The generator should return the same kind of data as accepted by
test_on_batch().
evaluate_generator(object, generator, steps, max_queue_size = 10)Model object to evaluate
Generator yielding lists (inputs, targets) or (inputs, targets, sample_weights)
Total number of steps (batches of samples) to yield from
generator before stopping.
maximum size for the generator queue
Scalar test loss (if the model has a single output and no metrics) or
list of scalars (if the model has multiple outputs and/or metrics). The
attribute model$metrics_names will give you the display labels for the
scalar outputs.
Other model functions: compile,
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