gw.training.train_pipeline.prepare_training_resume

gw.training.train_pipeline.prepare_training_resume(
    checkpoint_name,
    local_settings,
    train_dir,
)

Loads a PosteriorModel from a checkpoint, as well as the corresponding WaveformDataset, in order to continue training. It initializes the saved optimizer and scheduler from the checkpoint.

Parameters

Name	Type	Description	Default
checkpoint_name	str	File name containing the checkpoint (.pt format).	required
local_settings	dict	Local settings (e.g., num_workers, device)	required
train_dir	str	Path to training directory where the wandb info is saved.	required

Returns

Name	Type	Description
	(BasePosteriorModel, WaveformDataset)