TorchDirichletDistribution¶
- class probly.representation.distribution.torch_dirichlet.TorchDirichletDistribution(alphas: Tensor)[source]¶
Bases:
TorchAxisProtected[TorchDirichletDistribution,TorchDirichletDistribution | torch.Tensor | float,TorchDirichletDistribution,Never,TorchDirichletDistribution,Tensor,TorchDirichletDistribution],DirichletDistribution[TorchCategoricalDistribution]A Dirichlet distribution stored as a torch tensor.
Shape: (…, num_classes) The last axis represents the category dimension.
- property T: ShapeResultT¶
Inverts the order of the dimensions of the underlying array.
- alphas: torch.Tensor¶
- clone(*, memory_format: torch.memory_format = torch.preserve_format) OwnerT[source]¶
Return a copy of the array.
- cpu(memory_format: memory_format = torch.preserve_format) Self[source]¶
Move the array to the CPU.
- cuda(device: device | str | None = None, non_blocking: bool = False, memory_format: memory_format = torch.preserve_format) Self[source]¶
Move the array to the GPU.
- classmethod from_tensor(alphas: Tensor | list[float], dtype: dtype | None = None) TorchDirichletDistribution[source]¶
Create a Dirichlet distribution from a tensor or list.
- Parameters:
alphas – Dirichlet alpha parameters.
dtype – Desired tensor dtype.
- Returns:
The created torch Dirichlet distribution.
- gather(dim: int, index: torch.Tensor) ShapeResultT[source]¶
Return a copy with gathered protected values along a batch dimension.
- property mH: ShapeResultT¶
The adjoint (conjugate) transposed version of the underlying array.
- property mT: ShapeResultT¶
The transposed version of the underlying array.
- property mean: TorchCategoricalDistribution¶
Return the expected categorical probabilities.
- numpy(*, force: bool = False) np.ndarray[source]¶
Convert the Dirichlet alpha parameters to a numpy array.
- permitted_functions: ClassVar[set[Callable]] = {<built-in method eq of type object>, <built-in method mean of type object>, <built-in method ne of type object>, <built-in method sum of type object>, <function torch_average>}¶
- permute(*dims: torch.Size | int | tuple[int] | list[int]) ShapeResultT[source]¶
Return a permuted version of the array.
- primary_protected_name = 'alphas'¶
- protected_axes = {'alphas': 1}¶
- protected_values(func: Callable | None = None) dict[str, V] | None[source]¶
Read effective values as-is, optionally checking function permissions.
- reshape(*shape: int | tuple[int, ...]) ShapeResultT[source]¶
Return a copy with reshaped protected values.
- resolve_conj() OpResultT[source]¶
Return a version of the array with any conjugate operations resolved.
- resolve_neg() OpResultT[source]¶
Return a version of the array with any negation operations resolved.
- sample(num_samples: int = 1) TorchSample[TorchCategoricalDistribution][source]¶
Sample categorical distributions from the Dirichlet distribution.
- property shape: tuple[int, ...]¶
Read the logical shape without collecting fields unless all broadcast.
- size(dim: int | None = None) int | Size[source]¶
Return the size of the array along the given dimension.
- to_device(device: device | str | None = None, /, *, stream: int | Any | None = None) Self[source]¶
Move the array to the given device.
- Parameters:
device – Target device, or None to retain the current device.
stream – Unsupported; must be None.
- Returns:
The moved array representation.
- Raises:
NotImplementedError – If a stream is provided.
- type = 'dirichlet'¶