data_preparation.py

import os
import shutil
from sklearn.model_selection import train_test_split

def prepare_data(dataset_path):
    """
    Prepares the dataset by splitting it into training, validation, and test sets.

    Parameters:
    dataset_path (str): Path to the dataset.
    """
    images_path = os.path.join(dataset_path, 'images')
    yolo_annotations_path = os.path.join(dataset_path, 'yolo_annotations')

    # Paths to split datasets
    train_images_path = os.path.join(dataset_path, 'YOLO', 'train', 'images')
    val_images_path = os.path.join(dataset_path, 'YOLO', 'val', 'images')
    test_images_path = os.path.join(dataset_path, 'YOLO', 'test', 'images')

    train_annotations_path = os.path.join(dataset_path, 'YOLO', 'train', 'labels')
    val_annotations_path = os.path.join(dataset_path, 'YOLO', 'val', 'labels')
    test_annotations_path = os.path.join(dataset_path, 'YOLO', 'test', 'labels')

    # Create directories
    os.makedirs(train_images_path, exist_ok=True)
    os.makedirs(val_images_path, exist_ok=True)
    os.makedirs(test_images_path, exist_ok=True)
    os.makedirs(train_annotations_path, exist_ok=True)
    os.makedirs(val_annotations_path, exist_ok=True)
    os.makedirs(test_annotations_path, exist_ok=True)

    # Get list of all images
    all_images = [f for f in os.listdir(images_path) if f.endswith('.png')]
    train_images, val_test_images = train_test_split(all_images, test_size=0.3, random_state=42)
    val_images, test_images = train_test_split(val_test_images, test_size=0.33, random_state=42)

    # Function to copy images and annotations
    def copy_files(image_list, dest_image_path, dest_label_path):
        for image in image_list:
            image_path = os.path.join(images_path, image)
            label_path = os.path.join(yolo_annotations_path, image.replace('.png', '.txt'))

            shutil.copy(image_path, dest_image_path)
            shutil.copy(label_path, dest_label_path)

    # Copy files to respective directories
    copy_files(train_images, train_images_path, train_annotations_path)
    copy_files(val_images, val_images_path, val_annotations_path)
    copy_files(test_images, test_images_path, test_annotations_path)

    print("Dataset split into training, validation, and test sets.")

if __name__ == "__main__":
    prepare_data('Dataset')