The XML file generated by labelimg is converted to VOC format

Personal records

import os
import random
import xml.etree.ElementTree as ET

import numpy as np

from utils.utils import get_classes

#--------------------------------------------------------------------------------------------------------------------------------#
# annotation_mode Used to specify the contents of the file to be calculated at run time 
# annotation_mode by 0 Represents the entire label processing process , Including getting VOCdevkit/VOC2007/ImageSets Inside txt And for training 2007_train.txt、2007_val.txt
# annotation_mode by 1 On behalf of VOCdevkit/VOC2007/ImageSets Inside txt
# annotation_mode by 2 Stands for... For training 2007_train.txt、2007_val.txt
#--------------------------------------------------------------------------------------------------------------------------------#
annotation_mode     = 0
#-------------------------------------------------------------------#
#  It has to be changed , Used to generate 2007_train.txt、2007_val.txt Target information for 
#  And the... Used for training and prediction classes_path It's OK to be consistent 
#  If generated 2007_train.txt There is no target information in it 
#  So it's because classes Not set correctly 
#  Only in annotation_mode by 0 and 2 In force 
#-------------------------------------------------------------------#
classes_path        = 'model_data/voc_classes.txt'
#--------------------------------------------------------------------------------------------------------------------------------#
# trainval_percent Is used to specify the ( Training set + Verification set ) Ratio to test set , By default  ( Training set + Verification set ): Test set  = 9:1
# train_percent Is used to specify the ( Training set + Verification set ) The ratio of training set to verification set in , By default   Training set : Verification set  = 9:1
#  Only in annotation_mode by 0 and 1 In force 
#--------------------------------------------------------------------------------------------------------------------------------#
trainval_percent    = 0.9
train_percent       = 0.9
#-------------------------------------------------------#
#  Point to VOC The folder where the dataset is located 
#  By default, it points to... In the root directory VOC Data sets 
#-------------------------------------------------------#
VOCdevkit_path  = 'VOCdevkit'

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

#-------------------------------------------------------#
#  Count the number of targets 
#-------------------------------------------------------#
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(" No space is allowed in the folder path and picture name where the dataset is stored , Otherwise, normal model training will be affected , Please pay attention to the modification .")

    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(" The number of training sets is less than 500, It belongs to a small amount of data , Please pay attention to setting a larger training generation （Epoch） To meet sufficient gradient descent times （Step）.")

        if np.sum(nums) == 0:
            print(" No goals were achieved in the dataset , Please pay attention to the modification classes_path Corresponding to their own data set , And make sure the label name is correct , Otherwise, the training will have no effect ！")
            print(" No goals were achieved in the dataset , Please pay attention to the modification classes_path Corresponding to their own data set , And make sure the label name is correct , Otherwise, the training will have no effect ！")
            print(" No goals were achieved in the dataset , Please pay attention to the modification classes_path Corresponding to their own data set , And make sure the label name is correct , Otherwise, the training will have no effect ！")
            print("（ Important things are to be repeated for 3 times ）.")