Struct Tensor 

pub struct Tensor {
    pub data: Vec<f32>,
    pub shape: Vec<usize>,
}

Basic tensor operations for GNN computations

Fields

data: Vec<f32>

Flattened tensor data

shape: Vec<usize>

Shape of the tensor (dimensions)

Implementations

impl Tensor

pub fn new(data: Vec<f32>, shape: Vec<usize>) -> Result<Self>

Create a new tensor from data and shape

Arguments

• data - Flattened tensor data
• shape - Dimensions of the tensor

Returns

A new Tensor instance

Errors

Returns GnnError::InvalidShape if data length doesn’t match shape

pub fn zeros(shape: &[usize]) -> Result<Self>

Create a zero-filled tensor with the given shape

Arguments

• shape - Dimensions of the tensor

Returns

A new zero-filled Tensor

Errors

Returns GnnError::InvalidShape if shape is empty or contains zero

pub fn from_vec(data: Vec<f32>) -> Self

Create a 1D tensor from a vector

Arguments

• data - Vector data

Returns

A new 1D Tensor

pub fn dot(&self, other: &Tensor) -> Result<f32>

Compute dot product with another tensor (both must be 1D)

Arguments

• other - Another tensor to compute dot product with

Returns

The dot product as a scalar

Errors

Returns GnnError::DimensionMismatch if tensors are not 1D or have different lengths

pub fn matmul(&self, other: &Tensor) -> Result<Tensor>

Matrix multiplication

Arguments

• other - Another tensor to multiply with

Returns

The result of matrix multiplication

Errors

Returns GnnError::DimensionMismatch if dimensions are incompatible

pub fn add(&self, other: &Tensor) -> Result<Tensor>

Element-wise addition

Arguments

• other - Another tensor to add

Returns

The sum of the two tensors

Errors

Returns GnnError::DimensionMismatch if shapes don’t match

pub fn scale(&self, scalar: f32) -> Tensor

Scalar multiplication

Arguments

• scalar - Scalar value to multiply by

Returns

A new tensor with all elements scaled

pub fn relu(&self) -> Tensor

ReLU activation function (max(0, x))

Returns

A new tensor with ReLU applied element-wise

pub fn sigmoid(&self) -> Tensor

Sigmoid activation function (1 / (1 + e^(-x))) with numerical stability

Returns

A new tensor with sigmoid applied element-wise

pub fn tanh(&self) -> Tensor

Tanh activation function

Returns

A new tensor with tanh applied element-wise

pub fn l2_norm(&self) -> f32

Compute L2 norm (Euclidean norm) with improved precision

Returns

The L2 norm of the tensor

pub fn normalize(&self) -> Result<Tensor>

Normalize the tensor to unit L2 norm

Returns

A normalized tensor

Errors

Returns GnnError::InvalidInput if norm is zero

pub fn as_slice(&self) -> &[f32]

Get a slice view of the tensor data

Returns

A slice reference to the underlying data

pub fn into_vec(self) -> Vec<f32>

Consume the tensor and return the underlying vector

Returns

The vector containing the tensor data

pub fn len(&self) -> usize

Get the number of elements in the tensor

pub fn is_empty(&self) -> bool

Check if the tensor is empty

Trait Implementations

impl Clone for Tensor

fn clone(&self) -> Tensor

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Tensor

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

Formats the value using the given formatter.

impl PartialEq for Tensor

fn eq(&self, other: &Tensor) -> 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 Tensor