def fit_loop(model,
inputs,
targets,
sample_weights=None,
batch_size=None,
epochs=100,
verbose=1,
callbacks=None,
val_inputs=None,
val_targets=None,
val_sample_weights=None,
shuffle=True,
callback_metrics=None,
initial_epoch=0,
steps_per_epoch=None,
validation_steps=None):
"""Abstract fit function for arrays of data.
Arguments:
model: Keras Model instance.
inputs: List of input arrays.
targets: List of target arrays.
sample_weights: Optional list of sample weight arrays.
batch_size: Integer batch size or None if unknown.
epochs: Number of times to iterate over the data
verbose: Verbosity mode, 0, 1 or 2
callbacks: List of callbacks to be called during training
val_inputs: List of input arrays.
val_targets: List of target arrays.
val_sample_weights: Optional list of sample weight arrays.
shuffle: Whether to shuffle the data at the beginning of each epoch
callback_metrics: List of strings, the display names of the metrics
passed to the callbacks. They should be the
concatenation of list the display names of the outputs of
`f` and the list of display names of the outputs of `f_val`.
initial_epoch: Epoch at which to start training
(useful for resuming a previous training run)
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_steps: Number of steps to run validation for
(only if doing validation from data tensors).
Ignored with the default value of `None`.
Returns:
`History` object.
Raises:
ValueError: in case of invalid arguments.
"""
model._make_train_function()
f = model.train_function
sample_weights = sample_weights or []
val_sample_weights = val_sample_weights or []
if model.uses_learning_phase and not isinstance(K.learning_phase(), int):
ins = inputs + targets + sample_weights + [1]
if val_inputs:
val_ins = val_inputs + val_targets + val_sample_weights + [1]
else:
ins = inputs + targets + sample_weights
if val_inputs:
val_ins = val_inputs + val_targets + val_sample_weights
if not val_inputs:
val_ins = []
do_validation = False
if val_inputs:
do_validation = True
if verbose and inputs and hasattr(inputs[0], 'shape') and hasattr(
val_inputs[0], 'shape'):
print('Train on %d samples, validate on %d samples' %
(inputs[0].shape[0], val_inputs[0].shape[0]))
if validation_steps:
do_validation = True
if steps_per_epoch is None:
raise ValueError('Can only use `validation_steps` '
'when doing step-wise '
'training, i.e. `steps_per_epoch` '
'must be set.')
out_labels = model.metrics_names
if do_validation:
callback_metrics = copy.copy(out_labels) + [
'val_' + n for n in out_labels
]
else:
callback_metrics = copy.copy(out_labels)
num_train_samples = training_utils.check_num_samples(
ins, batch_size, steps_per_epoch, 'steps_per_epoch')
if num_train_samples is not None:
index_array = np.arange(num_train_samples)
model.history = cbks.History()
all_callbacks = [
cbks.BaseLogger(stateful_metrics=model.stateful_metric_names)
]
if verbose:
if steps_per_epoch is not None:
count_mode = 'steps'
else:
count_mode = 'samples'
all_callbacks.append(
cbks.ProgbarLogger(count_mode,
stateful_metrics=model.stateful_metric_names))
all_callbacks += (callbacks or []) + [model.history]
callbacks = cbks.CallbackList(all_callbacks)
out_labels = out_labels or []
# it's possible to callback a different model than self
# (used by Sequential models)
if hasattr(model, 'callback_model') and model.callback_model:
callback_model = model.callback_model
else:
callback_model = model
callbacks.set_model(callback_model)
callbacks.set_params({
'batch_size': batch_size,
'epochs': epochs,
'steps': steps_per_epoch,
'samples': num_train_samples,
'verbose': verbose,
'do_validation': do_validation,
'metrics': callback_metrics or [],
})
callbacks.on_train_begin()
callback_model.stop_training = False
for cbk in callbacks:
