Class Sequential
Inherits From: Model
Aliases:
- Class
tf.keras.Sequential
- Class
tf.keras.models.Sequential
Defined in tensorflow/python/keras/engine/sequential.py
.
Linear stack of layers.
Arguments:
layers
: list of layers to add to the model.
Example:
# Optionally, the first layer can receive an `input_shape` argument:
model = Sequential()
model.add(Dense(32, input_shape=(500,)))
# Afterwards, we do automatic shape inference:
model.add(Dense(32))
# This is identical to the following:
model = Sequential()
model.add(Dense(32, input_dim=500))
# And to the following:
model = Sequential()
model.add(Dense(32, batch_input_shape=(None, 500)))
# Note that you can also omit the `input_shape` argument:
# In that case the model gets built the first time you call `fit` (or other
# training and evaluation methods).
model = Sequential()
model.add(Dense(32))
model.add(Dense(32))
model.compile(optimizer=optimizer, loss=loss)
# This builds the model for the first time:
model.fit(x, y, batch_size=32, epochs=10)
# Note that when using this delayed-build pattern (no input shape specified),
# the model doesn't have any weights until the first call
# to a training/evaluation method (since it isn't yet built):
model = Sequential()
model.add(Dense(32))
model.add(Dense(32))
model.weights # returns []
# Whereas if you specify the input shape, the model gets built continuously
# as you are adding layers:
model = Sequential()
model.add(Dense(32, input_shape=(500,)))
model.add(Dense(32))
model.weights # returns list of length 4
When using the delayed-build pattern (no input shape specified), you can
choose to manually build your model by calling `build(batch_input_shape)`:
model = Sequential()
model.add(Dense(32))
model.add(Dense(32))
model.build((None, 500))
model.weights # returns list of length 4
__init__
__init__(
layers=None,
name=None
)
Properties
activity_regularizer
Optional regularizer function for the output of this layer.
dtype
input
Retrieves the input tensor(s) of a layer.
Only applicable if the layer has exactly one input, i.e. if it is connected to one incoming layer.
Returns:
Input tensor or list of input tensors.
Raises:
AttributeError
: if the layer is connected to more than one incoming layers.
Raises:
RuntimeError
: If called in Eager mode.AttributeError
: If no inbound nodes are found.
input_mask
Retrieves the input mask tensor(s) of a layer.
Only applicable if the layer has exactly one inbound node, i.e. if it is connected to one incoming layer.
Returns:
Input mask tensor (potentially None) or list of input mask tensors.
Raises:
AttributeError
: if the layer is connected to more than one incoming layers.
input_shape
Retrieves the input shape(s) of a layer.
Only applicable if the layer has exactly one input, i.e. if it is connected to one incoming layer, or if all inputs have the same shape.
Returns:
Input shape, as an integer shape tuple (or list of shape tuples, one tuple per input tensor).
Raises:
AttributeError
: if the layer has no defined input_shape.RuntimeError
: if called in Eager mode.
input_spec
Gets the network's input specs.
Returns:
A list of InputSpec
instances (one per input to the model)
or a single instance if the model has only one input.
layers
losses
Retrieves the network's losses.
Will only include losses that are either unconditional, or conditional on inputs to this model (e.g. will not include losses that depend on tensors that aren't inputs to this model).
When the network has no registered inputs, all losses are returned.
Returns:
A list of loss tensors.
metrics
Returns the model's metrics added using compile
, add_metric
APIs.
metrics_names
Returns the model's display labels for all outputs.
name
non_trainable_variables
non_trainable_weights
output
Retrieves the output tensor(s) of a layer.
Only applicable if the layer has exactly one output, i.e. if it is connected to one incoming layer.
Returns:
Output tensor or list of output tensors.
Raises:
AttributeError
: if the layer is connected to more than one incoming layers.RuntimeError
: if called in Eager mode.
output_mask
Retrieves the output mask tensor(s) of a layer.
Only applicable if the layer has exactly one inbound node, i.e. if it is connected to one incoming layer.
Returns:
Output mask tensor (potentially None) or list of output mask tensors.
Raises:
AttributeError
: if the layer is connected to more than one incoming layers.
output_shape
Retrieves the output shape(s) of a layer.
Only applicable if the layer has one output, or if all outputs have the same shape.
Returns:
Output shape, as an integer shape tuple (or list of shape tuples, one tuple per output tensor).
Raises:
AttributeError
: if the layer has no defined output shape.RuntimeError
: if called in Eager mode.
run_eagerly
Settable attribute indicating whether the model should run eagerly.
Running eagerly means that your model will be run step by step, like Python code. Your model might run slower, but it should become easier for you to debug it by stepping into individual layer calls.
By default, we will attempt to compile your model to a static graph to deliver the best execution performance.
Returns:
Boolean, whether the model should run eagerly.
state_updates
Returns the updates
from all layers that are stateful.
