syna.core module

Core — Tensor and autograd primitives.

Core Tensor, Parameter, Config and autograd Function primitives used across the syna library. This module contains the lightweight Tensor container and the Function base class which implement forward/backward for automatic differentiation.

class syna.core.Config

Bases: object

Global config flags affecting backprop and training behavior.

enable_backprop = True

train = True

class syna.core.Function

Bases: object

Base Function for forward/backward ops used in autograd.

Subclasses should implement forward (numpy arrays -> numpy arrays) and backward (Tensor grads -> Tensor grads).

backward(*args: Tensor) → Tensor | list[Tensor]

forward(*args: ndarray) → ndarray

class syna.core.Parameter(data, name: str | None = None)

Bases: Tensor

A thin wrapper for trainable parameters (keeps API separate).

class syna.core.Tensor(data, name: str | None = None)

Bases: object

Simple Tensor container holding data, gradient and creator Function.

Most operator behavior delegates to syna.functions.* helpers so this class focuses on bookkeeping for autograd.

property T

backward(retain_grad=False, create_graph=False) → None

Run backpropagation to compute gradients of inputs.

Args:

retain_grad: if False, intermediate gradients are cleared to save memory. create_graph: if True, create graph for higher-order gradients.

cleargrad() → None

Clear stored gradient.

property dtype

max(**kwargs)

min(**kwargs)

property ndim

reshape(*shape: int)

set_creator(func: Function) → None

Mark this tensor as created by func (used for backprop ordering).

property shape

property size

sum(axis=None, keepdims=False)

transpose(*axes: int)

unchain() → None

Remove reference to creator to break the computational graph.

unchain_backward()

Remove creators for all upstream tensors (useful for freeing graph).

syna.core.arange(start, stop=None, step=1, dtype=None, requires_grad: bool = False, name: str | None = None) → Tensor

Return a 1-D tensor with values from start to stop (exclusive).

syna.core.as_array(x) → ndarray

Convert scalars to numpy arrays; leave arrays unchanged.

syna.core.as_tensor(obj) → Tensor

Ensure obj is a Tensor; convert scalars/arrays to Tensor if needed.

Delegates to tensor(…), which follows PyTorch-style semantics.

syna.core.eye(n, m=None, dtype=None, requires_grad: bool = False, name: str | None = None) → Tensor

Return a 2-D identity matrix (or rectangular identity if m is given).

syna.core.full(shape, fill_value, dtype=None, requires_grad: bool = False, name: str | None = None) → Tensor

Return a tensor of shape shape filled with fill_value.

shape may be an int or a tuple/list of ints (matches numpy/torch style).

syna.core.full_like(x, fill_value, dtype=None, requires_grad: bool = False, name: str | None = None) → Tensor

Return a tensor with the same shape as x filled with fill_value.

x may be a Tensor or array-like.

syna.core.no_grad()

Context manager to disable gradient tracking.

syna.core.ones(*shape, dtype=None, requires_grad: bool = False, name: str | None = None) → Tensor

Return a tensor filled with ones.

syna.core.ones_like(x, dtype=None, requires_grad: bool = False, name: str | None = None) → Tensor

Return a tensor of ones with the same shape as x (Tensor or array-like).

syna.core.rand(*shape, dtype=None, requires_grad: bool = False, name: str | None = None) → Tensor

Return a tensor with uniform random values in [0, 1).

syna.core.randint(low, high=None, size=None, dtype=None, requires_grad: bool = False, name: str | None = None) → Tensor

Return random integers from low (inclusive) to high (exclusive).

syna.core.randn(*shape, dtype=None, requires_grad: bool = False, name: str | None = None) → Tensor

Return a tensor with samples from the standard normal distribution.

syna.core.range(start, stop=None, step=1, dtype=None, requires_grad: bool = False, name: str | None = None) → Tensor

Alias for arange to match torch.range-like convenience (behaves like arange).

syna.core.tensor(data, dtype=None, requires_grad: bool = False, name: str | None = None) → Tensor

Tensor factory.

Args:

data: array-like or scalar. dtype: numpy dtype (optional). requires_grad: if True, the returned Tensor is a leaf that will accumulate gradients. name: optional name for the Tensor.

syna.core.test_mode()

Context manager to set train flag to False.

syna.core.using_config(name: str, value: bool)

Temporarily set a Config attribute inside a context.

syna.core.zeros(*shape, dtype=None, requires_grad: bool = False, name: str | None = None) → Tensor

Return a tensor filled with zeros.

syna.core.zeros_like(x, dtype=None, requires_grad: bool = False, name: str | None = None) → Tensor

Return a tensor of zeros with the same shape as x (Tensor or array-like).