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. The loss value that will be minimized by the model will then be the sum of all individual losses.
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').
Optional list specifying scalar coefficients to weight
the loss contributions of different model outputs. The loss value that will
be minimized by the model will then be the weighted sum of all indvidual
losses, weighted by the loss_weights coefficients.
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.
Additional named arguments passed to tf$Session$run.
Other model functions: evaluate_generator,
evaluate, fit_generator,
fit, get_config,
get_layer,
keras_model_sequential,
keras_model, pop_layer,
predict.keras.engine.training.Model,
predict_generator,
predict_on_batch,
predict_proba,
summary.keras.engine.training.Model,
train_on_batch