How deeply does Deep Learning with R, Third Edition cover ModelCheckpoint?

Explains callback configuration and best-metric replacement through runnable examples, stopping short of callback implementation internals.

ModelCheckpoint

As explained in Deep Learning with R, Third Edition

ModelCheckpoint is a Keras callback that saves model states during training, optionally retaining only the state with the best monitored performance.

ModelCheckpoint is a Keras callback that saves model states during training. Configure it to monitor a metric and, with save_best_only = TRUE, retain only the state from the best-performing epoch. section 7.3.2 section 7.3.3

Save the best validation model

callbacks_list <- list( callback_early_stopping( monitor = "val_accuracy", patience = 1 ), callback_model_checkpoint( filepath = "checkpoint_path.keras", monitor = "val_loss", save_best_only = TRUE ) ) model |> fit( train_images, train_labels, epochs = 10, callbacks = callbacks_list, validation_data = list(val_images, val_labels) ) model <- load_model("checkpoint_path.keras") Here, training can stop when validation accuracy stops improving, while the checkpoint preserves the model with the lowest validation loss. section 7.3.3

Use ModelCheckpoint to:

Save the model after training epochs during a standard fit() run. section 7.3.2 section 8.2.4
Monitor validation loss and overwrite the saved file only when the current value improves. section 8.2.4
Reload the saved state later for evaluation instead of retraining after overfitting begins. section 8.2.4

callback_model_checkpoint()
callback_early_stopping()
callback_learning_rate_scheduler()
callback_reduce_lr_on_plateau()
callback_csv_logger()

Browse related Keras callbacks for early stopping, learning-rate adjustment, plateau handling, and metric logging. section 7.3.2

How Deep Learning with R, Third Edition covers it

Cover of Deep Learning with R, Third Edition

liveBook manning.com

Read Deep Learning with R, Third Edition on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Deep Learning with Python, Third EditionA Keras callback that saves a model or its best weights during training at specified points or when performance improves.

Compare how 2 books explain ModelCheckpoint →

Related concepts

callbackkind of · A callback is a function or other callable supplied to software for invocation later in response to a specified event, condition, or point in execution.
validation lossconfigures · The value of a loss function computed on held-out validation data to assess a model’s predictions.
early stoppingused by · Early stopping is a technique that terminates an iterative process before its planned completion when a specified condition indicates that further work is unnecessary or unlikely to improve the objective.
overfittingaddresses · Overfitting is a modeling condition in which a model fits patterns or idiosyncrasies in its training data too closely and consequently generalizes poorly to new data.
checkpointingproduces · A checkpoint is a designated point in a process at which its state or progress is recorded or evaluated, often to support recovery, continuation, or control.

This explainer was generated by Manning's knowledge graph from the text of Deep Learning with R, Third Edition. The section links point to the parts of the book it draws on.