filepath
can contain named formatting options, which will be filled the
value of epoch
and keys in logs
(passed in on_epoch_end
). For example:
if filepath
is weights.{epoch:02d}-{val_loss:.2f}.hdf5
, then the model
checkpoints will be saved with the epoch number and the validation loss in
the filename.
callback_model_checkpoint(filepath, monitor = "val_loss", verbose = 0,
save_best_only = FALSE, save_weights_only = FALSE, mode = c("auto",
"min", "max"), period = 1)
string, path to save the model file.
quantity to monitor.
verbosity mode, 0 or 1.
if save_best_only=TRUE
, the latest best model
according to the quantity monitored will not be overwritten.
if TRUE
, then only the model's weights will be
saved (save_model_weights_hdf5(filepath)
), else the full model is saved
(save_model_hdf5(filepath)
).
one of "auto", "min", "max". If save_best_only=TRUE
, the decision to
overwrite the current save file is made based on either the maximization or
the minimization of the monitored quantity. For val_acc, this should be
max, for val_loss this should be min, etc. In auto mode, the direction is
automatically inferred from the name of the monitored quantity.
Interval (number of epochs) between checkpoints.
if filepath
is
weights.{epoch:02d}-{val_loss:.2f}.hdf5
,: then the model checkpoints will
be saved with the epoch number and the validation loss in the filename.
Other callbacks: callback_csv_logger
,
callback_early_stopping
,
callback_lambda
,
callback_learning_rate_scheduler
,
callback_progbar_logger
,
callback_reduce_lr_on_plateau
,
callback_remote_monitor
,
callback_tensorboard
,
callback_terminate_on_naan