The generator should return the same kind of data as accepted by
predict_on_batch()
.
predict_generator(
object,
generator,
steps,
max_queue_size = 10,
workers = 1,
verbose = 0,
callbacks = NULL
)
Numpy array(s) of predictions.
Keras model object
Generator yielding batches of input samples.
Total number of steps (batches of samples) to yield from
generator
before stopping.
Maximum size for the generator queue. If unspecified,
max_queue_size
will default to 10.
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.
verbosity mode, 0 or 1.
List of callbacks to apply during prediction.
ValueError: In case the generator yields data in an invalid format.
Other model functions:
compile.keras.engine.training.Model()
,
evaluate.keras.engine.training.Model()
,
evaluate_generator()
,
fit.keras.engine.training.Model()
,
fit_generator()
,
get_config()
,
get_layer()
,
keras_model_sequential()
,
keras_model()
,
multi_gpu_model()
,
pop_layer()
,
predict.keras.engine.training.Model()
,
predict_on_batch()
,
predict_proba()
,
summary.keras.engine.training.Model()
,
train_on_batch()