Module creation 

Tensor Creation Functions

Provides convenient functions for creating tensors with various initializations including zeros, ones, random values, ranges, and more.

Key Features

• Factory functions for common tensor initializations
• Random tensor generation with various distributions
• Range and linspace functions

@version 0.1.0 @author AutomataNexus Development Team

Functions

arange

Creates a 1D tensor with values from start to end (exclusive) with step.

diag

Creates a 2D tensor with the given diagonal values.

empty

Creates an uninitialized tensor (values are undefined).

eye

Creates a 2D identity matrix.

full

Creates a tensor filled with a specific value.

full_like

Creates a tensor with the same shape as another, filled with a value.

linspace

Creates a 1D tensor with num evenly spaced values from start to end.

logspace

Creates a 1D tensor with num logarithmically spaced values.

normal

Creates a tensor with normally distributed random values.

ones

Creates a tensor filled with ones.

ones_like

Creates a tensor with the same shape as another, filled with ones.

rand

Creates a tensor with uniformly distributed random values in [0, 1).

randint

Creates a tensor with random integers in [low, high).

randn

Creates a tensor with normally distributed random values (mean=0, std=1).

uniform

Creates a tensor with uniformly distributed random values in [low, high).

zeros

Creates a tensor filled with zeros.

zeros_like

Creates a tensor with the same shape as another, filled with zeros.