This is useful for separating training updates and state updates, e.g. when we need to update a layer's internal state during prediction.
Returns:
A list of update ops.
stateful
trainable_variables
trainable_weights
updates
Retrieves the network's updates.
Will only include updates that are either unconditional, or conditional on inputs to this model (e.g. will not include updates that were created by layers of this model outside of the model).
When the network has no registered inputs, all updates are returned.
Effectively, network.updates
behaves like layer.updates
.
Concrete example:
bn = keras.layers.BatchNormalization()
x1 = keras.layers.Input(shape=(10,))
_ = bn(x1) # This creates 2 updates.
x2 = keras.layers.Input(shape=(10,))
y2 = bn(x2) # This creates 2 more updates.
# The BN layer has now 4 updates.
self.assertEqual(len(bn.updates), 4)
# Let's create a model from x2 to y2.
model = keras.models.Model(x2, y2)
# The model does not list all updates from its underlying layers,
# but only the updates that are relevant to it. Updates created by layers
# outside of the model are discarded.
self.assertEqual(len(model.updates), 2)
# If you keep calling the model, you append to its updates, just like
# what happens for a layer.
x3 = keras.layers.Input(shape=(10,))
y3 = model(x3)
self.assertEqual(len(model.updates), 4)
# But if you call the inner BN layer independently, you don't affect
# the model's updates.
x4 = keras.layers.Input(shape=(10,))
_ = bn(x4)
self.assertEqual(len(model.updates), 4)
Returns:
A list of update ops.
variables
Returns the list of all layer variables/weights.
Alias of self.weights
.
Returns:
A list of variables.
weights
Returns the list of all layer variables/weights.
Returns:
A list of variables.
Methods
tf.keras.models.Sequential.__call__
__call__(
inputs,
*args,
**kwargs
)
Wraps call
, applying pre- and post-processing steps.
Arguments:
inputs
: input tensor(s).*args
: additional positional arguments to be passed toself.call
.**kwargs
: additional keyword arguments to be passed toself.call
.
Returns:
Output tensor(s).
Raises:
ValueError
: if the layer'scall
method returns None (an invalid value).
tf.keras.models.Sequential.__setattr__
__setattr__(
name,
value
)
Implement setattr(self, name, value).
tf.keras.models.Sequential.add
add(layer)
Adds a layer instance on top of the layer stack.
Arguments:
layer
: layer instance.
Raises:
TypeError
: Iflayer
is not a layer instance.ValueError
: In case thelayer
argument does not know its input shape.ValueError
: In case thelayer
argument has multiple output tensors, or is already connected somewhere else (forbidden inSequential
models).
tf.keras.models.Sequential.apply
apply(
inputs,
*args,
**kwargs
)
Apply the layer on a input.
This is an alias of self.__call__
.
Arguments:
inputs
: Input tensor(s).*args
: additional positional arguments to be passed toself.call
.**kwargs
: additional keyword arguments to be passed toself.call
.
Returns:
Output tensor(s).
tf.keras.models.Sequential.build
build(input_shape=None)
Builds the model based on input shapes received.
This is to be used for subclassed models, which do not know at instantiation time what their inputs look like.
This method only exists for users who want to call model.build()
in a
standalone way (as a substitute for calling the model on real data to
build it). It will never be called by the framework (and thus it will
never throw unexpected errors in an unrelated workflow).
Args:
input_shape: Single tuple, TensorShape, or list of shapes, where shapes are tuples, integers, or TensorShapes.
Raises:
ValueError
: 1. In case of invalid user-provided data (not of type tuple, list, or TensorShape).- If the model requires call arguments that are agnostic to the input shapes (positional or kwarg in call signature).
- If not all layers were properly built.
- If float type inputs are not supported within the layers.
In each of these cases, the user should build their model by calling it on real tensor data.
tf.keras.models.Sequential.compile
compile(
optimizer,
loss=None,
metrics=None,
loss_weights=None,
sample_weight_mode=None,
weighted_metrics=None,
target_tensors=None,
distribute=None,
**kwargs
)
Configures the model for training.
