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)[source]#

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
  • modelDeepARModel 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.

configure_optimizers()[source]#

Returns the optimizer to use.

training_step(batch, batch_idx: int)[source]#

Execute training step.

validation_step(batch, batch_idx: int)[source]#

Execute validation step.