parakeet.utils package
Submodules
parakeet.utils.checkpoint module
- parakeet.utils.checkpoint.load_parameters(model, optimizer=None, checkpoint_dir=None, checkpoint_path=None)[source]
Load a specific model checkpoint from disk.
- Args:
model (Layer): model to load parameters. optimizer (Optimizer, optional): optimizer to load states if needed.
Defaults to None.
checkpoint_dir (str, optional): the directory where checkpoint is saved. checkpoint_path (str, optional): if specified, load the checkpoint
stored in the checkpoint_path and the argument ‘checkpoint_dir’ will be ignored. Defaults to None.
- Returns:
- iteration (int): number of iterations that the loaded checkpoint has
been trained.
- parakeet.utils.checkpoint.save_parameters(checkpoint_dir, iteration, model, optimizer=None)[source]
Checkpoint the latest trained model parameters.
- Args:
checkpoint_dir (str): the directory where checkpoint is saved. iteration (int): the latest iteration number. model (Layer): model to be checkpointed. optimizer (Optimizer, optional): optimizer to be checkpointed.
Defaults to None.
- Returns:
None