cbk.validation_data = val_ins
# To prevent a slowdown, we find beforehand the arrays that need conversion.
feed = model._feed_inputs + model._feed_targets + model._feed_sample_weights
indices_for_conversion_to_dense = []
for i in range(len(feed)):
if issparse is not None and issparse(
ins[i]) and not K.is_sparse(feed[i]):
indices_for_conversion_to_dense.append(i)
for epoch in range(initial_epoch, epochs):
# Reset stateful metrics
for m in model.metrics:
if isinstance(m, Layer):
m.reset_states()
# Update callbacks
callbacks.on_epoch_begin(epoch)
epoch_logs = {}
if steps_per_epoch is not None:
for step_index in range(steps_per_epoch):
batch_logs = {}
batch_logs['batch'] = step_index
batch_logs['size'] = 1
callbacks.on_batch_begin(step_index, batch_logs)
try:
outs = f(ins)
except errors.OutOfRangeError:
logging.warning(
'Your dataset iterator ran out of data; '
'interrupting training. Make sure that your dataset '
'can generate at least `steps_per_epoch * epochs` '
'batches (in this case, %d batches).' %
steps_per_epoch * epochs)
break
if not isinstance(outs, list):
outs = [outs]
for l, o in zip(out_labels, outs):
batch_logs[l] = o
callbacks.on_batch_end(step_index, batch_logs)
if callback_model.stop_training:
break
if do_validation:
val_outs = test_loop(model,
val_inputs,
val_targets,
sample_weights=val_sample_weights,
batch_size=batch_size,
steps=validation_steps,
verbose=0)
if not isinstance(val_outs, list):
val_outs = [val_outs]
# Same labels assumed.
for l, o in zip(out_labels, val_outs):
epoch_logs['val_' + l] = o
else:
if shuffle == 'batch':
index_array = training_utils.batch_shuffle(
index_array, batch_size)
elif shuffle:
np.random.shuffle(index_array)
batches = make_batches(num_train_samples, batch_size)
for batch_index, (batch_start, batch_end) in enumerate(batches):
batch_ids = index_array[batch_start:batch_end]
try:
if isinstance(ins[-1], int):
# Do not slice the training phase flag.
ins_batch = slice_arrays(ins[:-1],
batch_ids) + [ins[-1]]
else:
ins_batch = slice_arrays(ins, batch_ids)
except TypeError:
raise TypeError('TypeError while preparing batch. '
'If using HDF5 input data, '
'pass shuffle="batch".')
batch_logs = {}
batch_logs['batch'] = batch_index
batch_logs['size'] = len(batch_ids)
callbacks.on_batch_begin(batch_index, batch_logs)
for i in indices_for_conversion_to_dense:
ins_batch[i] = ins_batch[i].toarray()
outs = f(ins_batch)
if not isinstance(outs, list):
outs = [outs]
for l, o in zip(out_labels, outs):
batch_logs[l] = o
callbacks.on_batch_end(batch_index, batch_logs)
if callback_model.stop_training:
break
if batch_index == len(batches) - 1: # Last batch.
if do_validation:
val_outs = test_loop(model,
val_inputs,
val_targets,
sample_weights=val_sample_weights,
batch_size=batch_size,
verbose=0)
if not isinstance(val_outs, list):
val_outs = [val_outs]
# Same labels assumed.
for l, o in zip(out_labels, val_outs):
epoch_logs['val_' + l] = o
callbacks.on_epoch_end(epoch, epoch_logs)
if callback_model.stop_training:
break
callbacks.on_train_end()
return model.history
def fit_loop(model,
inputs,
targets,
sample_weights=None,
val_inputs=None,
val_targets=None,
val_sample_weights=None,
batch_size=None,
epochs=100,
verbose=1,
callbacks=None,
shuffle=True,
callback_metrics=None,
initial_epoch=0,
steps_per_epoch=None,
validation_steps=None):
"""Abstract fit function for eager execution.
