torchwrench.nn.functional.others module¶

torchwrench.nn.functional.others.average_power(x: T_TensorOrArray, dim: int | tuple[int, ...] | None = -1) → T_TensorOrArray[source]¶

Compute average power of a signal along a specified dim/axis.

torchwrench.nn.functional.others.cat(tensors: list[Tensor] | tuple[Tensor, ...], dim: int = 0, *, out: Tensor | None = None) → Tensor[source]¶

torchwrench.nn.functional.others.concat(tensors: list[Tensor] | tuple[Tensor, ...], dim: int = 0, *, out: Tensor | None = None) → Tensor[source]¶

torchwrench.nn.functional.others.count_parameters(model: Module, *, recurse: bool = True, only_trainable: bool = False, buffers: bool = False) → int[source]¶

Returns the number of parameters in a module.

torchwrench.nn.functional.others.deep_equal(x: T, y: T, *args: T) → bool[source]¶

Recursive comparison between objects.

Supports Scalar-like, NDArrays, Tensors, DataFrames, Mapping and List-like objects. Unlike default equal, NaNs values are considered equal. Tensors and NDArrays of different shapes are supported and returns False.

torchwrench.nn.functional.others.find(value: Any, x: Tensor, *, default: None | Tensor | bool | int | float | complex = None, dim: int = -1) → LongTensor[source]¶

Return the index of the first occurrence of value in a tensor.

torchwrench.nn.functional.others.get_ndim(x: bool | int | float | complex | None | str | bytes | ndarray | generic | Tensor0D | Tensor | Iterable, *, use_first_for_list_tuple: bool = False, return_indicator: False = False, return_default_on_invalid: False = False, default: Any = -1, return_valid: bool | None = None) → int[source]¶

torchwrench.nn.functional.others.get_ndim(x: bool | int | float | complex | None | str | bytes | ndarray | generic | Tensor0D | Tensor | Iterable, *, use_first_for_list_tuple: bool = False, return_indicator: False = False, return_default_on_invalid: bool, default: U = -1, return_valid: bool | None = None) → int | U

torchwrench.nn.functional.others.get_ndim(x: bool | int | float | complex | None | str | bytes | ndarray | generic | Tensor0D | Tensor | Iterable, *, use_first_for_list_tuple: bool = False, return_indicator: True, return_default_on_invalid: False = False, default: Any = -1, return_valid: bool | None = None) → ndim[int]

torchwrench.nn.functional.others.get_ndim(x: bool | int | float | complex | None | str | bytes | ndarray | generic | Tensor0D | Tensor | Iterable, *, use_first_for_list_tuple: bool = False, return_indicator: True, return_default_on_invalid: bool, default: U = -1, return_valid: bool | None = None) → ndim[int | U]

Scan first argument to return its number of dimension(s). Works recursively with Tensors, numpy arrays and builtins types instances.

Note: Sets and dicts are considered as scalars with a ndim equal to 0.

Args:

x: Input value to scan. use_first_for_list_tuple: If True, use first value to determine ndim for list and tuple argument. Otherwise it will scan each value in argument to determine its shape. defaults to False. return_indicator: If True, returns a tuple containing a boolean indicator if the data has an homogeneous ndim instead of raising a ValueError. defaults to False. return_default_on_invalid: If True and return_indicator=False, returns the default value instead of raising a ValueError. defaults to False. default: Value to return if input is a heterogeneous list/tuple. defaults to (). return_valid: Deprecated. Use return_indicator instead.

Raises:

ValueError if input has an heterogeneous number of dimensions and return_valid=False. TypeError if input has an unsupported type.

torchwrench.nn.functional.others.get_shape(x: bool | int | float | complex | None | str | bytes | ndarray | generic | Tensor0D | Tensor | DataFrame | list | tuple | set | frozenset | dict, *, output_type: Callable[[tuple[int, ...]], T] = identity, use_first_for_list_tuple: bool = False, return_indicator: False = False, return_default_on_invalid: False = False, default: Any = (), return_valid: bool | None = None) → T[source]¶

torchwrench.nn.functional.others.get_shape(x: bool | int | float | complex | None | str | bytes | ndarray | generic | Tensor0D | Tensor | DataFrame | list | tuple | set | frozenset | dict, *, output_type: Callable[[tuple[int, ...]], T] = identity, use_first_for_list_tuple: bool = False, return_indicator: False = False, return_default_on_invalid: bool, default: U = (), return_valid: bool | None = None) → T | U

torchwrench.nn.functional.others.get_shape(x: bool | int | float | complex | None | str | bytes | ndarray | generic | Tensor0D | Tensor | DataFrame | list | tuple | set | frozenset | dict, *, output_type: Callable[[tuple[int, ...]], T] = identity, use_first_for_list_tuple: bool = False, return_indicator: True, return_default_on_invalid: False = False, default: Any = (), return_valid: bool | None = None) → shape[T]

torchwrench.nn.functional.others.get_shape(x: bool | int | float | complex | None | str | bytes | ndarray | generic | Tensor0D | Tensor | DataFrame | list | tuple | set | frozenset | dict, *, output_type: Callable[[tuple[int, ...]], T] = identity, use_first_for_list_tuple: bool = False, return_indicator: True, return_default_on_invalid: bool, default: U = (), return_valid: bool | None = None) → shape[T | U]

Scan first argument to return its shape. Works recursively with Tensors, numpy arrays and builtins types instances.

Note: Sets and dicts are considered as scalars with a shape equal to ().

