*   Added a `use_causal_mask` call time argument to the layer. Passing
            `use_causal_mask=True` will compute a causal attention mask, and
            optionally combine it with any `attention_mask` passed in directly
            when calling the layer.
    *   Added `ignore_class` argument in the loss
        `SparseCategoricalCrossentropy` and metrics `IoU` and `MeanIoU`, to