def predict(self,
x,
batch_size=None,
steps=None,
max_queue_size=10,
workers=1):
"""Generates output predictions for the input samples.
Computation is done in batches.
# Arguments
x: Input data. It could be:
- A Numpy array (or array-like).
- A generator or `keras.utils.Sequence` returning
`(inputs, targets)` or `(inputs, targets, sample weights)`.
batch_size: Integer or `None`.
Number of samples per gradient update.
If unspecified, `batch_size` will default to 32.
Do not specify the `batch_size` if your data is in the
form of generators, or
`keras.utils.Sequence` instances (since they generate batches).
steps: Total number of steps (batches of samples)
before declaring the prediction round finished.
Ignored with the default value of `None`.
max_queue_size: Integer. Used for generator or `keras.utils.Sequence`
input only. Maximum size for the generator queue.
If unspecified, `max_queue_size` will default to 10.
workers: Integer. Used for generator or `keras.utils.Sequence` input
only. Maximum number of processes to spin up when using
process-based threading. If unspecified, `workers` will default
to 1.
# Returns
Numpy array(s) of predictions.
# Raises
ValueError: In case of mismatch between the provided
input data and the model's expectations.
"""
if batch_size is not None and data_utils.is_generator_or_sequence(x):
raise ValueError(
'The `batch_size` argument must not be specified when'
' using a generator or Sequence as an input.')
if batch_size is None:
# Backwards compatibility
batch_size = 32
# Case 1: generator-like. Input is Python generator, or Sequence object.
if data_utils.is_generator_or_sequence(x):
return self.predict_generator(x,
steps=steps,
max_queue_size=max_queue_size,
workers=workers)
# Case 2: Numpy array-like.
outputs = []
for start, stop in generic_utils.make_batches(len(x), batch_size):
outputs.append(self.predict_on_batch(x[start:stop]))
return np.vstack(outputs)
def _validate_arguments(is_sequence, is_dataset, use_multiprocessing, workers,
steps_per_epoch, validation_data, validation_steps,
mode, kwargs):
"""Raises errors if arguments are invalid.
Args:
is_sequence: Boolean, whether data is a `keras.utils.data_utils.Sequence`
instance.
is_dataset: Boolean, whether data is a dataset instance.
use_multiprocessing: Boolean. If `True`, use process-based threading. If
unspecified, `use_multiprocessing` will default to `False`. Note that
because this implementation relies on multiprocessing, you should not pass
non-picklable arguments to the generator as they can't be passed easily to
children processes.
workers: Integer. Maximum number of processes to spin up when using
process-based threading. If unspecified, `workers` will default to 1. If
0, will execute the generator on the main thread.
steps_per_epoch: Total number of steps (batches of samples) before declaring
one epoch finished and starting the next epoch. Ignored with the default
value of `None`.
validation_data: Either a tuple of NumPy/Tensor inputs (i.e. `(x,)` or `(x,
y)` or `(x, y, sample_weights)`) or a generator or
`keras.utils.data_utils.Sequence` object or Eager Iterator or Dataset.
validation_steps: Total number of steps (batches of samples) before
declaring validation finished.
mode: One of ModeKeys.TRAIN/ModeKeys.TEST/ModeKeys.PREDICT.
kwargs: Additional arguments for backwards compatibility.
Raises:
ValueError: If `steps_per_epoch` or `validation_steps` are not passed
for data types that require them, or if unrecognized keyword
arguments are passed.
"""
if not is_sequence and use_multiprocessing and workers > 1:
logging.warning(
UserWarning('Using a generator with `use_multiprocessing=True`'
' and multiple workers may duplicate your data.'
' Please consider using the `keras.utils.Sequence`'
' class.'))
if steps_per_epoch is None and not is_dataset:
arg_name = 'steps_per_epoch' if mode == ModeKeys.TRAIN else 'steps'
raise ValueError('Please specify the number of steps via the '
'`{}` argument.'.format(arg_name))
val_gen = (
data_utils.is_generator_or_sequence(validation_data) or
isinstance(validation_data, tf.data.Iterator))
if (val_gen and not isinstance(validation_data, data_utils.Sequence) and
not validation_steps):
raise ValueError('Please specify the `validation_steps` argument.')
if any(k != 'steps' for k in kwargs):
raise ValueError('Invalid arguments passed: {}'.format(
[k for k in kwargs if k != 'steps']))
def convert_to_generator_like(data,
batch_size=None,
steps_per_epoch=None,
epochs=1,
shuffle=False):
"""Make a generator out of NumPy or EagerTensor inputs.
Arguments:
data: Either a generator or `keras.utils.data_utils.Sequence` object or
`Dataset`, `Iterator`, or a {1,2,3}-tuple of NumPy arrays or EagerTensors.
If a tuple, the elements represent `(x, y, sample_weights)` and may be
`None` or `[None]`.
batch_size: Used when creating a generator out of tuples of NumPy arrays or
EagerTensors.
steps_per_epoch: Steps of the generator to run each epoch. If `None` the
number of steps will be read from the data (for
`keras.utils.data_utils.Sequence` types).
epochs: Total number of epochs to run.
shuffle: Whether the data should be shuffled.
Returns:
- Generator, `keras.utils.data_utils.Sequence`, or `Iterator`.
Raises:
- ValueError: If `batch_size` is not provided for NumPy or EagerTensor
inputs.
"""
if isinstance(data, tuple):
# Scrub `Nones` that might have been passed for `targets`, `sample_weights`.
data = tuple(ele for ele in data
if not all(e is None for e in tf.nest.flatten(ele)))
if data_utils.is_generator_or_sequence(data) or isinstance(
data, tf.data.Iterator):
if isinstance(data, data_utils.Sequence):
if steps_per_epoch is None:
steps_per_epoch = len(data)
return data, steps_per_epoch
if isinstance(data, tf.data.Dataset):
return tf.compat.v1.data.make_one_shot_iterator(data), steps_per_epoch
# Create generator from NumPy or EagerTensor Input.
num_samples = int(tf.nest.flatten(data)[0].shape[0])
if batch_size is None:
raise ValueError(
'When passing input data as arrays, do not specify '
'`steps_per_epoch`/`steps` argument. Please use `batch_size` instead.'
)
steps_per_epoch = int(math.ceil(num_samples / batch_size))
def _gen(data):
"""Makes a generator out of a structure of NumPy/EagerTensors."""
index_array = np.arange(num_samples)
for _ in range(epochs):
if shuffle:
np.random.shuffle(index_array)
batches = generic_utils.make_batches(num_samples, batch_size)
for (batch_start, batch_end) in batches:
batch_ids = index_array[batch_start:batch_end]
flat_batch_data = training_utils.slice_arrays(
tf.nest.flatten(data), batch_ids, contiguous=(not shuffle))
yield tf.nest.pack_sequence_as(data, flat_batch_data)
return _gen(data), steps_per_epoch
