Bilişim dünyasına kaliteli, özgün ve Türkçe içerikler kazandırmayı hedefleyen bir platform..

PASCAL to COCO Converter With Python Script

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

def pascal_voc_to_coco(xml_folder_path):
    annotations = []
    classes = {}
    data = {
        "annotations": annotations,
        "categories": [],
        "images": []
    }

    class_id = 0

    for xml_file in os.listdir(xml_folder_path):
        if not xml_file.endswith(".xml"):
            continue
        
        xml_path = os.path.join(xml_folder_path, xml_file)
        tree = ET.parse(xml_path)
        root = tree.getroot()

        filename = root.find("filename").text
        image_id = int(root.find("./size/depth").text)

        image_info = {
            "id": image_id,
            "file_name": filename
        }
        data["images"].append(image_info)

        for obj in root.findall("object"):
            name = obj.find("name").text
            xmin = int(obj.find("bndbox/xmin").text)
            ymin = int(obj.find("bndbox/ymin").text)
            xmax = int(obj.find("bndbox/xmax").text)
            ymax = int(obj.find("bndbox/ymax").text)

            if name not in classes:
                classes[name] = class_id
                class_info = {
                    "id": class_id,
                    "name": name
                }
                data["categories"].append(class_info)
                class_id += 1

            class_id = classes[name]

            annotation = {
                "image_id": image_id,
                "bbox": [xmin, ymin, xmax - xmin, ymax - ymin],
                "category_id": class_id,
                "id": len(annotations) + 1,
                "iscrowd": 0
            }
            annotations.append(annotation)

        json_filename = os.path.splitext(xml_file)[0] + ".json"
        json_path = os.path.join(xml_folder_path, json_filename)

        with open(json_path, "w") as file:
            json.dump(data, file, indent=4)

        annotations = []
        classes = {}
        data = {
            "annotations": annotations,
            "categories": [],
            "images": []
        }

        class_id = 0

    print("Conversion complete.")

xml_folder_path = "C:\\Users\\USER-PC\\Desktop\\kaggle-sainfoin-dataset\\test\\"
#xml_folder_path = "C:\\Users\\USER-PC\\Desktop\\kaggle-sainfoin-dataset\\train\\"
pascal_voc_to_coco(xml_folder_path)