gluonts.torch.model.patch_tst.module module

class gluonts.torch.model.patch_tst.module.PatchTSTModel(prediction_length: int, context_length: int, patch_len: int, stride: int, padding_patch: str, d_model: int, nhead: int, dim_feedforward: int, dropout: float, activation: str, norm_first: bool, num_encoder_layers: int, scaling: str, distr_output=gluonts.torch.distributions.studentT.StudentTOutput(beta=0.0))

Bases: torch.nn.modules.module.Module

Module implementing the PatchTST model for forecasting as described in https://arxiv.org/abs/2211.14730 extended to be probabilistic.

Parameters

• prediction_length – Number of time points to predict.

• context_length – Number of time steps prior to prediction time that the model.

• distr_output – Distribution to use to evaluate observations and sample predictions. Default: StudentTOutput().

describe_inputs(batch_size=1) → gluonts.model.inputs.InputSpec

forward(past_target: torch.Tensor, past_observed_values: torch.Tensor) → Tuple[Tuple[torch.Tensor, ...], torch.Tensor, torch.Tensor]

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

loss(past_target: torch.Tensor, past_observed_values: torch.Tensor, future_target: torch.Tensor, future_observed_values: torch.Tensor) → torch.Tensor

training: bool

class gluonts.torch.model.patch_tst.module.SinusoidalPositionalEmbedding(num_positions: int, embedding_dim: int)

Bases: torch.nn.modules.sparse.Embedding

This module produces sinusoidal positional embeddings of any length.

embedding_dim: int

forward(input_ids_shape: torch.Size, past_key_values_length: int = 0) → torch.Tensor

input_ids_shape is expected to be [bsz x seqlen x …].

freeze: bool

max_norm: Optional[float]

norm_type: float

num_embeddings: int

padding_idx: Optional[int]

scale_grad_by_freq: bool

sparse: bool

training: bool

weight: torch.Tensor