Arguments:
optimizer
: String (name of optimizer) or optimizer instance. Seetf.keras.optimizers
.loss
: String (name of objective function) or objective function. Seetf.losses
. If the model has multiple outputs, you can use a different loss on each output by passing a dictionary or a list of losses. The loss value that will be minimized by the model will then be the sum of all individual losses.metrics
: List of metrics to be evaluated by the model during training and testing. Typically you will usemetrics=['accuracy']
. To specify different metrics for different outputs of a multi-output model, you could also pass a dictionary, such asmetrics={'output_a': 'accuracy'}
.loss_weights
: Optional list or dictionary specifying scalar coefficients (Python floats) to weight the loss contributions of different model outputs. The loss value that will be minimized by the model will then be the weighted sum of all individual losses, weighted by theloss_weights
coefficients. If a list, it is expected to have a 1:1 mapping to the model's outputs. If a tensor, it is expected to map output names (strings) to scalar coefficients.sample_weight_mode
: If you need to do timestep-wise sample weighting (2D weights), set this to"temporal"
.None
defaults to sample-wise weights (1D). If the model has multiple outputs, you can use a differentsample_weight_mode
on each output by passing a dictionary or a list of modes.weighted_metrics
: List of metrics to be evaluated and weighted by sample_weight or class_weight during training and testing.target_tensors
: By default, Keras will create placeholders for the model's target, which will be fed with the target data during training. If instead you would like to use your own target tensors (in turn, Keras will not expect external Numpy data for these targets at training time), you can specify them via thetarget_tensors
argument. It can be a single tensor (for a single-output model), a list of tensors, or a dict mapping output names to target tensors.distribute
: The DistributionStrategy instance that we want to use to distribute the training of the model.**kwargs
: These arguments are passed totf.Session.run
.
Raises:
ValueError
: In case of invalid arguments foroptimizer
,loss
,metrics
orsample_weight_mode
.
tf.keras.models.Sequential.compute_mask
compute_mask(
inputs,
mask
)
Computes an output mask tensor.
Arguments:
inputs
: Tensor or list of tensors.mask
: Tensor or list of tensors.
Returns:
None or a tensor (or list of tensors, one per output tensor of the layer).
tf.keras.models.Sequential.compute_output_shape
compute_output_shape(input_shape)
Computes the output shape of the layer.
Assumes that the layer will be built to match that input shape provided.
Arguments:
input_shape
: Shape tuple (tuple of integers) or list of shape tuples (one per output tensor of the layer). Shape tuples can include None for free dimensions, instead of an integer.
Returns:
An input shape tuple.
tf.keras.models.Sequential.count_params
count_params()
Count the total number of scalars composing the weights.
Returns:
An integer count.
Raises:
ValueError
: if the layer isn't yet built (in which case its weights aren't yet defined).
tf.keras.models.Sequential.evaluate
evaluate(
x=None,
y=None,
batch_size=None,
verbose=1,
sample_weight=None,
steps=None,
max_queue_size=10,
workers=1,
use_multiprocessing=False
)
Returns the loss value & metrics values for the model in test mode.
Computation is done in batches.
Arguments:
x
: Input data. It could be:- A Numpy array (or array-like), or a list of arrays (in case the model has multiple inputs).
- A TensorFlow tensor, or a list of tensors (in case the model has multiple inputs).
- A dict mapping input names to the corresponding array/tensors, if the model has named inputs.
- A
tf.data
dataset or a dataset iterator. - A generator or
keras.utils.Sequence
instance.
y
: Target data. Like the input datax
, it could be either Numpy array(s) or TensorFlow tensor(s). It should be consistent withx
(you cannot have Numpy inputs and tensor targets, or inversely). Ifx
is a dataset, dataset iterator, generator orkeras.utils.Sequence
instance,y
should not be specified (since targets will be obtained from the iterator/dataset).batch_size
: Integer orNone
. Number of samples per gradient update. If unspecified,batch_size
will default to 32. Do not specify thebatch_size
is your data is in the form of symbolic tensors, dataset, dataset iterators, generators, orkeras.utils.Sequence
instances (since they generate batches).verbose
: 0 or 1. Verbosity mode. 0 = silent, 1 = progress bar.sample_weight
: Optional Numpy array of weights for the test samples, used for weighting the loss function. 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 specifysample_weight_mode="temporal"
incompile()
. This argument is not supported whenx
is a dataset or a dataset iterator, instead pass sample weights as the third element ofx
.steps
: Integer orNone
. Total number of steps (batches of samples) before declaring the evaluation round finished. Ignored with the default value ofNone
.max_queue_size
: Integer. Used for generator orkeras.utils.Sequence
input only. Maximum size for the generator queue. If unspecified,max_queue_size
will default to 10.workers
: Integer. Used for generator orkeras.utils.Sequence
input only. 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.use_multiprocessing
: Boolean. Used for generator orkeras.utils.Sequence
input only. IfTrue
, use process-based threading. If unspecified,use_multiprocessing
will default toFalse
. 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.
Returns:
Scalar test loss (if the model has a single output and no metrics)
or list of scalars (if the model has multiple outputs
and/or metrics). The attribute model.metrics_names
will give you
the display labels for the scalar outputs.
Raises:
ValueError
: in case of invalid arguments.
tf.keras.models.Sequential.evaluate_generator
evaluate_generator(
generator,
steps=None,
max_queue_size=10,
workers=1,
use_multiprocessing=False,
verbose=0
)
Evaluates the model on a data generator.
The generator should return the same kind of data
as accepted by test_on_batch
.
