Struct SpecializationContext 

pub struct SpecializationContext {
    pub input_shapes: Vec<Vec<usize>>,
    pub device: Option<String>,
}

Context for graph specialization.

Fields

input_shapes: Vec<Vec<usize>>

Input shapes for specialization

device: Option<String>

Device target (if specified)

Implementations

impl SpecializationContext

pub fn from_shapes(shapes: &[TensorShape]) -> Self

Create a new specialization context from input shapes.

pub fn with_device(self, device: String) -> Self

Create a context with device specification.

Trait Implementations

impl Clone for SpecializationContext

fn clone(&self) -> SpecializationContext

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for SpecializationContext

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

Formats the value using the given formatter.

impl Hash for SpecializationContext

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 SpecializationContext

fn eq(&self, other: &SpecializationContext) -> 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 Eq for SpecializationContext

impl StructuralPartialEq for SpecializationContext