TorchSample

class probly.representation.sample.torch.TorchSample(tensor: D, sample_dim: int, weights: torch.Tensor | None = None)[source]

Bases: TorchLikeImplementation, Sample, Generic

A sample implementation for torch tensors.

property T: Self

Inverts the order of the dimensions of the underlying array.

clone(*, memory_format: memory_format = torch.preserve_format) → Self[source]

Return a copy of the array.

concat(other: Sample[D]) → Self[source]

Append another sample to this sample.

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.

detach() → Self[source]

Return a detached copy of the sample tensor wrapper.

property device: Any

The device of the underlying array.

property dtype: dtype

The data type of the underlying array.

classmethod from_iterable(samples: Iterable[ArrayLike[D]], weights: Iterable[float] | None = None, sample_dim: SampleAxis | None = None, sample_axis: SampleAxis | None = 'auto', dtype: torch.dtype | None = None) → Self[source]

Create an TorchSample from a sequence of samples.

Parameters:

  • samples – The predictions to create the sample from.

  • weights – Optional weights for the samples.

  • sample_dim – The dimension along which samples are organized.

  • sample_axis – Alias for sample_dim for compatibility.

  • dtype – Desired data type of the array.

Returns:

The created TorchSample.

classmethod from_sample(sample: Sample[T], *, sample_axis: SampleAxis = 'auto') → Self[source]

Create a new Sample from an existing Sample.

Parameters:

  • sample – The sample to create the new sample from.

  • sample_axis – The dimension along which samples are organized.

Returns:

The created Sample.

property is_weighted: bool

Return whether the samples are weighted.

property mH: Self

The adjoint view over the last two dimensions.

property mT: Self

The transposed view over the last two dimensions.

move_sample_axis(new_sample_axis: int) → TorchSample[source]

Alias for TorchSample.move_sample_dim().

move_sample_dim(new_sample_dim: int) → TorchSample[source]

Return a new TorchSample with the sample dimension moved to new_sample_dim.

Parameters:

new_sample_dim – The new sample dimension.

Returns:

A new TorchSample with the sample dimension moved.

property ndim: int

The number of dimensions of the underlying array.

numpy(*, force: bool = False) → NDArray[Any][source]

Convert to a numpy array.

permute(*dims: Size | int | tuple[int] | list[int]) → Self[source]

Return a permuted version of the array.

resolve_conj() → Self[source]

Return a version of the array with any conjugate operations resolved.

resolve_neg() → Self[source]

Return a version of the array with any negation operations resolved.

property sample_axis: int

The axis along which samples are organized.

sample_dim: int
sample_mean() → D[source]

Compute the mean of the sample.

property sample_size: int

Return the number of samples.

sample_std(ddof: int = 0) → D[source]

Compute the standard deviation of the sample.

sample_var(ddof: int = 0) → D[source]

Compute the variance of the sample.

property samples: D

Return an iterator over the samples.

property shape: tuple[int, ...]

The shape of the underlying array.

size(dim: int) → int[source]
size(dim: None = None) → Size

The total number of elements in the underlying array.

tensor: D
to(*args: Any, **kwargs: Any) → Self[source]

Moves and/or casts the underlying tensor. See torch.Tensor.to for details.

Parameters:

  • *args – Positional arguments to pass to torch.Tensor.to.

  • **kwargs – Keyword arguments to pass to torch.Tensor.to.

Returns:

A copy of the TorchSample.

to_device(device: Literal['cpu'], /, *, stream: int | Any | None = None) → Self[source]

Move the array to a device.

transpose(dim0: int, dim1: int) → Self[source]

Return a transposed version of the array.

weights: Tensor | None

Examples using probly.representation.sample.torch.TorchSample

Het-Net on MNIST

Het-Net on MNIST

Ensemble Ordinal Classification Uncertainty

Ensemble Ordinal Classification Uncertainty

Ensemble Regression Uncertainty

Ensemble Regression Uncertainty

Bayesian Ensemble on MNIST

Bayesian Ensemble on MNIST

Bayesian Neural Network on MNIST

Bayesian Neural Network on MNIST

DropConnect on MNIST

DropConnect on MNIST

MC Dropout on MNIST

MC Dropout on MNIST

Deep Ensemble on MNIST

Deep Ensemble on MNIST

Sub-Ensemble on MNIST

Sub-Ensemble on MNIST