[PYTHON] Convert xml format data to txt format data (yolov3)

Preface

When I try to detect an object with tensorflow using yolo, the data is often in xml format and cannot be applied to yolo. Then let's make it ourselves.

Code actually created and used

import xml.etree.ElementTree as ET
import sys , os
import glob

cate_list = ["Car","Pedestrian","Truck","Signal","Signs","Bicycle","Motorbike","Bus","SVehicle","Train"]

with open("voc_classes.txt","w") as f:
    f.write('\n'.join(cate_list))
    
def class_encord(class_name):
    cate_id = {"Car":0,"Pedestrian":1,"Truck":2,"Signal":3,"Signs":4,"Bicycle":5,"Motorbike":6,"Bus":7,"SVehicle":8,"Train":9}
    return cate_id[class_name]

def convert(data_file,list_file):
    in_file = open(data_file)
    tree = ET.parse(in_file)
    root = tree.getroot()
    for obj in root.iter("item"):
        cate = obj.find("category").text
        cate = cate.lstrip("\n").lstrip("   ")
        cate = cate.rstrip("    ").rstrip("\n")
        category_id = class_encord(cate)
        xmlbox = obj.find("box2d")
        data = [int(float(xmlbox.find("x1").text)),int(float(xmlbox.find("x2").text)),int(float(xmlbox.find("y1").text)),int(float(xmlbox.find("y2").text))]
        list_file.write(" " + ",".join([str(a) for a in data]) + "," + str(category_id))

data_file_list = glob.glob("Annotations/*.xml")

list_file = open("2007_train.txt","w")
for data_file in data_file_list:
    jpg_file = "train_" + data_file.rstrip(".xml") + ".jpg "
    list_file.write(jpg_file)
    convert(data_file,list_file)
    list_file.write("\n")
list_file.close()

It's not generalized, so it's very hard to see (; ^ ω ^) I will list the parameters that can be used by changing it

• cate_list: List of objects you want to detect.
• open ("voc_classes.txt"): If you rename the txt file, the object list will be output to txt.
• cate_id: Enter the object and its corresponding value.
• list_file: Text data for the completed training.

Code flow

yolo uses the txt that describes the object, so output it.

cate_list = ["Car","Pedestrian","Truck","Signal","Signs","Bicycle","Motorbike","Bus","SVehicle","Train"]

with open("voc_classes.txt","w") as f:
    f.write('\n'.join(cate_list))

A function for encoding the object name and id.

def class_encord(class_name):
    cate_id = {"Car":0,"Pedestrian":1,"Truck":2,"Signal":3,"Signs":4,"Bicycle":5,"Motorbike":6,"Bus":7,"SVehicle":8,"Train":9}
    return cate_id[class_name]

A function that converts xml data to a txt file. What you are doing is as simple as reading with tml.etree.ElementTree, fetching and writing each data.

def convert(data_file,list_file):
    in_file = open(data_file)
    tree = ET.parse(in_file)
    root = tree.getroot()
    for obj in root.iter("item"):
        cate = obj.find("category").text
        cate = cate.lstrip("\n").lstrip("   ")
        cate = cate.rstrip("    ").rstrip("\n")
        category_id = class_encord(cate)
        xmlbox = obj.find("box2d")
        data = [int(float(xmlbox.find("x1").text)),int(float(xmlbox.find("x2").text)),int(float(xmlbox.find("y1").text)),int(float(xmlbox.find("y2").text))]
        list_file.write(" " + ",".join([str(a) for a in data]) + "," + str(category_id))

All that's left is to do it.

data_file_list = glob.glob("Annotations/*.xml")

list_file = open("2007_train.txt","w")
for data_file in data_file_list:
    jpg_file = "train_" + data_file.rstrip(".xml") + ".jpg "
    list_file.write(jpg_file)
    convert(data_file,list_file)
    list_file.write("\n")
list_file.close()

Object detection is interesting (^ ▽ ^) Data organization is difficult.