Arguments:
model: Instance of the model that is being executed in Eager mode.
inputs: List of input arrays.
targets: List of target arrays.
sample_weights: Optional list of sample weight arrays.
val_inputs: Input data for validation.
val_targets: Target data for validation.
val_sample_weights: Sample weight data for validation.
batch_size: Integer batch size or None if unknown.
epochs: Number of times to iterate over the data
verbose: Verbosity mode, 0, 1 or 2
callbacks: List of callbacks to be called during training
shuffle: Whether to shuffle the data at the beginning of each epoch
callback_metrics: List of strings, the display names of the metrics
passed to the callbacks. They should be the
concatenation of list the display names of the outputs of
`f` and the list of display names of the outputs of `f_val`.
initial_epoch: Epoch at which to start training
(useful for resuming a previous training run)
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_steps: Number of steps to run validation for (only if doing
validation from data tensors). Ignored with default value of `None`.
Returns:
`History` object.
Raises:
ValueError: In case of invalid argument values.
"""
if not batch_size:
raise ValueError(
'With eager execution, `batch_size` should be specified.')
if steps_per_epoch or validation_steps:
raise ValueError('With eager execution, `steps_per_epoch` and '
'`validation_steps` are not valid arguments '
'(set `batch_size` instead).')
# Required for Eager mode
with backend.learning_phase_scope(1):
do_validation = False
if val_inputs:
do_validation = True
if (verbose and inputs and hasattr(inputs[0], 'shape')
and hasattr(val_inputs[0], 'shape')):
print('Train on %d samples, validate on %d samples' %
(inputs[0].shape[0], val_inputs[0].shape[0]))
if validation_steps:
if steps_per_epoch is None:
raise ValueError(
'Can only use `validation_steps` when doing step-wise '
'training, i.e. `steps_per_epoch` must be set.')
do_validation = True
out_labels = model.metrics_names
if do_validation:
callback_metrics = copy.copy(out_labels) + [
'val_' + n for n in out_labels
]
else:
callback_metrics = copy.copy(out_labels)
if sample_weights:
feed_data = inputs + targets + sample_weights
else:
feed_data = inputs + targets
num_train_samples = training_utils.check_num_samples(
feed_data,
batch_size=batch_size,
steps=steps_per_epoch,
steps_name='steps_per_epoch')
if num_train_samples is not None:
index_array = np.arange(num_train_samples)
model.history = cbks.History()
callbacks = [cbks.BaseLogger()] + (callbacks or []) + [model.history]
if verbose:
if steps_per_epoch is not None:
count_mode = 'steps'
else:
count_mode = 'samples'
callbacks += [cbks.ProgbarLogger(count_mode)]
callbacks = cbks.CallbackList(callbacks)
# it's possible to callback a different model than self
# (used by Sequential models)
if hasattr(model, 'callback_model') and model.callback_model:
callback_model = model.callback_model
else:
callback_model = model
callbacks.set_model(callback_model)
callbacks.set_params({
'batch_size': batch_size,
'epochs': epochs,
'steps': steps_per_epoch,
'samples': num_train_samples,
'verbose': verbose,
'do_validation': do_validation,
'metrics': callback_metrics or [],
})
callbacks.on_train_begin()
callback_model.stop_training = False
for cbk in callbacks:
if not val_inputs:
cbk.validation_data = []
elif val_sample_weights:
cbk.validation_data = val_inputs + val_targets + val_sample_weights
else:
cbk.validation_data = val_inputs + val_targets
for epoch in range(initial_epoch, epochs):
callbacks.on_epoch_begin(epoch)
epoch_logs = {}
if shuffle == 'batch':
index_array = model._batch_shuffle(index_array, batch_size)
elif shuffle:
np.random.shuffle(index_array)
batches = generic_utils.make_batches(num_train_samples, batch_size)
for batch_index, (batch_start, batch_end) in enumerate(batches):
batch_ids = index_array[batch_start:batch_end]
try:
inputs_batch = slice_arrays(inputs,
batch_ids,
contiguous=not shuffle)
targets_batch = slice_arrays(targets,
batch_ids,
contiguous=not shuffle)
if sample_weights:
sample_weights_batch = slice_arrays(
sample_weights, batch_ids, contiguous=not shuffle)
else:
sample_weights_batch = None
except TypeError:
raise TypeError('TypeError while preparing batch. '
'If using HDF5 input data, '
'pass shuffle="batch".')
