[][src]Struct onnx_pb::AttributeProto

pub struct AttributeProto {
    pub name: String,
    pub ref_attr_name: String,
    pub doc_string: String,
    pub type: i32,
    pub f: f32,
    pub i: i64,
    pub s: Vec<u8>,
    pub t: Option<TensorProto>,
    pub g: Option<GraphProto>,
    pub sparse_tensor: Option<SparseTensorProto>,
    pub floats: Vec<f32>,
    pub ints: Vec<i64>,
    pub strings: Vec<Vec<u8>>,
    pub tensors: Vec<TensorProto>,
    pub graphs: Vec<GraphProto>,
    pub sparse_tensors: Vec<SparseTensorProto>,
}

Attributes

A named attribute containing either singular float, integer, string, graph, and tensor values, or repeated float, integer, string, graph, and tensor values. An AttributeProto MUST contain the name field, and only one of the following content fields, effectively enforcing a C/C++ union equivalent.

Fields

name: String

The name field MUST be present for this version of the IR.

namespace Attribute

ref_attr_name: String

if ref_attr_name is not empty, ref_attr_name is the attribute name in parent function. In this case, this AttributeProto does not contain data, and it's a reference of attribute in parent scope. NOTE: This should ONLY be used in function (sub-graph). It's invalid to be used in main graph.

doc_string: String

A human-readable documentation for this attribute. Markdown is allowed.

type: i32

The type field MUST be present for this version of the IR. For 0.0.1 versions of the IR, this field was not defined, and implementations needed to use has_field hueristics to determine which value field was in use. For IR_VERSION 0.0.2 or later, this field MUST be set and match the f|i|s|t|... field in use. This change was made to accomodate proto3 implementations.

discriminator that indicates which field below is in use

f: f32

Exactly ONE of the following fields must be present for this version of the IR

float

i: i64

int

s: Vec<u8>

UTF-8 string

t: Option<TensorProto>

tensor value

g: Option<GraphProto>

graph

sparse_tensor: Option<SparseTensorProto>

sparse tensor value

floats: Vec<f32>

list of floats

ints: Vec<i64>

list of ints

strings: Vec<Vec<u8>>

list of UTF-8 strings

tensors: Vec<TensorProto>

list of tensors

graphs: Vec<GraphProto>

list of graph

sparse_tensors: Vec<SparseTensorProto>

list of sparse tensors

Implementations

impl AttributeProto[src]

pub fn type(&self) -> AttributeType[src]

Returns the enum value of type, or the default if the field is set to an invalid enum value.

pub fn set_type(&mut self, value: AttributeType)[src]

Sets type to the provided enum value.

Trait Implementations

impl Clone for AttributeProto[src]

impl Debug for AttributeProto[src]

impl Default for AttributeProto[src]

impl Message for AttributeProto[src]

impl PartialEq<AttributeProto> for AttributeProto[src]

impl StructuralPartialEq for AttributeProto[src]

Auto Trait Implementations

Blanket Implementations

impl<T> Any for T where
    T: 'static + ?Sized
[src]

impl<T> Borrow<T> for T where
    T: ?Sized
[src]

impl<T> BorrowMut<T> for T where
    T: ?Sized
[src]

impl<T> From<T> for T[src]

impl<T, U> Into<U> for T where
    U: From<T>, 
[src]

impl<T> ToOwned for T where
    T: Clone
[src]

type Owned = T

The resulting type after obtaining ownership.

impl<T, U> TryFrom<U> for T where
    U: Into<T>, 
[src]

type Error = Infallible

The type returned in the event of a conversion error.

impl<T, U> TryInto<U> for T where
    U: TryFrom<T>, 
[src]

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.