RegressionRoutine

class torch_uncertainty.routines.RegressionRoutine(model, output_dim, loss, dist_family=None, dist_estimate='mean', is_ensemble=False, optim_recipe=None, eval_shift=False, format_batch_fn=None)

Routine for training & testing on regression tasks.

Parameters:

• model (torch.nn.Module) – Model to train.

• output_dim (int) – Number of outputs of the model.

• loss (torch.nn.Module) – Loss function to optimize the model.

• dist_family (str, optional) – The distribution family to use for probabilistic regression. If None then point-wise regression. Defaults to None.

• dist_estimate (str, optional) – The estimate to use when computing the point-wise metrics. Defaults to "mean".

• is_ensemble (bool, optional) – Whether the model is an ensemble. Defaults to False.

• optim_recipe (dict or torch.optim.Optimizer, optional) – The optimizer and optionally the scheduler to use. Defaults to None.

• eval_shift (bool, optional) – Indicates whether to evaluate the Distribution shift performance. Defaults to False.

• format_batch_fn (torch.nn.Module, optional) – The function to format the batch. Defaults to None.

Warning

If probabilistic is True, the model must output a PyTorch distribution.

Warning

You must define optim_recipe if you do not use the CLI.

Note

optim_recipe can be anything that can be returned by LightningModule.configure_optimizers(). Find more details here.

evaluation_forward(inputs)

Get the prediction and handle predicted eventual distribution parameters.

Parameters:

inputs (Tensor) – the input data.

Returns:

the prediction as a Tensor and a distribution.

Return type:

tuple[Tensor, Distribution | None]

forward(inputs)

Forward pass of the routine.

The forward pass automatically squeezes the output if the regression is one-dimensional and if the routine contains a single model.

Parameters:

inputs (Tensor) – The input tensor.

Returns:

The output tensor or the parameters of the output

distribution.

Return type:

Tensor | dict[str, Tensor]

on_test_epoch_end()

Compute and log the values of the collected metrics in test_step.

on_test_start()

Prepare the test step.

Update the batchnorms if needed.

on_train_start()

Put the hyperparameters in tensorboard.

on_validation_epoch_end()

Compute and log the values of the collected metrics in validation_step.

on_validation_start()

Prepare the validation step.

Update the model’s wrapper and the batchnorms if needed.

test_step(batch, batch_idx, dataloader_idx=0)

Perform a single test step based on the input tensors.

Compute the prediction of the model and the value of the metrics on the test batch. Also handle OOD and distribution-shifted images.

Parameters:

• batch (tuple[Tensor, Tensor]) – the test data and their corresponding targets.

• batch_idx (int) – the number of the current batch (unused).

• dataloader_idx (int) – 0 if in-distribution, 1 if out-of-distribution.

training_step(batch)

Perform a single training step based on the input tensors.

Parameters:

batch (tuple[Tensor, Tensor]) – the training data and their corresponding targets

Returns:

the loss corresponding to this training step.

Return type:

Tensor

validation_step(batch)

Perform a single validation step based on the input tensors.

Compute the prediction of the model and the value of the metrics on the validation batch.

Parameters:

batch (tuple[Tensor, Tensor]) – the validation data and their corresponding targets.