batch_logs = {}
batch_logs['batch'] = batch_index
batch_logs['size'] = len(batch_ids)
callbacks.on_batch_begin(batch_index, batch_logs)
inputs_batch = [
ops.convert_to_tensor(val, dtype=backend.floatx())
for val in inputs_batch
]
targets_batch = [
ops.convert_to_tensor(val, dtype=backend.floatx())
for val in targets_batch
]
if sample_weights:
sample_weights_batch = [
ops.convert_to_tensor(val, dtype=backend.floatx())
if val is not None else None
for val in sample_weights_batch
]
outs, loss, loss_metrics = _process_single_batch(
model,
inputs_batch,
targets_batch,
sample_weights=sample_weights_batch,
training=True)
if not isinstance(outs, list):
outs = [outs]
for l, o in zip(out_labels, outs):
batch_logs[l] = o
# Required for Eager mode
metrics_results = _eager_metrics_fn(model, outs, targets_batch)
batch_logs['loss'] = tensor_util.constant_value(
backend.mean(loss))
for k, v in zip(model.metrics_names, [backend.mean(loss)] +
loss_metrics + metrics_results):
batch_logs[k] = tensor_util.constant_value(v)
callbacks.on_batch_end(batch_index, batch_logs)
if callback_model.stop_training:
break
if batch_index == len(batches) - 1: # Last batch.
if do_validation:
val_outs = test_loop(model,
val_inputs,
val_targets,
sample_weights=val_sample_weights,
batch_size=batch_size,
verbose=0)
if not isinstance(val_outs, list):
val_outs = [val_outs]
# Same labels assumed.
for l, o in zip(out_labels, val_outs):
epoch_logs['val_' + l] = o
callbacks.on_epoch_end(epoch, epoch_logs)
if callback_model.stop_training:
break
callbacks.on_train_end()
return model.history
def fit_loop(model,
inputs,
targets,
sample_weights=None,
class_weight=None,
val_inputs=None,
val_targets=None,
val_sample_weights=None,
batch_size=None,
epochs=1,
verbose=1,
callbacks=None,
shuffle=True,
callback_metrics=None,
initial_epoch=0,
steps_per_epoch=None,
validation_steps=None):
"""Fit function for eager execution.
Arguments:
model: Instance of the model that is being executed in Eager mode.
inputs: List of input arrays.
targets: List of target arrays.
sample_weights: Optional list of sample weight arrays.
class_weight: Optional class-weight array to weight the importance of
samples in `inputs` based on the class they belong to, as conveyed by
`targets`.
val_inputs: Input data for validation.
val_targets: Target data for validation.
val_sample_weights: Sample weight data for validation.
batch_size: Integer batch size or None if unknown.
epochs: Number of times to iterate over the data
verbose: Verbosity mode, 0, 1 or 2
callbacks: List of callbacks to be called during training
shuffle: Whether to shuffle the data at the beginning of each epoch
callback_metrics: List of strings, the display names of the metrics
passed to the callbacks. They should be the
concatenation of list the display names of the outputs of
`f` and the list of display names of the outputs of `f_val`.
initial_epoch: Epoch at which to start training
(useful for resuming a previous training run)
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_steps: Number of steps to run validation for (only if doing
validation from data tensors). Ignored with default value of `None`.
Returns:
`History` object.
Raises:
ValueError: In case of invalid argument values.
