txt for train done.")
        
        def printTable(List1, List2):
            for i in range(len(List1[0])):
                print("|", end=' ')
                for j in range(len(List1)):
                    print(List1[j][i].rjust(int(List2[j])), end=' ')
                    print("|", end=' ')
                print()

        str_nums = [str(int(x)) for x in nums]
        tableData = [
            classes, str_nums
        ]
        colWidths = [0]*len(tableData)
        len1 = 0
        for i in range(len(tableData)):
            for j in range(len(tableData[i])):
                if len(tableData[i][j]) > colWidths[i]:
                    colWidths[i] = len(tableData[i][j])
        printTable(tableData, colWidths)

        if photo_nums[0] <= 500:
            print("訓練集數量小於500，屬於較小的資料量，請注意設定較大的訓練世代（Epoch）以滿足足夠的梯度下降次數（Step）。")

        if np.sum(nums) == 0:
            print("在資料集中並未獲得任何目標，請注意修改classes_path對應自己的資料集，並且保證標籤名字正確，否則訓練將會沒有任何效果！")
            print("在資料集中並未獲得任何目標，請注意修改classes_path對應自己的資料集，並且保證標籤名字正確，否則訓練將會沒有任何效果！")
            print("在資料集中並未獲得任何目標，請注意修改classes_path對應自己的資料集，並且保證標籤名字正確，否則訓練將會沒有任何效果！")
            print("（重要的事情說三遍）。")

2、根據train,test,中的txt檔案，去檢索Annotations檔案中的xml格式的標籤資訊，轉化為txt格式的標籤資訊

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join

sets=['train', 'test',]

classes = ["fire","smoke"]#這裡輸入你的資料集類別


def convert(size, box):#讀取xml檔案中的資料，xywh
    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('Annotations/%s.xml'%(image_id),encoding='utf-8')#這裡是讀取xml的資料夾
    out_file = open('Annotations/%s.txt'%(image_id), 'w',encoding='utf-8')#存入txt檔案的資料夾
    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 image_set in sets:
    # if not os.path.exists('labels/'):
    #     os.makedirs('labels/')
    image_ids = open('ImageSets/Main/%s.txt'%(image_set)).read().strip().split()#讀取train.txt或者test.txt從而找到每個xml檔案的檔名，這裡的train.txt中僅包含檔名，不包好路徑。
    #list_file = open('%s.txt'%(image_set), 'w')
    for image_id in image_ids:
        #list_file.write('/root/object-detection/yolov5-master/data/police_obj/images/%s.jpg\n'%(image_id))#從寫train.txt或者test.txt檔案，把圖片檔案的絕對路徑寫入，方便讀取圖片
        convert_annotation(image_id)
    #list_file.close()

3、根據train,test,中的txt檔案，將圖片分開

# -*- coding: UTF-8 -*-
# !/usr/bin/env python
import sys
import re
from PIL import Image

#sys.path.append('E:\\CODE')
# f1 = open('E:\CODE\TX\dir.txt','r')
# f2 = open('E:\CODE\TX\dir.txt','w+')
# for line in f1.readlines():
#    if re.findall(' 1',line): #查詢“空格1”的行 每行的格式000005 -1\n 000007
#       f2.write(line)#把查詢到的行寫入f2.
# f1.close()
# f2.close()
# data = []
import numpy as np

data = []
for line in open("ImageSets/Main/test.txt", "r"):  # 設定檔案物件並讀取每一行檔案
    data.append(line)
# print(data)
# f3 = open('E:\CODE\TX\dir.txt','r')
for a in data:
    #  print(a)
    # line3=line2[:-4] #讀取每行去掉後四位的數#
    im = Image.open('JPEGImages/{}.jpg'.format(a[:-1]))  # 開啟改路徑下的line3記錄的的檔名
    im.save('fenli_image/{}.jpg'.format(a[:-1]))  # 把資料夾中指定的檔名稱的圖片另存到該路徑下
    im.close()

4、最後達到yolov5支援的資料組織形式

mydaya-------image -----test
         |           |
         |           |__train
         |
         |
         |---labels-----test
                      |
                      |__train