API REFERENCE/omnibias-keras

omnibias.keras.activations.registry

0.0.2a1AlphaPython >=3.10Apache-2.0

Keras 3 operator layers and activation paths implemented with keras.ops for TensorFlow, JAX, or Torch.

import omnibias.keras.activations.registry

Module contract & mathematical conventions

Activation registry (Keras backend): ActivationSpec and lookup.

The ActivationSpec dataclass is defined generically in omnibias.core.spec; this module re-exports it and maintains a process-wide registry so get_activation can resolve string names like "tanh" to their full spec. The kernels stored in each spec are written against keras.ops so they run on any Keras backend.

Shared formulas do not imply universal floating-point identity. Verify dtype, shape, derivative-order support, and the stated numerical assumptions for the path you use.

Module source ↗Source revision 9a2d73df0573Running reference examples →

Imports & aliases

These names share a definition with another public module. Follow a name for its full contract, parameters, and examples.

Import from this module	Canonical reference
ActivationSpec	omnibias.core.ActivationSpec

FUNCTION

get_activation

omnibias.keras.get_activationSource ↗

get_activation(name: str | ActivationSpec[Any]) -> ActivationSpec[Any]

Resolve a name (or pass-through spec) to an ActivationSpec.

Parameters

Name	Type & default	Contract
namepositional-or-keyword	str | ActivationSpec[Any]Required	See the operation contract and implementation below.

ReturnsActivationSpec[Any]

Explicit validation & failure cases

• When not isinstance(name, str), raises TypeError(f'Expected str or ActivationSpec, got {type(name).__name__}: {name!r}').
• When key not in _REGISTRY, raises KeyError(f'Unknown activation {name!r}. Known: {known}.').

These are explicit source guards. Backend operations may also raise for invalid shapes, dtypes, or unsupported devices.

Executed regression · tempered rejects bad scale

Recorded coverage confirms this test executed the API body. This example belongs to the pinned upstream test suite. It may use fixtures and imports from its full file. Run it from that checkout with its test dependencies installed.

Full file, imports & fixtures ↗

def test_tempered_rejects_bad_scale() -> None:
    with pytest.raises(ValueError):
        TemperedActivation("softplus", beta=1.0, scale="bogus")

python -m pytest "packages/omnibias-keras/tests/test_tempered_blocks.py::test_tempered_rejects_bad_scale" -q

Regression example · fastpath negative order raises

This example belongs to the pinned upstream test suite. It may use fixtures and imports from its full file. Run it from that checkout with its test dependencies installed.

Full file, imports & fixtures ↗

def test_fastpath_negative_order_raises() -> None:
    z = ops.convert_to_tensor(np.zeros(3))
    with pytest.raises(ValueError):
        get_activation("tanh").fastpath(z, -1)

python -m pytest packages/omnibias-keras/tests/test_activations.py -k test_fastpath_negative_order_raises -q

Read the implementation

def get_activation(name: str | ActivationSpec[Any]) -> ActivationSpec[Any]:
    """Resolve a name (or pass-through spec) to an :class:`ActivationSpec`."""
    if isinstance(name, ActivationSpec):
        return name
    if not isinstance(name, str):
        raise TypeError(
            f"Expected str or ActivationSpec, got {type(name).__name__}: {name!r}"
        )
    key = name.lower()
    if key not in _REGISTRY:
        known = ", ".join(sorted(set(_REGISTRY.keys())))
        raise KeyError(f"Unknown activation {name!r}. Known: {known}.")
    return _REGISTRY[key]

Other public import paths

• omnibias.keras.get_activation
• omnibias.keras.activations.get_activation
• omnibias.keras.activations.registry.get_activation

FUNCTION

is_registered

omnibias.keras.is_registeredSource ↗

is_registered(name: str) -> bool

True if name (or one of its aliases) is in the registry.

Parameters

Name	Type & default	Contract
namepositional-or-keyword	strRequired	See the operation contract and implementation below.

Returnsbool

Read the implementation

def is_registered(name: str) -> bool:
    """True if ``name`` (or one of its aliases) is in the registry."""
    return isinstance(name, str) and name.lower() in _REGISTRY

Other public import paths

• omnibias.keras.is_registered
• omnibias.keras.activations.is_registered
• omnibias.keras.activations.registry.is_registered

FUNCTION

list_activations

omnibias.keras.list_activationsSource ↗

list_activations() -> list[str]

Return the canonical (non-alias) activation names, sorted.

Returnslist[str]

Executed regression · all piecewise registered

Recorded coverage confirms this test executed the API body. This example belongs to the pinned upstream test suite. It may use fixtures and imports from its full file. Run it from that checkout with its test dependencies installed.

Full file, imports & fixtures ↗

def test_all_piecewise_registered() -> None:
    registered = set(list_activations())
    for name in _PIECEWISE_NAMES:
        assert name in registered, f"{name!r} not registered"

python -m pytest "packages/omnibias-keras/tests/test_piecewise.py::test_all_piecewise_registered" -q

Regression example · all expected activations registered

This example belongs to the pinned upstream test suite. It may use fixtures and imports from its full file. Run it from that checkout with its test dependencies installed.

Full file, imports & fixtures ↗

def test_all_expected_activations_registered() -> None:
    registered = set(list_activations())
    for name in _NAMES:
        assert name in registered, f"{name!r} not registered"

python -m pytest packages/omnibias-keras/tests/test_activations.py -k test_all_expected_activations_registered -q

Read the implementation

def list_activations() -> list[str]:
    """Return the canonical (non-alias) activation names, sorted."""
    return sorted({spec.name for spec in _REGISTRY.values()})

Other public import paths

• omnibias.keras.list_activations
• omnibias.keras.activations.list_activations
• omnibias.keras.activations.registry.list_activations

FUNCTION

register_activation

omnibias.keras.register_activationSource ↗

register_activation(spec: ActivationSpec[Any]) -> ActivationSpec[Any]

Register an ActivationSpec under its name and aliases.

Parameters

Name	Type & default	Contract
specpositional-or-keyword	ActivationSpec[Any]Required	See the operation contract and implementation below.

ReturnsActivationSpec[Any]

Explicit validation & failure cases

• When not spec.name, raises ValueError('ActivationSpec.name must be a non-empty string.').
• When name in _REGISTRY and _REGISTRY[name] is not spec, raises ValueError(f'Activation {name!r} is already registered with a different spec.').
• When akey in _REGISTRY and _REGISTRY[akey] is not spec, raises ValueError(f'Alias {alias!r} for activation {name!r} clashes with an existing entry.').

These are explicit source guards. Backend operations may also raise for invalid shapes, dtypes, or unsupported devices.

Read the implementation

def register_activation(spec: ActivationSpec[Any]) -> ActivationSpec[Any]:
    """Register an :class:`ActivationSpec` under its name and aliases."""
    if not spec.name:
        raise ValueError("ActivationSpec.name must be a non-empty string.")
    name = spec.name.lower()
    if name in _REGISTRY and _REGISTRY[name] is not spec:
        raise ValueError(
            f"Activation {name!r} is already registered with a different spec."
        )
    _REGISTRY[name] = spec
    for alias in spec.aliases:
        akey = alias.lower()
        if akey in _REGISTRY and _REGISTRY[akey] is not spec:
            raise ValueError(
                f"Alias {alias!r} for activation {name!r} clashes with an existing entry."
            )
        _REGISTRY[akey] = spec
    return spec

Other public import paths

• omnibias.keras.register_activation
• omnibias.keras.activations.register_activation
• omnibias.keras.activations.registry.register_activation

← Package overviewRunnable learning examples →