Base R6 class for Keras callbacks
An R6Class generator object
logs named list that callback methods take as argument will
contain keys for quantities relevant to the current batch or epoch.
fit.keras.engine.training.Model() method for sequential
models will include the following quantities in the
it passes to its callbacks:
on_epoch_end: logs include
loss, and optionally include
val_loss (if validation is enabled in
val_acc (if validation and accuracy monitoring are enabled).
on_batch_begin: logs include
size, the number of samples in the current batch.
on_batch_end: logs include
loss, and optionally
acc (if accuracy monitoring is enabled).
Named list with training parameters (eg. verbosity, batch size, number of epochs...).
Reference to the Keras model being trained.
Called at the beginning of each epoch.
Called at the end of each epoch.
Called at the beginning of each batch.
Called at the end of each batch.
Called at the beginning of training.
Called at the end of training.