"""
# Required for eager execution
with backend.learning_phase_scope(1):
do_validation = False
if val_inputs:
do_validation = True
if (steps_per_epoch is None and verbose and inputs
and hasattr(inputs[0], 'shape')
and hasattr(val_inputs[0], 'shape')):
print('Train on %d samples, validate on %d samples' %
(inputs[0].shape[0], val_inputs[0].shape[0]))
num_train_samples = None
out_labels = None
if steps_per_epoch is None or model._is_compiled:
out_labels = model.metrics_names
if do_validation:
callback_metrics = copy.copy(out_labels) + [
'val_' + n for n in out_labels
]
else:
callback_metrics = copy.copy(out_labels)
if steps_per_epoch is None:
if sample_weights:
feed_data = inputs + targets + sample_weights
else:
feed_data = inputs + targets
num_train_samples = training_utils.check_num_samples(
feed_data,
batch_size=batch_size,
steps=steps_per_epoch,
steps_name='steps_per_epoch')
if num_train_samples is not None:
index_array = np.arange(num_train_samples)
model.history = cbks.History()
callbacks = [cbks.BaseLogger()] + (callbacks or []) + [model.history]
if verbose:
if steps_per_epoch is not None:
count_mode = 'steps'
else:
count_mode = 'samples'
callbacks += [cbks.ProgbarLogger(count_mode)]
callbacks = cbks.CallbackList(callbacks)
# it's possible to callback a different model than self
# (used by Sequential models)
if hasattr(model, 'callback_model') and model.callback_model:
callback_model = model.callback_model
else:
callback_model = model
callbacks.set_model(callback_model)
callbacks.set_params({
'batch_size': batch_size,
'epochs': epochs,
'steps': steps_per_epoch,
'samples': num_train_samples,
'verbose': verbose,
'do_validation': do_validation,
'metrics': callback_metrics or [],
})
callbacks.on_train_begin()
callback_model.stop_training = False
for cbk in callbacks:
if not val_inputs:
cbk.validation_data = []
elif isinstance(val_inputs, iterator_ops.EagerIterator):
cbk.validation_data = val_inputs
elif val_sample_weights:
cbk.validation_data = val_inputs + val_targets + val_sample_weights
else:
cbk.validation_data = val_inputs + val_targets
for epoch in range(initial_epoch, epochs):
callbacks.on_epoch_begin(epoch)
epoch_logs = {}
if steps_per_epoch is not None:
iterator_fit_loop(model,
inputs,
class_weight,
steps_per_epoch=steps_per_epoch,
callback_model=callback_model,
out_labels=out_labels,
epoch_logs=epoch_logs,
val_inputs=val_inputs,
val_targets=val_targets,
val_sample_weights=val_sample_weights,
epochs=epochs,
verbose=verbose,
callbacks=callbacks,
callback_metrics=callback_metrics,
validation_steps=validation_steps,
do_validation=do_validation)
else:
batch_fit_loop(model,
inputs,
targets,
epoch_logs=epoch_logs,
index_array=index_array,
out_labels=out_labels,
callback_model=callback_model,
batch_size=batch_size,
sample_weights=sample_weights,
val_inputs=val_inputs,
val_targets=val_targets,
val_sample_weights=val_sample_weights,
callbacks=callbacks,
shuffle=shuffle,
num_train_samples=num_train_samples,
do_validation=do_validation)
callbacks.on_epoch_end(epoch, epoch_logs)
if callback_model.stop_training:
break
callbacks.on_train_end()
return model.history
def fit_loop(model,
ins,
out_labels=None,
batch_size=None,
epochs=100,
verbose=1,
callbacks=None,
val_ins=None,
shuffle=True,
callback_metrics=None,
initial_epoch=0,
steps_per_epoch=None,
validation_steps=None):
"""Abstract fit function for `f(ins)`.
Assume that f returns a list, labeled by out_labels.
