Utils

Load a CAREamics config from a checkpoint.

Some fields, if missing, will be populated by defaults. Namely, version, training_config and experiment_name.

The default for experiment_name will be "loaded_from_<checkpoint_filename>".

Parameters:

• checkpoint_path (Path) –

  Path to the PyTorch Lightning checkpoint file.

Returns:

• Configuration –

  A CAREamics configuration object.

Raises:

• ValueErrors: –

  If certain required information is not found in the checkpoint.

Load a trained CAREamics module from checkpoint.

Automatically detects the algorithm type from the checkpoint and loads the appropriate module with trained weights.

Parameters:

• checkpoint_path (Path) –

  Path to the PyTorch Lightning checkpoint file.

Returns:

• CAREamicsModule –

  Lightning module with loaded weights.

Raises:

• ValueError –

  If the algorithm type cannot be determined from the checkpoint.

Return the loss curves from the csv logs.

Parameters:

• experiment_name (str) –

  Name of the experiment.

• log_folder (Path or str) –

  Path to the folder containing the csv logs.

Returns:

• dict –

  Dictionary containing the loss curves, with keys "train_epoch", "val_epoch", "train_loss" and "val_loss".