Args:

x: Input value to scan. output_type: Output shape type. defaults to identity, which returns a tuple of ints. use_first_for_list_tuple: If True, use first value in sequences to determine shape for list and tuple argument. Otherwise it will scan each value in argument to determine its shape. defaults to False. return_indicator: If True, returns a tuple containing a boolean indicator if the data has an homogeneous shape instead of raising a ValueError. defaults to False. return_default_on_invalid: If True and return_indicator=False, returns the default value instead of raising a ValueError. defaults to False. default: Value to return if input is a heterogeneous list/tuple. This default value is NOT passed to the output_type() callable argument. defaults to (). return_valid: Deprecated. Use return_indicator instead.

Raises:

ValueError: if input has an heterogeneous shape and return_valid=False. TypeError: if input has an unsupported type.

torchwrench.nn.functional.others.mse(x1: Tensor, x2: Tensor, *, dim: int | tuple[int, ...] | None = None) → Tensor[source]¶

Mean squared error function.

torchwrench.nn.functional.others.ndim(x: bool | int | float | complex | None | str | bytes | ndarray | generic | Tensor0D | Tensor | Iterable, *, use_first_for_list_tuple: bool = False, return_indicator: bool = False, return_default_on_invalid: bool = False, default: U = -1, return_valid: bool | None = None) → int | U | ndim[int | U][source]¶

Scan first argument to return its number of dimension(s). Works recursively with Tensors, numpy arrays and builtins types instances.

Note: Sets and dicts are considered as scalars with a ndim equal to 0.

Args:

x: Input value to scan. use_first_for_list_tuple: If True, use first value to determine ndim for list and tuple argument. Otherwise it will scan each value in argument to determine its shape. defaults to False. return_indicator: If True, returns a tuple containing a boolean indicator if the data has an homogeneous ndim instead of raising a ValueError. defaults to False. return_default_on_invalid: If True and return_indicator=False, returns the default value instead of raising a ValueError. defaults to False. default: Value to return if input is a heterogeneous list/tuple. defaults to (). return_valid: Deprecated. Use return_indicator instead.

Raises:

ValueError if input has an heterogeneous number of dimensions and return_valid=False. TypeError if input has an unsupported type.

torchwrench.nn.functional.others.nelement(x: bool | int | float | complex | None | str | bytes | ndarray | generic | Tensor0D | Tensor | Iterable) → int[source]¶

Returns the number of elements in Tensor-like object.

torchwrench.nn.functional.others.prod(x: T_TensorOrArray, *, dim: int | None = None, start: Any = 1) → T_TensorOrArray[source]¶

torchwrench.nn.functional.others.prod(x: Iterable[T_BuiltinNumber], *, dim: Any = None, start: T_BuiltinNumber = 1) → T_BuiltinNumber

Returns the product of all elements in input.

torchwrench.nn.functional.others.ranks(x: Tensor, dim: int = -1, descending: bool = False) → LongTensor[source]¶

Get the ranks of each value in range [0, x.shape[dim][.

torchwrench.nn.functional.others.rmse(x1: Tensor, x2: Tensor, *, dim: int | tuple[int, ...] | None = None) → Tensor[source]¶

Root mean squared error function.

torchwrench.nn.functional.others.shape(x: bool | int | float | complex | None | str | bytes | ~numpy.ndarray | ~numpy.generic | ~torchwrench.types.tensor_subclasses.Tensor0D | ~torch.Tensor | ~pandas.DataFrame | list | tuple | set | frozenset | dict, *, output_type: ~typing.Callable[[~typing.Tuple[int, ...]], __SPHINX_IMMATERIAL_TYPE_VAR__V_T] = <function identity>, use_first_for_list_tuple: bool = False, return_indicator: bool = False, return_default_on_invalid: bool = False, default: __SPHINX_IMMATERIAL_TYPE_VAR__V_U = (), return_valid: bool | None = None) → T | U | shape[T | U][source]¶

Scan first argument to return its shape. Works recursively with Tensors, numpy arrays and builtins types instances.

Note: Sets and dicts are considered as scalars with a shape equal to ().

Args:

x: Input value to scan. output_type: Output shape type. defaults to identity, which returns a tuple of ints. use_first_for_list_tuple: If True, use first value in sequences to determine shape for list and tuple argument. Otherwise it will scan each value in argument to determine its shape. defaults to False. return_indicator: If True, returns a tuple containing a boolean indicator if the data has an homogeneous shape instead of raising a ValueError. defaults to False. return_default_on_invalid: If True and return_indicator=False, returns the default value instead of raising a ValueError. defaults to False. default: Value to return if input is a heterogeneous list/tuple. This default value is NOT passed to the output_type() callable argument. defaults to (). return_valid: Deprecated. Use return_indicator instead.

Raises:

ValueError: if input has an heterogeneous shape and return_valid=False. TypeError: if input has an unsupported type.

torchwrench.nn.functional.others.stack(tensors: list[Tensor0D] | tuple[Tensor0D, ...], dim: int = 0, *, out: Tensor1D | None = None) → Tensor1D[source]¶

torchwrench.nn.functional.others.stack(tensors: list[Tensor1D] | tuple[Tensor1D, ...], dim: int = 0, *, out: Tensor2D | None = None) → Tensor2D

torchwrench.nn.functional.others.stack(tensors: list[Tensor2D] | tuple[Tensor2D, ...], dim: int = 0, *, out: Tensor3D | None = None) → Tensor3D

torchwrench.nn.functional.others.stack(tensors: list[Tensor] | tuple[Tensor, ...], dim: int = 0, *, out: Tensor | None = None) → Tensor