array_reduce_max

ArrayReduceMaxLayer

ArrayReduceMaxLayer(
    name=None,
    input_dtype=None,
    output_dtype=None,
    default_value=0.0,
    **kwargs
)

Bases: BaseLayer

Reduces the last dimension of a tensor by taking the maximum.

Input: (..., N) Output: (...)

NaN values in the result are replaced with the configured default_value.

Source code in src/kamae/keras/core/layers/array_reduce_max.py

def __init__(
    self,
    name: Optional[str] = None,
    input_dtype: Optional[str] = None,
    output_dtype: Optional[str] = None,
    default_value: float = 0.0,
    **kwargs: Any,
) -> None:
    super().__init__(
        name=name, input_dtype=input_dtype, output_dtype=output_dtype, **kwargs
    )
    self.default_value = default_value