standard_model

Standard model class(es).

class graphnet.models.standard_model.StandardModel(*args, **kwargs)

Bases: Model

Main class for standard models in graphnet.

This class chains together the different elements of a complete GNN-based model (detector read-in, GNN architecture, and task-specific read-outs).

Construct StandardModel.

Parameters:

• args (Any) –

• kwargs (Any) –

Return type:

object

property target_labels: List[str]

Return target label.

property prediction_labels: List[str]

Return prediction labels.

configure_optimizers()

Configure the model’s optimizer(s).

Return type:

Dict[str, Any]

forward(data)

Forward pass, chaining model components.

Return type:

List[Union[Tensor, Data]]

Parameters:

data (Data) –

shared_step(batch, batch_idx)

Perform shared step.

Applies the forward pass and the following loss calculation, shared between the training and validation step.

Return type:

Tensor

Parameters:

• batch (Data) –

• batch_idx (int) –

training_step(train_batch, batch_idx)

Perform training step.

Return type:

Tensor

Parameters:

• train_batch (Data) –

• batch_idx (int) –

validation_step(val_batch, batch_idx)

Perform validation step.

Return type:

Tensor

Parameters:

• val_batch (Data) –

• batch_idx (int) –

compute_loss(preds, data, verbose)

Compute and sum losses across tasks.

Return type:

Tensor

Parameters:

• preds (Tensor) –

• data (Data) –

• verbose (bool) –

inference()

Activate inference mode.

Return type:

None

train(mode)

Deactivate inference mode.

Return type:

Model

Parameters:

mode (bool) –

predict(dataloader, gpus, distribution_strategy)

Return predictions for dataloader.

Return type:

List[Tensor]

Parameters:

• dataloader (DataLoader) –

• gpus (List[int] | int | None) –

• distribution_strategy (str | None) –

predict_as_dataframe(dataloader, prediction_columns, *, additional_attributes, gpus, distribution_strategy)

Return predictions for dataloader as a DataFrame.

Include additional_attributes as additional columns in the output DataFrame.

Return type:

DataFrame

Parameters:

• dataloader (DataLoader) –

• prediction_columns (List[str] | None) –

• additional_attributes (List[str] | None) –

• gpus (List[int] | int | None) –

• distribution_strategy (str | None) –