Enum TensorDType 

pub enum TensorDType {
    F32,
    F16,
    F64,
    I8,
    I16,
    I32,
    I64,
    U8,
    U16,
    U32,
    U64,
    Bool,
}

Canonical scalar dtype advertised by a model input or output.

Mirrors a pragmatic subset of the ONNX dtype list. Internally oxionnx stores tensor data as f32, so anything non-F32 signals a cast at the boundary (performed inside the pipeline layer).

Variants

F32

32-bit IEEE float.

F16

16-bit IEEE float.

F64

64-bit IEEE float.

I8

Signed 8-bit integer.

I16

Signed 16-bit integer.

I32

Signed 32-bit integer.

I64

Signed 64-bit integer.

U8

Unsigned 8-bit integer.

U16

Unsigned 16-bit integer.

U32

Unsigned 32-bit integer.

U64

Unsigned 64-bit integer.

Bool

Boolean.

Implementations

impl TensorDType

pub fn name(self) -> &'static str

Short canonical name matching ONNX nomenclature.

Trait Implementations

impl Clone for TensorDType

fn clone(&self) -> TensorDType

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for TensorDType

impl Debug for TensorDType

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

Formats the value using the given formatter.

impl Eq for TensorDType

impl Hash for TensorDType

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl PartialEq for TensorDType

fn eq(&self, other: &TensorDType) -> 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 StructuralPartialEq for TensorDType