def download_terra_incognita()

in domainbed/scripts/download.py [0:0]

• 53 lines of code
• 12 McCabe index (conditional complexity)

def download_terra_incognita(data_dir):
    # Original URL: https://beerys.github.io/CaltechCameraTraps/
    # New URL: http://lila.science/datasets/caltech-camera-traps

    full_path = stage_path(data_dir, "terra_incognita")

    download_and_extract(
        "https://lilablobssc.blob.core.windows.net/caltechcameratraps/eccv_18_all_images_sm.tar.gz",
        os.path.join(full_path, "terra_incognita_images.tar.gz"))

    download_and_extract(
        "https://lilablobssc.blob.core.windows.net/caltechcameratraps/labels/caltech_camera_traps.json.zip",
        os.path.join(full_path, "caltech_camera_traps.json.zip"))

    include_locations = ["38", "46", "100", "43"]

    include_categories = [
        "bird", "bobcat", "cat", "coyote", "dog", "empty", "opossum", "rabbit",
        "raccoon", "squirrel"
    ]

    images_folder = os.path.join(full_path, "eccv_18_all_images_sm/")
    annotations_file = os.path.join(full_path, "caltech_images_20210113.json")
    destination_folder = full_path

    stats = {}

    if not os.path.exists(destination_folder):
        os.mkdir(destination_folder)

    with open(annotations_file, "r") as f:
        data = json.load(f)

    category_dict = {}
    for item in data['categories']:
        category_dict[item['id']] = item['name']

    for image in data['images']:
        image_location = image['location']

        if image_location not in include_locations:
            continue

        loc_folder = os.path.join(destination_folder,
                                  'location_' + str(image_location) + '/')

        if not os.path.exists(loc_folder):
            os.mkdir(loc_folder)

        image_id = image['id']
        image_fname = image['file_name']

        for annotation in data['annotations']:
            if annotation['image_id'] == image_id:
                if image_location not in stats:
                    stats[image_location] = {}

                category = category_dict[annotation['category_id']]

                if category not in include_categories:
                    continue

                if category not in stats[image_location]:
                    stats[image_location][category] = 0
                else:
                    stats[image_location][category] += 1

                loc_cat_folder = os.path.join(loc_folder, category + '/')

                if not os.path.exists(loc_cat_folder):
                    os.mkdir(loc_cat_folder)

                dst_path = os.path.join(loc_cat_folder, image_fname)
                src_path = os.path.join(images_folder, image_fname)

                shutil.copyfile(src_path, dst_path)

    shutil.rmtree(images_folder)
    os.remove(annotations_file)