Class ModelCheckpoint
Save the model after every epoch. filepath can contain named formatting options, which will be filled with the values 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.
Implements
Inherited Members
Namespace: Keras.Callbacks
Assembly: Keras.dll
Syntax
public class ModelCheckpoint : Callback, IDisposable
Constructors
| Improve this Doc View SourceModelCheckpoint(String, String, Int32, Boolean, Boolean, String, Int32)
Initializes a new instance of the ModelCheckpoint class.
Declaration
public ModelCheckpoint(string filepath, string monitor = "val_loss", int verbose = 0, bool save_best_only = true, bool save_weights_only = false, string mode = "auto", int period = 1)
Parameters
Type | Name | Description |
---|---|---|
System.String | filepath | string, path to save the model file. |
System.String | monitor | quantity to monitor. |
System.Int32 | verbose | verbosity mode, 0 or 1. |
System.Boolean | save_best_only | if save_best_only=True, the latest best model according to the quantity monitored will not be overwritten. |
System.Boolean | save_weights_only | if True, then only the model's weights will be saved (model.save_weights(filepath)), else the full model is saved (model.save(filepath)). |
System.String | mode | 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. |
System.Int32 | period | Interval (number of epochs) between checkpoints. |