def make_concepts_targets_and_randoms()

in tcav/tcav_examples/image_models/imagenet/download_and_make_datasets.py [0:0]

• 22 lines of code
• 6 McCabe index (conditional complexity)

def make_concepts_targets_and_randoms(source_dir, number_of_images_per_folder, number_of_random_folders):
    # Run script to download data to source_dir
    if not gfile.exists(source_dir):
        gfile.makedirs(source_dir)
    if not gfile.exists(os.path.join(source_dir,'broden1_224/')) or not gfile.exists(os.path.join(source_dir,'inception5h')):
        subprocess.call(['bash' , 'FetchDataAndModels.sh', source_dir])

    # Determine classes that we will fetch
    imagenet_classes = ['zebra']
    broden_concepts = ['striped', 'dotted', 'zigzagged']

    # make targets from imagenet
    imagenet_dataframe = fetcher.make_imagenet_dataframe("./imagenet_url_map.csv")
    for image in imagenet_classes:
        fetcher.fetch_imagenet_class(source_dir, image, number_of_images_per_folder, imagenet_dataframe)

    # Make concepts from broden
    for concept in broden_concepts:
        fetcher.download_texture_to_working_folder(broden_path=os.path.join(source_dir, 'broden1_224'),
                                                   saving_path=source_dir,
                                                   texture_name=concept,
                                                   number_of_images=number_of_images_per_folder)

    # Make random folders. If we want to run N random experiments with tcav, we need N+1 folders.
    fetcher.generate_random_folders(
        working_directory=source_dir,
        random_folder_prefix="random500",
        number_of_random_folders=number_of_random_folders+1,
        number_of_examples_per_folder=number_of_images_per_folder,
        imagenet_dataframe=imagenet_dataframe
    )