Arguments:
generator
: Generator yielding tuples (inputs, targets) or (inputs, targets, sample_weights) or an instance ofkeras.utils.Sequence
object in order to avoid duplicate data when using multiprocessing.steps
: Total number of steps (batches of samples) to yield fromgenerator
before stopping. Optional forSequence
: if unspecified, will use thelen(generator)
as a number of steps.max_queue_size
: maximum size for the generator queueworkers
: 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.use_multiprocessing
: Boolean. IfTrue
, use process-based threading. If unspecified,use_multiprocessing
will default toFalse
. 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.verbose
: Verbosity mode, 0 or 1.
Returns:
Scalar test loss (if the model has a single output and no metrics)
or list of scalars (if the model has multiple outputs
and/or metrics). The attribute model.metrics_names
will give you
the display labels for the scalar outputs.
Raises:
ValueError
: in case of invalid arguments.
Raises:
ValueError
: In case the generator yields data in an invalid format.
tf.keras.models.Sequential.fit
fit(
x=None,
y=None,
batch_size=None,
epochs=1,
verbose=1,
callbacks=None,
validation_split=0.0,
validation_data=None,
shuffle=True,
class_weight=None,
sample_weight=None,
initial_epoch=0,
steps_per_epoch=None,
validation_steps=None,
max_queue_size=10,
workers=1,
use_multiprocessing=False,
**kwargs
)
Trains the model for a fixed number of epochs (iterations on a dataset).
Arguments:
x
: Input data. It could be:- A Numpy array (or array-like), or a list of arrays (in case the model has multiple inputs).
- A TensorFlow tensor, or a list of tensors (in case the model has multiple inputs).
- A dict mapping input names to the corresponding array/tensors, if the model has named inputs.
- A
tf.data
dataset or a dataset iterator. Should return a tuple of either(inputs, targets)
or(inputs, targets, sample_weights)
. - A generator or
keras.utils.Sequence
returning(inputs, targets)
or(inputs, targets, sample weights)
.
y
: Target data. Like the input datax
, it could be either Numpy array(s) or TensorFlow tensor(s). It should be consistent withx
(you cannot have Numpy inputs and tensor targets, or inversely). Ifx
is a dataset, dataset iterator, generator, orkeras.utils.Sequence
instance,y
should not be specified (since targets will be obtained fromx
).batch_size
: Integer orNone
. Number of samples per gradient update. If unspecified,batch_size
will default to 32. Do not specify thebatch_size
if your data is in the form of symbolic tensors, dataset, dataset iterators, generators, orkeras.utils.Sequence
instances (since they generate batches).epochs
: Integer. Number of epochs to train the model. An epoch is an iteration over the entirex
andy
data provided. Note that in conjunction withinitial_epoch
,epochs
is to be understood as "final epoch". The model is not trained for a number of iterations given byepochs
, but merely until the epoch of indexepochs
is reached.verbose
: Integer. 0, 1, or 2. Verbosity mode. 0 = silent, 1 = progress bar, 2 = one line per epoch.callbacks
: List ofkeras.callbacks.Callback
instances. List of callbacks to apply during training. Seetf.keras.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 thex
andy
data provided, before shuffling. This argument is not supported whenx
is a dataset, dataset iterator, generator orkeras.utils.Sequence
instance.validation_data
: Data 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 overridevalidation_split
.validation_data
could be: - tuple(x_val, y_val)
of Numpy arrays or tensors - tuple(x_val, y_val, val_sample_weights)
of Numpy arrays - dataset or a dataset iterator For the first two cases,batch_size
must be provided. For the last case,validation_steps
must be provided.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 whensteps_per_epoch
is notNone
.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 specifysample_weight_mode="temporal"
incompile()
. This argument is not supported whenx
is a dataset, dataset iterator, generator, orkeras.utils.Sequence
instance, instead provide the sample_weights as the third element ofx
.initial_epoch
: Integer. Epoch at which to start training (useful for resuming a previous training run).steps_per_epoch
: Integer orNone
. 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 defaultNone
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 ifvalidation_data
is provided and is a dataset or dataset iterator. Total number of steps (batches of samples) to draw before stopping when performing validation at the end of every epoch.max_queue_size
: Integer. Used for generator orkeras.utils.Sequence
input only. Maximum size for the generator queue. If unspecified,max_queue_size
will default to 10.workers
: Integer. Used for generator orkeras.utils.Sequence
input only. 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.use_multiprocessing
: Boolean. Used for generator orkeras.utils.Sequence
input only. IfTrue
, use process-based threading. If unspecified,use_multiprocessing
will default toFalse
. 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.**kwargs
: Used for backwards compatibility.
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.
tf.keras.models.Sequential.fit_generator
fit_generator(
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
)
Fits the model on data yielded batch-by-batch by a Python generator.
The generator is run in parallel to the model, for efficiency. For instance, this allows you to do real-time data augmentation on images on CPU in parallel to training your model on GPU.