Arguments:
model: Instance of the model that is being executed in Eager mode.
ins: List of tensors to be fed to `f`
out_labels: List of strings, display names of
the outputs of `f`
batch_size: Integer batch size or None if unknown.
epochs: Number of times to iterate over the data
verbose: Verbosity mode, 0, 1 or 2
callbacks: List of callbacks to be called during training
val_ins: List of tensors to be fed to `val_f`
shuffle: Whether to shuffle the data at the beginning of each epoch
callback_metrics: List of strings, the display names of the metrics
passed to the callbacks. They should be the
concatenation of list the display names of the outputs of
`f` and the list of display names of the outputs of `f_val`.
initial_epoch: Epoch at which to start training
(useful for resuming a previous training run)
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_steps: Number of steps to run validation for (only if doing
validation from data tensors). Ignored with default value of `None`.
Returns:
`History` object.
Raises:
ValueError: In case of invalid argument values.
"""
# Required for Eager mode
K.set_learning_phase(True)
do_validation = False
if val_ins:
do_validation = True
if (verbose and ins and hasattr(ins[0], 'shape')
and hasattr(val_ins[0], 'shape')):
print('Train on %d samples, validate on %d samples' %
(ins[0].shape[0], val_ins[0].shape[0]))
if validation_steps:
if steps_per_epoch is None:
raise ValueError(
'Can only use `validation_steps` when doing step-wise '
'training, i.e. `steps_per_epoch` must be set.')
do_validation = True
num_train_samples = model._check_num_samples(ins, batch_size,
steps_per_epoch,
'steps_per_epoch')
if num_train_samples is not None:
index_array = np.arange(num_train_samples)
model.history = cbks.History()
callbacks = [cbks.BaseLogger()] + (callbacks or []) + [model.history]
if verbose:
if steps_per_epoch is not None:
count_mode = 'steps'
else:
count_mode = 'samples'
callbacks += [cbks.ProgbarLogger(count_mode)]
callbacks = cbks.CallbackList(callbacks)
out_labels = out_labels or []
# it's possible to callback a different model than self
# (used by Sequential models)
if hasattr(model, 'callback_model') and model.callback_model:
callback_model = model.callback_model
else:
callback_model = model
callbacks.set_model(callback_model)
callbacks.set_params({
'batch_size': batch_size,
'epochs': epochs,
'steps': steps_per_epoch,
'samples': num_train_samples,
'verbose': verbose,
'do_validation': do_validation,
'metrics': callback_metrics or [],
})
callbacks.on_train_begin()
callback_model.stop_training = False
for cbk in callbacks:
cbk.validation_data = val_ins
for epoch in range(initial_epoch, epochs):
callbacks.on_epoch_begin(epoch)
epoch_logs = {}
if shuffle == 'batch':
index_array = model._batch_shuffle(index_array, batch_size)
elif shuffle:
np.random.shuffle(index_array)
batches = _make_batches(num_train_samples, batch_size)
for batch_index, (batch_start, batch_end) in enumerate(batches):
batch_ids = index_array[batch_start:batch_end]
try:
if isinstance(ins[-1], float):
# Do not slice the training phase flag.
ins_batch = _slice_arrays(ins[:-1], batch_ids) + [ins[-1]]
else:
ins_batch = _slice_arrays(ins, batch_ids)
except TypeError:
raise TypeError('TypeError while preparing batch. '
'If using HDF5 input data, '
'pass shuffle="batch".')
batch_logs = {}
batch_logs['batch'] = batch_index
batch_logs['size'] = len(batch_ids)
callbacks.on_batch_begin(batch_index, batch_logs)
ins_batch_converted = []
for ib in ins_batch:
ins_batch_converted.append(
ops.convert_to_tensor(ib, dtype=K.floatx()))
eager_model_inputs = []
eager_model_outputs = []
for i in range(len(model.inputs)):
eager_model_inputs.append(ins_batch_converted[i])
for i in range(len(model.inputs), len(ins_batch_converted)):
eager_model_outputs.append(ins_batch_converted[i])
outs, loss, loss_metrics = _process_single_batch(
eager_model_inputs, eager_model_outputs, model)
if not isinstance(outs, list):
outs = [outs]
for l, o in zip(out_labels, outs):
batch_logs[l] = o
# Required for Eager mode
metrics_names, metrics_results = _eager_metrics_fn(
model, outs, eager_model_outputs)
batch_logs['loss'] = tensor_util.constant_value(K.mean(loss))
