Struct TensorProto 

pub struct TensorProto {

    pub dtype: i32,
    pub tensor_shape: Option<TensorShapeProto>,
    pub version_number: i32,
    pub tensor_content: Vec<u8>,
    pub half_val: Vec<i32>,
    pub float_val: Vec<f32>,
    pub double_val: Vec<f64>,
    pub int_val: Vec<i32>,
    pub string_val: Vec<Vec<u8>>,
    pub scomplex_val: Vec<f32>,
    pub int64_val: Vec<i64>,
    pub bool_val: Vec<bool>,
    pub dcomplex_val: Vec<f64>,
    pub resource_handle_val: Vec<ResourceHandleProto>,
    pub variant_val: Vec<VariantTensorDataProto>,
    pub uint32_val: Vec<u32>,
    pub uint64_val: Vec<u64>,
}

Protocol buffer representing a tensor.

Fields

dtype: i32

tensor_shape: Option<TensorShapeProto>

Shape of the tensor. TODO(touts): sort out the 0-rank issues.

version_number: i32

Version number.

In version 0, if the “repeated xxx” representations contain only one element, that element is repeated to fill the shape. This makes it easy to represent a constant Tensor with a single value.

tensor_content: Vec<u8>

Serialized raw tensor content from either Tensor::AsProtoTensorContent or memcpy in tensorflow::grpc::EncodeTensorToByteBuffer. This representation can be used for all tensor types. The purpose of this representation is to reduce serialization overhead during RPC call by avoiding serialization of many repeated small items.

half_val: Vec<i32>

DT_HALF, DT_BFLOAT16. Note that since protobuf has no int16 type, we’ll have some pointless zero padding for each value here.

float_val: Vec<f32>

DT_FLOAT.

double_val: Vec<f64>

DT_DOUBLE.

int_val: Vec<i32>

DT_INT32, DT_INT16, DT_INT8, DT_UINT8.

string_val: Vec<Vec<u8>>

DT_STRING

scomplex_val: Vec<f32>

DT_COMPLEX64. scomplex_val(2i) and scomplex_val(2i+1) are real and imaginary parts of i-th single precision complex.

int64_val: Vec<i64>

DT_INT64

bool_val: Vec<bool>

DT_BOOL

dcomplex_val: Vec<f64>

DT_COMPLEX128. dcomplex_val(2i) and dcomplex_val(2i+1) are real and imaginary parts of i-th double precision complex.

resource_handle_val: Vec<ResourceHandleProto>

DT_RESOURCE

variant_val: Vec<VariantTensorDataProto>

DT_VARIANT

uint32_val: Vec<u32>

DT_UINT32

uint64_val: Vec<u64>

DT_UINT64

Implementations

impl TensorProto

pub fn dtype(&self) -> DataType

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

pub fn set_dtype(&mut self, value: DataType)

Sets dtype to the provided enum value.

Trait Implementations

impl Clone for TensorProto

fn clone(&self) -> TensorProto

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TensorProto

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

Formats the value using the given formatter.

impl Default for TensorProto

fn default() -> Self

Returns the “default value” for a type.

impl From<TensorProto> for AttrValue

fn from(t: TensorProto) -> AttrValue

Converts to this type from the input type.

impl Message for TensorProto

fn encoded_len(&self) -> usize

Returns the encoded length of the message without a length delimiter.

fn clear(&mut self)

Clears the message, resetting all fields to their default.

fn encode<B>(&self, buf: &mut B) -> Result<(), EncodeError>

where B: BufMut, Self: Sized,

Encodes the message to a buffer.

fn encode_to_vec(&self) -> Vec<u8>

where Self: Sized,

Encodes the message to a newly allocated buffer.

fn encode_length_delimited<B>(&self, buf: &mut B) -> Result<(), EncodeError>

where B: BufMut, Self: Sized,

Encodes the message with a length-delimiter to a buffer.

fn encode_length_delimited_to_vec(&self) -> Vec<u8>

where Self: Sized,

Encodes the message with a length-delimiter to a newly allocated buffer.

fn decode<B>(buf: B) -> Result<Self, DecodeError>

where B: Buf, Self: Default,

Decodes an instance of the message from a buffer.

fn decode_length_delimited<B>(buf: B) -> Result<Self, DecodeError>

where B: Buf, Self: Default,

Decodes a length-delimited instance of the message from the buffer.

fn merge<B>(&mut self, buf: B) -> Result<(), DecodeError>

where B: Buf, Self: Sized,

Decodes an instance of the message from a buffer, and merges it into self.

fn merge_length_delimited<B>(&mut self, buf: B) -> Result<(), DecodeError>

where B: Buf, Self: Sized,

Decodes a length-delimited instance of the message from buffer, and merges it into self.

impl PartialEq for TensorProto

fn eq(&self, other: &TensorProto) -> 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 TryFrom<&Tensor> for TensorProto

type Error = Error

The type returned in the event of a conversion error.

fn try_from(from: &Tensor) -> TractResult<TensorProto>

Performs the conversion.

impl TryFrom<&TensorProto> for Tensor

type Error = Error

The type returned in the event of a conversion error.

fn try_from(t: &TensorProto) -> TractResult<Tensor>

Performs the conversion.

impl StructuralPartialEq for TensorProto