pystruct.utils.SaveLogger

class pystruct.utils.SaveLogger(file_name, save_every=10, verbose=0)

Logging class that stores the model periodically.

Can be used to back up a model during learning. Also a prototype to demonstrate the logging interface.

Parameters :

file_name : string

File in which the model will be stored. If the string contains ‘%d’, this will be replaced with the current iteration.

save_every : int (default=10)

How often the model should be stored (in iterations).

verbose : int (default=0)

Verbosity level.

Methods

load()

Load the model stoed in file_name and return it.

__init__(file_name, save_every=10, verbose=0)

__call__(learner, iteration=0)

Save learner if iterations is a multiple of save_every or “final”.

Parameters :

learner : object

Learning object to be saved.

iteration : int or ‘final’ (default=0)

If ‘final’ or save_every % iteration == 0, the model will be saved.

load()

Load the model stoed in file_name and return it.