# TODO(anjalisridhar): Move this to compile to avoid duplicate code.
# In graph mode we set the metric names in compile. However in
# Eager mode we calculate the metrics for each batch in fit_loop.
# We could calculate the metric names and functions in compile.
# This would avoid setting the callback parameters separately.
# We need to do this for the first iteration alone
for m in metrics_names:
if m not in callback_metrics:
callback_metrics.append(m)
callbacks.set_params({
'batch_size': batch_size,
'epochs': epochs,
'steps': steps_per_epoch,
'samples': num_train_samples,
'verbose': verbose,
'do_validation': do_validation,
'metrics': callback_metrics or [],
})
for k, v in zip(model.metrics_names,
[K.mean(loss)] + loss_metrics + metrics_results):
batch_logs[k] = tensor_util.constant_value(v)
callbacks.on_batch_end(batch_index, batch_logs)
if callback_model.stop_training:
break
if batch_index == len(batches) - 1: # Last batch.
if do_validation:
val_outs = test_loop(model,
val_ins,
batch_size=batch_size,
verbose=0)
if not isinstance(val_outs, list):
val_outs = [val_outs]
# Same labels assumed.
for l, o in zip(out_labels, val_outs):
epoch_logs['val_' + l] = o
callbacks.on_epoch_end(epoch, epoch_logs)
if callback_model.stop_training:
break
callbacks.on_train_end()
return model.history
def fit_generator(model,
generator,
steps_per_epoch=None,
epochs=1,
verbose=1,
callbacks=None,
validation_data=None,
validation_steps=None,
class_weight=None,
max_queue_size=10,
workers=1,
use_multiprocessing=False,
shuffle=True,
initial_epoch=0):
"""See docstring for `Model.fit_generator`."""
wait_time = 0.01 # in seconds
epoch = initial_epoch
do_validation = bool(validation_data)
model._make_train_function()
if do_validation:
model._make_test_function()
is_sequence = isinstance(generator, Sequence)
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:
if is_sequence:
steps_per_epoch = len(generator)
else:
raise ValueError('`steps_per_epoch=None` is only valid for a'
' generator based on the `keras.utils.Sequence`'
' class. Please specify `steps_per_epoch` or use'
' the `keras.utils.Sequence` class.')
# python 2 has 'next', 3 has '__next__'
# avoid any explicit version checks
val_gen = (hasattr(validation_data, 'next')
or hasattr(validation_data, '__next__')
or isinstance(validation_data, Sequence))
if (val_gen and not isinstance(validation_data, Sequence)
and not validation_steps):
raise ValueError('`validation_steps=None` is only valid for a'
' generator based on the `keras.utils.Sequence`'
' class. Please specify `validation_steps` or use'
' the `keras.utils.Sequence` class.')
# Prepare display labels.
out_labels = model.metrics_names
callback_metrics = out_labels + ['val_%s' % n for n in out_labels]
# prepare callbacks
model.history = cbks.History()
callbacks = [cbks.BaseLogger()] + (callbacks or []) + [model.history]
if verbose:
callbacks += [cbks.ProgbarLogger(count_mode='steps')]
callbacks = cbks.CallbackList(callbacks)
# it's possible to callback a different model than self:
if hasattr(model, 'callback_model') and model.callback_model:
callback_model = model.callback_model
else:
callback_model = model
callbacks.set_model(callback_model)
callbacks.set_params({
'epochs': epochs,
'steps': steps_per_epoch,
'verbose': verbose,
'do_validation': do_validation,
'metrics': callback_metrics,
})
callbacks.on_train_begin()
enqueuer = None
val_enqueuer = None
try:
if do_validation and not val_gen:
# Prepare data for validation
if len(validation_data) == 2:
val_x, val_y = validation_data # pylint: disable=unpacking-non-sequence
val_sample_weight = None
elif len(validation_data) == 3:
val_x, val_y, val_sample_weight = validation_data # pylint: disable=unpacking-non-sequence
else:
raise ValueError('`validation_data` should be a tuple '
'`(val_x, val_y, val_sample_weight)` '
'or `(val_x, val_y)`. Found: ' +
str(validation_data))
val_x, val_y, val_sample_weights = model._standardize_user_data(
val_x, val_y, val_sample_weight)
val_data = val_x + val_y + val_sample_weights
if model.uses_learning_phase and not isinstance(
K.learning_phase(), int):
val_data += [0.]
for cbk in callbacks:
cbk.validation_data = val_data
if workers > 0:
if is_sequence:
enqueuer = OrderedEnqueuer(
generator,
use_multiprocessing=use_multiprocessing,
shuffle=shuffle)
else:
enqueuer = GeneratorEnqueuer(
generator,
use_multiprocessing=use_multiprocessing,
wait_time=wait_time)
enqueuer.start(workers=workers, max_queue_size=max_queue_size)
output_generator = enqueuer.get()
else:
if is_sequence:
output_generator = iter(generator)
else:
output_generator = generator
callback_model.stop_training = False
# Construct epoch logs.
epoch_logs = {}
while epoch < epochs:
callbacks.on_epoch_begin(epoch)
steps_done = 0
batch_index = 0
while steps_done < steps_per_epoch:
generator_output = next(output_generator)
if not hasattr(generator_output, '__len__'):
raise ValueError('Output of generator should be '
'a tuple `(x, y, sample_weight)` '
'or `(x, y)`. Found: ' +
str(generator_output))
if len(generator_output) == 2:
x, y = generator_output
sample_weight = None
elif len(generator_output) == 3:
x, y, sample_weight = generator_output
else:
raise ValueError('Output of generator should be '
'a tuple `(x, y, sample_weight)` '
'or `(x, y)`. Found: ' +
str(generator_output))
# build batch logs
batch_logs = {}
if isinstance(x, list):
batch_size = x[0].shape[0]
elif isinstance(x, dict):
batch_size = list(x.values())[0].shape[0]
else:
batch_size = x.shape[0]
batch_logs['batch'] = batch_index
batch_logs['size'] = batch_size
callbacks.on_batch_begin(batch_index, batch_logs)
outs = model.train_on_batch(x,
y,
sample_weight=sample_weight,
class_weight=class_weight)
if not isinstance(outs, list):
outs = [outs]
for l, o in zip(out_labels, outs):
batch_logs[l] = o
callbacks.on_batch_end(batch_index, batch_logs)
batch_index += 1
steps_done += 1
# Epoch finished.
if steps_done >= steps_per_epoch and do_validation:
if val_gen:
val_outs = evaluate_generator(
model,
validation_data,
validation_steps,
workers=workers,
use_multiprocessing=use_multiprocessing,
max_queue_size=max_queue_size)
else:
# No need for try/except because
# data has already been validated.
val_outs = model.evaluate(
val_x,
val_y,
batch_size=batch_size,
sample_weight=val_sample_weights,
verbose=0)
if not isinstance(val_outs, list):
val_outs = [val_outs]
# Same labels assumed.
for l, o in zip(out_labels, val_outs):
epoch_logs['val_' + l] = o
if callback_model.stop_training:
break
callbacks.on_epoch_end(epoch, epoch_logs)
epoch += 1
if callback_model.stop_training:
break
finally:
try:
if enqueuer is not None:
enqueuer.stop()
finally:
if val_enqueuer is not None:
val_enqueuer.stop()
callbacks.on_train_end()
return model.history
