TorchSparseLogCategoricalDistribution¶
- class probly.representation.distribution.torch_sparse_log_categorical.TorchSparseLogCategoricalDistribution(group_ids: Tensor, entry_logits: Tensor)[source]¶
Bases:
TorchAxisProtected[TorchSparseLogCategoricalDistribution,TorchSparseLogCategoricalDistribution,TorchSparseLogCategoricalDistribution,Never,TorchSparseLogCategoricalDistribution,Tensor,TorchSparseLogCategoricalDistribution],CategoricalDistribution[Tensor]Sparse categorical distribution with grouped log-weights.
Shape:
batch_shape. The final axis ofgroup_idsandentry_logitsstores sparse support entries. Entries with the same group id are combined by summing their exponentiated logits when converting to a dense categorical distribution.- property T: ShapeResultT¶
Inverts the order of the dimensions of the underlying array.
- 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.
- entry_logits: torch.Tensor¶
- gather(dim: int, index: torch.Tensor) ShapeResultT[source]¶
Return a copy with gathered protected values along a batch dimension.
- group_ids: torch.Tensor¶
- property mH: ShapeResultT¶
The adjoint (conjugate) transposed version of the underlying array.
- property mT: ShapeResultT¶
The transposed version of the underlying array.
- permitted_functions = {}¶
- permute(*dims: torch.Size | int | tuple[int] | list[int]) ShapeResultT[source]¶
Return a permuted version of the array.
- primary_protected_name = 'group_ids'¶
- 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, rng: Generator | None = None) TorchSample[Tensor][source]¶
Sample from the equivalent dense categorical 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_dense(num_classes: int | None = None) TorchProbabilityCategoricalDistribution[source]¶
Convert sparse grouped logits to a dense categorical distribution.
- Parameters:
num_classes – Optional dense class count. Defaults to
max(group_ids) + 1.- Returns:
Dense categorical distribution with zero mass for absent groups.
- 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 = 'categorical'¶
- uniform_logits() TorchSparseLogCategoricalDistribution[source]¶
Return a copy with identical groups and uniform sparse logits.
- Returns:
A sparse categorical distribution with shared
group_idsand zero logits.
- property unnormalized_probabilities: Tensor¶
Get unnormalized probabilities of the categorical distribution.