pixellab: Распознавание на фото по видео

Всем привет! Пытаюсь сделать распознfвание на фото по видео https://www.youtube.com/watch?v=X8-mgyRAr0w&t=122s но получаю ошибку

NotImplementedError: Save or restore weights that is not an instance of tf.Variable is not supported in h5, use save_format='tf' instead. Got a model or layer Conv2D with weights [<KerasVariable shape=(7, 7, 3, 64), dtype=float32, path=conv1/kernel>, ]

Код:

import os
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
from pixellib.instance import instance_segmentation


def object_detection_on_an_image():
    segment_image = instance_segmentation()
    segment_image.load_model(r"C:\Users\Саша\PycharmProjects\TenserFlowTests\mask_rcnn_coco.h5")

    target_class = segment_image.select_target_classes(person=True)

    result = segment_image.segmentImage(
        # image_path="1city.jpg",
        # image_path="2cars_people.jpeg",
        image_path="3silicon_valley.jpg",
        show_bboxes=True,
        segment_target_classes=target_class,
        # extract_segmented_objects=True,
        # save_extracted_objects=True,
        output_image_name="output.jpg"
    )

    # print(result[0]["scores"])
    objects_count = len(result[0]["scores"])
    print(f"Найдено объектов: {objects_count}")


def main():
    object_detection_on_an_image()


if __name__ == '__main__':
    main()

Информация:

Версия: python 3.11

Файлы: