def random_sized_crop_list()

in slowfast/datasets/cv2_transform.py [0:0]

• 36 lines of code
• 10 McCabe index (conditional complexity)

def random_sized_crop_list(images, size, crop_area_fraction=0.08):
    """
    Perform random sized cropping on the given list of images. Random crop with
        size 8% - 100% image area and aspect ratio in [3/4, 4/3].
    Args:
        images (list): image to crop.
        size (int): size to crop.
        area_frac (float): area of fraction.
    Returns:
        (list): list of cropped image.
    """
    for _ in range(0, 10):
        height = images[0].shape[0]
        width = images[0].shape[1]
        area = height * width
        target_area = np.random.uniform(crop_area_fraction, 1.0) * area
        aspect_ratio = np.random.uniform(3.0 / 4.0, 4.0 / 3.0)
        w = int(round(math.sqrt(float(target_area) * aspect_ratio)))
        h = int(round(math.sqrt(float(target_area) / aspect_ratio)))
        if np.random.uniform() < 0.5:
            w, h = h, w
        if h <= height and w <= width:
            if height == h:
                y_offset = 0
            else:
                y_offset = np.random.randint(0, height - h)
            if width == w:
                x_offset = 0
            else:
                x_offset = np.random.randint(0, width - w)
            y_offset = int(y_offset)
            x_offset = int(x_offset)

            croppsed_images = []
            for image in images:
                cropped = image[
                    y_offset : y_offset + h, x_offset : x_offset + w, :
                ]
                assert (
                    cropped.shape[0] == h and cropped.shape[1] == w
                ), "Wrong crop size"
                cropped = cv2.resize(
                    cropped, (size, size), interpolation=cv2.INTER_LINEAR
                )
                croppsed_images.append(cropped.astype(np.float32))
            return croppsed_images

    return [center_crop(size, scale(size, image)) for image in images]