The use of keras.utils.Sequence
guarantees the ordering
and guarantees the single use of every input per epoch when
using use_multiprocessing=True
.
Arguments:
generator
: A generator or an instance ofSequence
(keras.utils.Sequence
) object in order to avoid duplicate data when using multiprocessing. The output of the generator must be either - a tuple(inputs, targets)
- a tuple(inputs, targets, sample_weights)
. This tuple (a single output of the generator) makes a single batch. Therefore, all arrays in this tuple must have the same length (equal to the size of this batch). Different batches may have different sizes. For example, the last batch of the epoch is commonly smaller than the others, if the size of the dataset is not divisible by the batch size. The generator is expected to loop over its data indefinitely. An epoch finishes whensteps_per_epoch
batches have been seen by the model.steps_per_epoch
: Total number of steps (batches of samples) to yield fromgenerator
before declaring one epoch finished and starting the next epoch. It should typically be equal to the number of samples of your dataset divided by the batch size. Optional forSequence
: if unspecified, will use thelen(generator)
as a number of steps.epochs
: Integer, total number of iterations on the data.verbose
: Verbosity mode, 0, 1, or 2.callbacks
: List of callbacks to be called during training.validation_data
: This can be either - a generator for the validation data - a tuple (inputs, targets) - a tuple (inputs, targets, sample_weights).validation_steps
: Only relevant ifvalidation_data
is a generator. Total number of steps (batches of samples) to yield fromgenerator
before stopping. Optional forSequence
: if unspecified, will use thelen(validation_data)
as a number of steps.class_weight
: Dictionary mapping class indices to a weight for the class.max_queue_size
: Integer. Maximum size for the generator queue. If unspecified,max_queue_size
will default to 10.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.use_multiprocessing
: Boolean. IfTrue
, use process-based threading. If unspecified,use_multiprocessing
will default toFalse
. 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.shuffle
: Boolean. Whether to shuffle the order of the batches at the beginning of each epoch. Only used with instances ofSequence
(keras.utils.Sequence
). Has no effect whensteps_per_epoch
is notNone
.initial_epoch
: Epoch at which to start training (useful for resuming a previous training run)
Returns:
A `History` object.
Example:
def generate_arrays_from_file(path):
while 1:
f = open(path)
for line in f:
# create numpy arrays of input data
# and labels, from each line in the file
x1, x2, y = process_line(line)
yield ({'input_1': x1, 'input_2': x2}, {'output': y})
f.close()
model.fit_generator(generate_arrays_from_file('/my_file.txt'),
steps_per_epoch=10000, epochs=10)
Raises:
ValueError
: In case the generator yields data in an invalid format.
tf.keras.models.Sequential.from_config
@classmethod
from_config(
cls,
config,
custom_objects=None
)
Instantiates a Model from its config (output of get_config()
).
Arguments:
config
: Model config dictionary.custom_objects
: Optional dictionary mapping names (strings) to custom classes or functions to be considered during deserialization.
Returns:
A model instance.
Raises:
ValueError
: In case of improperly formatted config dict.
tf.keras.models.Sequential.get_config
get_config()
Returns the config of the layer.
A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.
The config of a layer does not include connectivity
information, nor the layer class name. These are handled
by Network
(one layer of abstraction above).
Returns:
Python dictionary.
tf.keras.models.Sequential.get_input_at
get_input_at(node_index)
Retrieves the input tensor(s) of a layer at a given node.
Arguments:
node_index
: Integer, index of the node from which to retrieve the attribute. E.g.node_index=0
will correspond to the first time the layer was called.
Returns:
A tensor (or list of tensors if the layer has multiple inputs).
Raises:
RuntimeError
: If called in Eager mode.
tf.keras.models.Sequential.get_input_mask_at
get_input_mask_at(node_index)
Retrieves the input mask tensor(s) of a layer at a given node.
Arguments:
node_index
: Integer, index of the node from which to retrieve the attribute. E.g.node_index=0
will correspond to the first time the layer was called.
Returns:
A mask tensor (or list of tensors if the layer has multiple inputs).
tf.keras.models.Sequential.get_input_shape_at
get_input_shape_at(node_index)
Retrieves the input shape(s) of a layer at a given node.
Arguments:
node_index
: Integer, index of the node from which to retrieve the attribute. E.g.node_index=0
will correspond to the first time the layer was called.
Returns:
A shape tuple (or list of shape tuples if the layer has multiple inputs).
Raises:
RuntimeError
: If called in Eager mode.
tf.keras.models.Sequential.get_layer
get_layer(
name=None,
index=None
)
Retrieves a layer based on either its name (unique) or index.
If name
and index
are both provided, index
will take precedence.
Indices are based on order of horizontal graph traversal (bottom-up).
Arguments:
name
: String, name of layer.index
: Integer, index of layer.
Returns:
A layer instance.
