gluonts.torch.model.deepar.lightning_module module

class gluonts.torch.model.deepar.lightning_module.DeepARLightningModule(model: gluonts.torch.model.deepar.module.DeepARModel, loss: gluonts.torch.modules.loss.DistributionLoss = NegativeLogLikelihood(beta=0.0), lr: float = 0.001, weight_decay: float = 1e-08, patience: int = 10)

Bases: pytorch_lightning.core.module.LightningModule

A pl.LightningModule class that can be used to train a DeepARModel with PyTorch Lightning.

This is a thin layer around a (wrapped) DeepARModel object, that exposes the methods to evaluate training and validation loss.

Parameters

• model – DeepARModel to be trained.

• loss – Loss function to be used for training, default: NegativeLogLikelihood().

• lr – Learning rate, default: 1e-3.

• weight_decay – Weight decay regularization parameter, default: 1e-8.

• patience – Patience parameter for learning rate scheduler, default: 10.

configure_optimizers()

Returns the optimizer to use.

forward(*args, **kwargs)

Same as torch.nn.Module.forward().

Parameters

• *args – Whatever you decide to pass into the forward method.

• **kwargs – Keyword arguments are also possible.

Returns

Your model’s output

training_step(batch, batch_idx: int)

Execute training step.

validation_step(batch, batch_idx: int)

Execute validation step.