gluonts.torch.util module

class gluonts.torch.util.IterableDataset(iterable)

Bases: torch.utils.data.dataset.IterableDataset

gluonts.torch.util.copy_parameters(net_source: torch.nn.modules.module.Module, net_dest: torch.nn.modules.module.Module, strict: Optional[bool] = True) → None

Copies parameters from one network to another.

Parameters

• net_source – Input network.

• net_dest – Output network.

• strict – whether to strictly enforce that the keys in state_dict match the keys returned by this module’s state_dict() function. Default: True

gluonts.torch.util.get_forward_input_names(module: Type[torch.nn.modules.module.Module])

gluonts.torch.util.lagged_sequence_values(indices: List[int], prior_sequence: torch.Tensor, sequence: torch.Tensor) → torch.Tensor

Constructs an array of lagged values from a given sequence.

Parameters

• indices – Indices of the lagged observations. For example, [0] indicates that, at any time t, the will have only the observation from time t itself; instead, [0, 24] indicates that the output will have observations from times t and t-24.

• prior_sequence – Tensor containing the input sequence prior to the time range for which the output is required (shape: (N, H, C)).

• sequence – Tensor containing the input sequence in the time range where the output is required (shape: (N, T, C)).

Returns

A tensor of shape (N, T, L): if I = len(indices), and sequence.shape = (N, T, C), then L = C * I.

Return type

Tensor

gluonts.torch.util.weighted_average(x: torch.Tensor, weights: Optional[torch.Tensor] = None, dim=None) → torch.Tensor

Computes the weighted average of a given tensor across a given dim, masking values associated with weight zero,

meaning instead of nan * 0 = nan you will get 0 * 0 = 0.

Parameters

• x – Input tensor, of which the average must be computed.

• weights – Weights tensor, of the same shape as x.

• dim – The dim along which to average x

Returns

The tensor with values averaged along the specified dim.

Return type

Tensor