@dataclass
class VisionTransformerArgs:
    """Arguments to the VisionTransformerForSegmentation."""
    image_size: int = 128
    patch_size: int = 16
    in_channels: int = 3
    out_channels: int = 3
    embed_size: int = 768
    num_blocks: int = 12
    num_heads: int = 8
    dropout: float = 0.2
# end class