Raises:
ValueError
: In case of invalid layer name or index.
tf.keras.models.Sequential.get_losses_for
get_losses_for(inputs)
Retrieves losses relevant to a specific set of inputs.
Arguments:
inputs
: Input tensor or list/tuple of input tensors.
Returns:
List of loss tensors of the layer that depend on inputs
.
Raises:
RuntimeError
: If called in Eager mode.
tf.keras.models.Sequential.get_output_at
get_output_at(node_index)
Retrieves the output tensor(s) of a layer at a given node.
Arguments:
node_index
: Integer, index of the node from which to retrieve the attribute. E.g.node_index=0
will correspond to the first time the layer was called.
Returns:
A tensor (or list of tensors if the layer has multiple outputs).
Raises:
RuntimeError
: If called in Eager mode.
tf.keras.models.Sequential.get_output_mask_at
get_output_mask_at(node_index)
Retrieves the output mask tensor(s) of a layer at a given node.
Arguments:
node_index
: Integer, index of the node from which to retrieve the attribute. E.g.node_index=0
will correspond to the first time the layer was called.
Returns:
A mask tensor (or list of tensors if the layer has multiple outputs).
tf.keras.models.Sequential.get_output_shape_at
get_output_shape_at(node_index)
Retrieves the output shape(s) of a layer at a given node.
Arguments:
node_index
: Integer, index of the node from which to retrieve the attribute. E.g.node_index=0
will correspond to the first time the layer was called.
Returns:
A shape tuple (or list of shape tuples if the layer has multiple outputs).
Raises:
RuntimeError
: If called in Eager mode.
tf.keras.models.Sequential.get_updates_for
get_updates_for(inputs)
Retrieves updates relevant to a specific set of inputs.
Arguments:
inputs
: Input tensor or list/tuple of input tensors.
Returns:
List of update ops of the layer that depend on inputs
.
Raises:
RuntimeError
: If called in Eager mode.
tf.keras.models.Sequential.get_weights
get_weights()
Retrieves the weights of the model.
Returns:
A flat list of Numpy arrays.
tf.keras.models.Sequential.load_weights
load_weights(
filepath,
by_name=False
)
Loads all layer weights, either from a TensorFlow or an HDF5 weight file.
If by_name
is False weights are loaded based on the network's
topology. This means the architecture should be the same as when the weights
were saved. Note that layers that don't have weights are not taken into
account in the topological ordering, so adding or removing layers is fine as
long as they don't have weights.
If by_name
is True, weights are loaded into layers only if they share the
same name. This is useful for fine-tuning or transfer-learning models where
some of the layers have changed.
Only topological loading (by_name=False
) is supported when loading weights
from the TensorFlow format. Note that topological loading differs slightly
between TensorFlow and HDF5 formats for user-defined classes inheriting from
tf.keras.Model
: HDF5 loads based on a flattened list of weights, while the
TensorFlow format loads based on the object-local names of attributes to
which layers are assigned in the Model
's constructor.
Arguments:
filepath
: String, path to the weights file to load. For weight files in TensorFlow format, this is the file prefix (the same as was passed tosave_weights
).by_name
: Boolean, whether to load weights by name or by topological order. Only topological loading is supported for weight files in TensorFlow format.
Returns:
When loading a weight file in TensorFlow format, returns the same status
object as tf.train.Checkpoint.restore
. When graph building, restore
ops are run automatically as soon as the network is built (on first call
for user-defined classes inheriting from Model
, immediately if it is
already built).
When loading weights in HDF5 format, returns None
.
Raises:
ImportError
: If h5py is not available and the weight file is in HDF5 format.
tf.keras.models.Sequential.pop
pop()
Removes the last layer in the model.
Raises:
TypeError
: if there are no layers in the model.
tf.keras.models.Sequential.predict
predict(
x,
batch_size=None,
verbose=0,
steps=None,
max_queue_size=10,
workers=1,
use_multiprocessing=False
)
Generates output predictions for the input samples.
Computation is done in batches.
Arguments:
x: Input samples. It could be:
- A Numpy array (or array-like), or a list of arrays
(in case the model has multiple inputs).
- A TensorFlow tensor, or a list of tensors
(in case the model has multiple inputs).
- A tf.data
dataset or a dataset iterator.
- A generator or keras.utils.Sequence
instance.
* 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
is your data is in the
form of symbolic tensors, dataset, dataset iterators,
generators, or keras.utils.Sequence
instances (since they generate
batches).
* verbose
: Verbosity mode, 0 or 1.
* 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. If 0, will execute the generator on the main thread.
* use_multiprocessing
: Boolean. Used for generator or
keras.utils.Sequence
input only. 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.
Returns:
Numpy array(s) of predictions.
Raises:
ValueError
: In case of mismatch between the provided input data and the model's expectations, or in case a stateful model receives a number of samples that is not a multiple of the batch size.
tf.keras.models.Sequential.predict_classes
predict_classes(
x,
batch_size=32,
verbose=0
)
Generate class predictions for the input samples.
The input samples are processed batch by batch.
Arguments:
x
: input data, as a Numpy array or list of Numpy arrays (if the model has multiple inputs).batch_size
: integer.verbose
: verbosity mode, 0 or 1.
Returns:
A numpy array of class predictions.
tf.keras.models.Sequential.predict_generator
predict_generator(
generator,
steps=None,
max_queue_size=10,
workers=1,
use_multiprocessing=False,
verbose=0
)
Generates predictions for the input samples from a data generator.
The generator should return the same kind of data as accepted by
predict_on_batch
.
Arguments:
generator
: Generator yielding batches of input samples or an instance ofkeras.utils.Sequence
object in order to avoid duplicate data when using multiprocessing.steps
: Total number of steps (batches of samples) to yield fromgenerator
before stopping. Optional forSequence
: if unspecified, will use thelen(generator)
as a number of steps.max_queue_size
: Maximum size for the generator queue.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.use_multiprocessing
: Boolean. IfTrue
, use process-based threading. If unspecified,use_multiprocessing
will default toFalse
. 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.verbose
: verbosity mode, 0 or 1.
Returns:
Numpy array(s) of predictions.
Raises:
ValueError
: In case the generator yields data in an invalid format.
tf.keras.models.Sequential.predict_on_batch
predict_on_batch(x)
Returns predictions for a single batch of samples.
Arguments:
x
: Input data. It could be:- A Numpy array (or array-like), or a list of arrays (in case the model has multiple inputs).
- A TensorFlow tensor, or a list of tensors (in case the model has multiple inputs).
- A
tf.data
dataset or a dataset iterator.
Returns:
Numpy array(s) of predictions.
Raises:
ValueError
: In case of mismatch between given number of inputs and expectations of the model.
tf.keras.models.Sequential.predict_proba
predict_proba(
x,
batch_size=32,
verbose=0
)
Generates class probability predictions for the input samples.
The input samples are processed batch by batch.
Arguments:
x
: input data, as a Numpy array or list of Numpy arrays (if the model has multiple inputs).batch_size
: integer.verbose
: verbosity mode, 0 or 1.
Returns:
A Numpy array of probability predictions.
tf.keras.models.Sequential.reset_metrics
reset_metrics()
Resets the state of metrics.
tf.keras.models.Sequential.reset_states
reset_states()
tf.keras.models.Sequential.save
save(
filepath,
overwrite=True,
include_optimizer=True
)
Saves the model to a single HDF5 file.
The savefile includes: - The model architecture, allowing to re-instantiate the model. - The model weights. - The state of the optimizer, allowing to resume training exactly where you left off.
This allows you to save the entirety of the state of a model in a single file.
Saved models can be reinstantiated via keras.models.load_model
.
The model returned by load_model
is a compiled model ready to be used (unless the saved model
was never compiled in the first place).
Arguments:
filepath
: String, path to the file to save the weights to.overwrite
: Whether to silently overwrite any existing file at the target location, or provide the user with a manual prompt.include_optimizer
: If True, save optimizer's state together.
Example:
from keras.models import load_model
model.save('my_model.h5') # creates a HDF5 file 'my_model.h5'
del model # deletes the existing model
# returns a compiled model
# identical to the previous one
model = load_model('my_model.h5')
tf.keras.models.Sequential.save_weights
save_weights(
filepath,
overwrite=True,
save_format=None
)
Saves all layer weights.
Either saves in HDF5 or in TensorFlow format based on the save_format
argument.
When saving in HDF5 format, the weight file has:
- layer_names
(attribute), a list of strings
(ordered names of model layers).
- For every layer, a group
named layer.name
- For every such layer group, a group attribute weight_names
,
a list of strings
(ordered names of weights tensor of the layer).
- For every weight in the layer, a dataset
storing the weight value, named after the weight tensor.
When saving in TensorFlow format, all objects referenced by the network are
saved in the same format as tf.train.Checkpoint
, including any Layer
instances or Optimizer
instances assigned to object attributes. For
networks constructed from inputs and outputs using tf.keras.Model(inputs,
outputs)
, Layer
instances used by the network are tracked/saved
automatically. For user-defined classes which inherit from tf.keras.Model
,
Layer
instances must be assigned to object attributes, typically in the
constructor. See the documentation of tf.train.Checkpoint
and
tf.keras.Model
for details.
Arguments:
filepath
: String, path to the file to save the weights to. When saving in TensorFlow format, this is the prefix used for checkpoint files (multiple files are generated). Note that the '.h5' suffix causes weights to be saved in HDF5 format.overwrite
: Whether to silently overwrite any existing file at the target location, or provide the user with a manual prompt.save_format
: Either 'tf' or 'h5'. Afilepath
ending in '.h5' or '.keras' will default to HDF5 ifsave_format
isNone
. OtherwiseNone
defaults to 'tf'.
