The generator should return the same kind of data as accepted by test_on_batch().

evaluate_generator(
  object,
  generator,
  steps,
  max_queue_size = 10,
  workers = 1,
  callbacks = NULL
)

Arguments

object

Model object to evaluate

generator

Generator yielding lists (inputs, targets) or (inputs, targets, sample_weights)

steps

Total number of steps (batches of samples) to yield from generator before stopping.

max_queue_size

Maximum size for the generator queue. If unspecified, max_queue_size will default to 10.

workers

Maximum number of threads to use for parallel processing. Note that parallel processing will only be performed for native Keras generators (e.g. flow_images_from_directory()) as R based generators must run on the main thread.

callbacks

List of callbacks to apply during evaluation.

Value

Named list of model test loss (or losses for models with multiple outputs) and model metrics.

See also