Configure a Keras model for training
compile(object, optimizer, loss, metrics = NULL, loss_weights = NULL,
sample_weight_mode = NULL)Model object to compile.
Name of optimizer or optimizer object.
Name of objective function or objective function. If the model has multiple outputs, you can use a different loss on each output by passing a dictionary or a list of objectives.
List of metrics to be evaluated by the model during training
and testing. Typically you will use metrics='accuracy'. To specify
different metrics for different outputs of a multi-output model, you could
also pass a named list such as metrics=list(output_a = 'accuracy').
Loss weights
If you need to do timestep-wise sample weighting
(2D weights), set this to "temporal". NULL defaults to sample-wise
weights (1D). If the model has multiple outputs, you can use a different
sample_weight_mode on each output by passing a list of modes.
Other model functions: evaluate_generator,
evaluate, fit_generator,
fit, get_config,
get_layer,
keras_model_sequential,
keras_model, pop_layer,
predict.tensorflow.keras.engine.training.Model,
predict_generator,
predict_on_batch,
predict_proba,
summary.tensorflow.keras.engine.training.Model,
train_on_batch