for classification and return
        >>> # only the features
        >>> backbone = torchvision.models.mobilenet_v2(weights=MobileNet_V2_Weights.DEFAULT).features
        >>> # RetinaNet needs to know the number of
        >>> # output channels in a backbone. For mobilenet_v2, it's 1280,
        >>> # so we need to add it here
        >>> backbone.out_channels = 1280
        >>>
        >>> # let's make the network generate 5 x 3 anchors per spatial
        >>> # location, with 5 different sizes and 3 different aspect
        >>> # ratios. We have a Tuple[Tuple[int]] because each feature
        >>> # map could potentially have different sizes and
        >>> # aspect ratios
        >>> anchor_generator = AnchorGenerator(
        >>>     sizes=((32, 64, 128, 256, 512),),
        >>>     aspect_ratios=((0.5, 1.0, 2.0),)
        >>> )
        >>>
        >>> # put the pieces together inside a RetinaNet model
        >>> model = RetinaNet(backbone,
        >>>                   num_classes=2,
        >>>                   anchor_generator=anchor_generator)
        >>> model.eval()
        >>> x = [torch.rand(3, 300, 400), torch.rand(3, 500, 400)]
        >>> predictions = model(x)
    )