The generator should return the same kind of data as accepted by
evaluate_generator(object, generator, steps, max_queue_size = 10, workers = 1)
Model object to evaluate
Generator yielding lists (inputs, targets) or (inputs, targets, sample_weights)
Total number of steps (batches of samples) to yield from
Maximum size for the generator queue. If unspecified,
Maximum number of threads to use for parallel processing. Note that
parallel processing will only be performed for native Keras generators (e.g.
Named list of model test loss (or losses for models with multiple outputs) and model metrics.
Other model functions: