import os import random import shutil def extract_images(source_folder, destination_folder): count = 0 for root, _, files in os.walk(source_folder): for file in files: if file.endswith(('jpg', '.png')): src_path = os.path.join(root, file) dst_path = os.path.join(destination_folder, f"{count:05d}" + os.path.splitext(file)[1]) shutil.copy(src_path, dst_path) count += 1 def split_data(data_folder): train_folder = f"{data_folder}/train" validation_folder = f"{data_folder}/validation" test_folder = f"{data_folder}/test" for folder in [train_folder, validation_folder, test_folder]: if not os.path.exists(folder): os.makedirs(folder) image_files = [f for f in os.listdir(data_folder) if os.path.isfile(os.path.join(data_folder, f))] random.shuffle(image_files) total_images = len(image_files) train_count = int(0.7 * total_images) validation_count = int(0.2 * total_images) for i in range(train_count): shutil.move(os.path.join(data_folder, image_files[i]), train_folder) for i in range(train_count, train_count + validation_count): shutil.move(os.path.join(data_folder, image_files[i]), validation_folder) for i in range(train_count + validation_count, total_images): shutil.move(os.path.join(data_folder, image_files[i]), test_folder) if __name__ == "__main__": source_folder = "manga/" destination_folder = "data/" extract_images(source_folder, destination_folder) data_folder = "data/" split_data(data_folder)