Struct ReductionOp 

pub struct ReductionOp<'a> {
    pub axes: Option<&'a [i32]>,
    pub keep_dims: bool,
}

Shape inference for reduction operators.

Fields

axes: Option<&'a [i32]>

Axes over which the reduction is applied.

Reduction ops take the axes as an attribute in ONNX opset <= 13 and an input in opset 18+.

keep_dims: bool

True if the reduced dimension is retained as a 1-sized dimension in the output.

Trait Implementations

impl<'a> Clone for ReductionOp<'a>

fn clone(&self) -> ReductionOp<'a>

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl<'a> Debug for ReductionOp<'a>

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl InferShapes for ReductionOp<'_>

fn infer_shapes( &self, inputs: &[SymTensor], _sym_gen: &mut SymbolGen, ) -> Result<Vec<SymTensor>, InferShapesError>

Infer the shapes and optionally values of an operator’s outputs given its inputs.

impl<'a> PartialEq for ReductionOp<'a>

fn eq(&self, other: &ReductionOp<'a>) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl<'a> StructuralPartialEq for ReductionOp<'a>