Raises:
ImportError
: If h5py is not available when attempting to save in HDF5 format.ValueError
: For invalid/unknown format arguments.
tf.keras.models.Sequential.set_weights
set_weights(weights)
Sets the weights of the model.
Arguments:
weights
: A list of Numpy arrays with shapes and types matching the output ofmodel.get_weights()
.
tf.keras.models.Sequential.summary
summary(
line_length=None,
positions=None,
print_fn=None
)
Prints a string summary of the network.
Arguments:
line_length
: Total length of printed lines (e.g. set this to adapt the display to different terminal window sizes).positions
: Relative or absolute positions of log elements in each line. If not provided, defaults to[.33, .55, .67, 1.]
.print_fn
: Print function to use. Defaults toprint
. It will be called on each line of the summary. You can set it to a custom function in order to capture the string summary.
Raises:
ValueError
: ifsummary()
is called before the model is built.
tf.keras.models.Sequential.test_on_batch
test_on_batch(
x,
y=None,
sample_weight=None,
reset_metrics=True
)
Test the model on a single batch of samples.
Arguments:
x
: Input data. It could be:- A Numpy array (or array-like), or a list of arrays (in case the model has multiple inputs).
- A TensorFlow tensor, or a list of tensors (in case the model has multiple inputs).
- A dict mapping input names to the corresponding array/tensors, if the model has named inputs.
- A
tf.data
dataset or a dataset iterator.
y
: Target data. Like the input datax
, it could be either Numpy array(s) or TensorFlow tensor(s). It should be consistent withx
(you cannot have Numpy inputs and tensor targets, or inversely). Ifx
is a dataset or a dataset iterator,y
should not be specified (since targets will be obtained from the iterator).sample_weight
: Optional array of the same length as x, containing weights to apply to the model's loss for each sample. 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(). This argument is not supported whenx
is a dataset or a dataset iterator.reset_metrics
: IfTrue
, the metrics returned will be only for this batch. IfFalse
, the metrics will be statefully accumulated across batches.
Returns:
Scalar test loss (if the model has a single output and no metrics)
or list of scalars (if the model has multiple outputs
and/or metrics). The attribute model.metrics_names
will give you
the display labels for the scalar outputs.
Raises:
ValueError
: In case of invalid user-provided arguments.
tf.keras.models.Sequential.to_json
to_json(**kwargs)
Returns a JSON string containing the network configuration.
To load a network from a JSON save file, use
keras.models.model_from_json(json_string, custom_objects={})
.
Arguments:
**kwargs
: Additional keyword arguments to be passed tojson.dumps()
.
Returns:
A JSON string.
tf.keras.models.Sequential.to_yaml
to_yaml(**kwargs)
Returns a yaml string containing the network configuration.
To load a network from a yaml save file, use
keras.models.model_from_yaml(yaml_string, custom_objects={})
.
custom_objects
should be a dictionary mapping
the names of custom losses / layers / etc to the corresponding
functions / classes.
Arguments:
**kwargs
: Additional keyword arguments to be passed toyaml.dump()
.
Returns:
A YAML string.
Raises:
ImportError
: if yaml module is not found.
tf.keras.models.Sequential.train_on_batch
train_on_batch(
x,
y=None,
sample_weight=None,
class_weight=None,
reset_metrics=True
)
Runs a single gradient update on a single batch of data.
Arguments:
x
: Input data. It could be:- A Numpy array (or array-like), or a list of arrays (in case the model has multiple inputs).
- A TensorFlow tensor, or a list of tensors (in case the model has multiple inputs).
- A dict mapping input names to the corresponding array/tensors, if the model has named inputs.
- A
tf.data
dataset or a dataset iterator.
y
: Target data. Like the input datax
, it could be either Numpy array(s) or TensorFlow tensor(s). It should be consistent withx
(you cannot have Numpy inputs and tensor targets, or inversely). Ifx
is a dataset or a dataset iterator,y
should not be specified (since targets will be obtained from the iterator).sample_weight
: Optional array of the same length as x, containing weights to apply to the model's loss for each sample. 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(). This argument is not supported whenx
is a dataset or a dataset iterator.class_weight
: Optional dictionary mapping class indices (integers) to a weight (float) to apply to the model's loss for the samples from this class during training. This can be useful to tell the model to "pay more attention" to samples from an under-represented class.reset_metrics
: IfTrue
, the metrics returned will be only for this batch. IfFalse
, the metrics will be statefully accumulated across batches.
Returns:
Scalar training loss
(if the model has a single output and no metrics)
or list of scalars (if the model has multiple outputs
and/or metrics). The attribute model.metrics_names
will give you
the display labels for the scalar outputs.
Raises:
ValueError
: In case of invalid user-provided arguments.