in keras/engine/training.py [0:0]
def fit(self,
x=None,
y=None,
batch_size=None,
epochs=1,
verbose=1,
callbacks=None,
validation_split=0.,
validation_data=None,
shuffle=True,
class_weight=None,
sample_weight=None,
initial_epoch=0,
steps_per_epoch=None,
validation_steps=None,
**kwargs):
"""Trains the model for a given number of epochs (iterations on a dataset).
# Arguments
x: Numpy array of training data (if the model has a single input),
or list of Numpy arrays (if the model has multiple inputs).
If input layers in the model are named, you can also pass a
dictionary mapping input names to Numpy arrays.
`x` can be `None` (default) if feeding from
framework-native tensors (e.g. TensorFlow data tensors).
y: Numpy array of target (label) data
(if the model has a single output),
or list of Numpy arrays (if the model has multiple outputs).
If output layers in the model are named, you can also pass a
dictionary mapping output names to Numpy arrays.
`y` can be `None` (default) if feeding from
framework-native tensors (e.g. TensorFlow data tensors).
batch_size: Integer or `None`.
Number of samples per gradient update.
If unspecified, `batch_size` will default to 32.
epochs: Integer. Number of epochs to train the model.
An epoch is an iteration over the entire `x` and `y`
data provided.
Note that in conjunction with `initial_epoch`,
`epochs` is to be understood as "final epoch".
The model is not trained for a number of iterations
given by `epochs`, but merely until the epoch
of index `epochs` is reached.
verbose: Integer. 0, 1, or 2. Verbosity mode.
0 = silent, 1 = progress bar, 2 = one line per epoch.
callbacks: List of `keras.callbacks.Callback` instances.
List of callbacks to apply during training.
See [callbacks](/callbacks).
validation_split: Float between 0 and 1.
Fraction of the training data to be used as validation data.
The model will set apart this fraction of the training data,
will not train on it, and will evaluate
the loss and any model metrics
on this data at the end of each epoch.
The validation data is selected from the last samples
in the `x` and `y` data provided, before shuffling.
validation_data: tuple `(x_val, y_val)` or tuple
`(x_val, y_val, val_sample_weights)` on which to evaluate
the loss and any model metrics at the end of each epoch.
The model will not be trained on this data.
`validation_data` will override `validation_split`.
shuffle: Boolean (whether to shuffle the training data
before each epoch) or str (for 'batch').
'batch' is a special option for dealing with the
limitations of HDF5 data; it shuffles in batch-sized chunks.
Has no effect when `steps_per_epoch` is not `None`.
class_weight: Optional dictionary mapping class indices (integers)
to a weight (float) value, used for weighting the loss function
(during training only).
This can be useful to tell the model to
"pay more attention" to samples from
an under-represented class.
sample_weight: Optional Numpy array of weights for
the training samples, used for weighting the loss function
(during training only). You can either pass a flat (1D)
Numpy array with the same length as the input samples
(1:1 mapping between weights and samples),
or in the case of temporal data,
you can pass a 2D array with shape
`(samples, sequence_length)`,
to apply a different weight to every timestep of every sample.
In this case you should make sure to specify
`sample_weight_mode="temporal"` in `compile()`.
initial_epoch: Integer.
Epoch at which to start training
(useful for resuming a previous training run).
steps_per_epoch: Integer or `None`.
Total number of steps (batches of samples)
before declaring one epoch finished and starting the
next epoch. When training with input tensors such as
TensorFlow data tensors, the default `None` is equal to
the number of samples in your dataset divided by
the batch size, or 1 if that cannot be determined.
validation_steps: Only relevant if `steps_per_epoch`
is specified. Total number of steps (batches of samples)
to validate before stopping.
# Returns
A `History` object. Its `History.history` attribute is
a record of training loss values and metrics values
at successive epochs, as well as validation loss values
and validation metrics values (if applicable).
# Raises
RuntimeError: If the model was never compiled.
ValueError: In case of mismatch between the provided input data
and what the model expects.
"""
# Backwards compatibility
if batch_size is None and steps_per_epoch is None:
batch_size = 32
# Legacy support
if 'nb_epoch' in kwargs:
warnings.warn('The `nb_epoch` argument in `fit` '
'has been renamed `epochs`.', stacklevel=2)
epochs = kwargs.pop('nb_epoch')
if kwargs:
raise TypeError('Unrecognized keyword arguments: ' + str(kwargs))
if x is None and y is None and steps_per_epoch is None:
raise ValueError('If fitting from data tensors, '
'you should specify the `steps_per_epoch` '
'argument.')
# Validate user data.
x, y, sample_weights = self._standardize_user_data(
x, y,
sample_weight=sample_weight,
class_weight=class_weight,
batch_size=batch_size)
# Prepare validation data.
do_validation = False
if validation_data:
do_validation = True
if len(validation_data) == 2:
val_x, val_y = validation_data
val_sample_weight = None
elif len(validation_data) == 3:
val_x, val_y, val_sample_weight = validation_data
else:
raise ValueError('When passing validation_data, '
'it must contain 2 (x_val, y_val) '
'or 3 (x_val, y_val, val_sample_weights) '
'items, however it contains %d items' %
len(validation_data))
val_x, val_y, val_sample_weights = self._standardize_user_data(
val_x, val_y,
sample_weight=val_sample_weight,
batch_size=batch_size)
if self._uses_dynamic_learning_phase():
val_inputs = val_x + val_y + val_sample_weights + [0.]
else:
val_inputs = val_x + val_y + val_sample_weights
elif validation_split and 0. < validation_split < 1.:
if any(K.is_tensor(t) for t in x):
raise ValueError(
'If your data is in the form of symbolic tensors, '
'you cannot use `validation_split`.')
do_validation = True
if hasattr(x[0], 'shape'):
split_at = int(int(x[0].shape[0]) * (1. - validation_split))
else:
split_at = int(len(x[0]) * (1. - validation_split))
x, val_x = (slice_arrays(x, 0, split_at),
slice_arrays(x, split_at))
y, val_y = (slice_arrays(y, 0, split_at),
slice_arrays(y, split_at))
sample_weights, val_sample_weights = (
slice_arrays(sample_weights, 0, split_at),
slice_arrays(sample_weights, split_at))
if self._uses_dynamic_learning_phase():
val_inputs = val_x + val_y + val_sample_weights + [0.]
else:
val_inputs = val_x + val_y + val_sample_weights
elif validation_steps:
do_validation = True
if self._uses_dynamic_learning_phase():
val_inputs = [0.]
# Prepare input arrays and training function.
if self._uses_dynamic_learning_phase():
fit_inputs = x + y + sample_weights + [1.]
else:
fit_inputs = x + y + sample_weights
self._make_train_function()
fit_function = self.train_function
# Prepare display labels.
out_labels = self.metrics_names
if do_validation:
self._make_test_function()
val_function = self.test_function
callback_metrics = copy.copy(out_labels) + [
'val_' + n for n in out_labels]
else:
callback_metrics = copy.copy(out_labels)
val_function = None
val_inputs = []
# Delegate logic to `fit_loop`.
return training_arrays.fit_loop(self, fit_function, fit_inputs,
out_labels=out_labels,
batch_size=batch_size,
epochs=epochs,
verbose=verbose,
callbacks=callbacks,
val_function=val_function,
val_inputs=val_inputs,
shuffle=shuffle,
callback_metrics=callback_metrics,
initial_epoch=initial_epoch,
steps_per_epoch=steps_per_epoch,
validation_steps=validation_steps)