hub.KerasLayer

Wraps a SavedModel (or a legacy TF1 Hub format) as a Keras Layer.

hub.KerasLayer(
    handle,
    trainable=False,
    arguments=None,
    _sentinel=None,
    tags=None,
    signature=None,
    signature_outputs_as_dict=None,
    output_key=None,
    output_shape=None,
    load_options=None,
    **kwargs
)

Used in the notebooks

Used in the guide	Used in the tutorials
Using Counterfactual Logit Pairing with Keras	Universal Sentence Encoder SentEval demo Bangla Article Classification With TF-Hub Exploring the TF-Hub CORD-19 Swivel Embeddings CropNet: Cassava Disease Detection Retraining an Image Classifier

This layer wraps a callable object for use as a Keras layer. The callable object can be passed directly, or be specified by a Python string with a handle that gets passed to hub.load().

This is the preferred API to load a TF2-style SavedModel from TF Hub into a Keras model. Calling this function requires TF 1.15 or newer. It can be called both in eager and graph mode.

The callable object is expected to follow the conventions detailed below. (These are met by TF2-compatible modules loaded from TensorFlow Hub.)

The callable is invoked with a single positional argument set to one tensor or a nest of tensors containing the inputs to the layer. If the callable accepts a training argument, a Python boolean is passed for it. It is True if this layer is marked trainable and called for training, analogous to keras.layers.BatchNormalization. (By contrast, keras.layers.Dropout ignores the trainable state and applies the training argument verbatim.)

If present, the following attributes of callable are understood to have special meanings: variables: a list of all tf.Variable objects that the callable depends on. trainable_variables: those elements of variables that are reported as trainable variables of this Keras Layer when the layer is trainable. regularization_losses: a list of callables to be added as losses of this Keras Layer when the layer is trainable. Each one must accept zero arguments and return a scalar tensor.

Note: to work-around missing shape inference functionalities from functions created from FunctionDefs, in rare cases one has to pass an 'output_shape' and potentially 'input_shape' and 'dtype'. E.g. the following is a typical work-around:

hub.KerasLayer(
    "/tmp/text_embedding_model",
    output_shape=[20],  # Outputs a tensor with shape [batch_size, 20].
    input_shape=[],     # Expects a tensor of shape [batch_size] as input.
    dtype=tf.string)    # Expects a tf.string input tensor.

Note: This layer can be used inside the model_fn of a TF2 Estimator. See the migration guide for guidance on how to pick up trainable variables, losses and updates explicitly from Keras objects instead of relying on graph collections. This layer class does not support graph collections. Distributed training of the Estimator requires setting the option session_config.share_cluster_devices_in_session within the tf.estimator.RunConfig. (This option was experimental from TF1.14 to TF2.1.)

Note: The data types used by a saved model have been fixed at saving time. Using keras.mixed_precision etc. has no effect on the saved model that gets loaded by a hub.KerasLayer.

Attributes
handle	A callable object (subject to the conventions above), or a Python string to load a saved model via hub.load(). A string is required to save the Keras config of this Layer.
trainable	Optional. A boolean controlling whether this layer is trainable. Must not be set to True when using a signature (raises ValueError), including the use of legacy TF1 Hub format.
arguments	Optional. A dict with additional keyword arguments passed to the callable. These must be JSON-serializable to save the Keras config of this layer, and are not tracked as checkpointing dependencies of this layer.
_sentinel	Used to prevent further positional arguments.
tags	Optional. If set indicates which graph variant to use. For legacy models in TF1 Hub format leaving unset means to use the empty tags set.
signature	Optional. If set, KerasLayer will use the requested signature. For legacy models in TF1 Hub format leaving unset means to use the default signature. When using a signature, either signature_outputs_as_dict or output_key have to set.
signature_outputs_as_dict	If set to True, the call to this layer returns a dict of all the signature outputs. Can only be used if a signature is specified (or default signature is used for legacy models in TF1 Hub format).
output_key	Name of the output item to return if the layer returns a dict. For legacy models in TF1 Hub format leaving unset means to return the default output.
output_shape	A tuple or a nest of tuples with the (possibly partial) output shapes of the callable without leading batch size. This must have the same nesting structure as the output of the callable object and cover all output tensors.
load_options	Optional, tf.saved_model.LoadOptions object that specifies options for loading when a Python string is provided as handle. This argument can only be used from TensorFlow 2.3 onwards.
**kwargs	Forwarded to Keras' base Layer constructor.
activity_regularizer	Optional regularizer function for the output of this layer.
compute_dtype	The dtype of the layer's computations. This is equivalent to Layer.dtype_policy.compute_dtype. Unless mixed precision is used, this is the same as Layer.dtype, the dtype of the weights. Layers automatically cast their inputs to the compute dtype, which causes computations and the output to be in the compute dtype as well. This is done by the base Layer class in Layer.call, so you do not have to insert these casts if implementing your own layer. Layers often perform certain internal computations in higher precision when compute_dtype is float16 or bfloat16 for numeric stability. The output will still typically be float16 or bfloat16 in such cases.
dtype	The dtype of the layer weights. This is equivalent to Layer.dtype_policy.variable_dtype. Unless mixed precision is used, this is the same as Layer.compute_dtype, the dtype of the layer's computations.
dtype_policy	The dtype policy associated with this layer. This is an instance of a tf.keras.mixed_precision.Policy.
dynamic	Whether the layer is dynamic (eager-only); set in the constructor.
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.
input_spec	InputSpec instance(s) describing the input format for this layer. When you create a layer subclass, you can set self.input_spec to enable the layer to run input compatibility checks when it is called. Consider a Conv2D layer: it can only be called on a single input tensor of rank 4. As such, you can set, in __init__(): self.input_spec = tf.keras.layers.InputSpec(ndim=4) Now, if you try to call the layer on an input that isn't rank 4 (for instance, an input of shape (2,), it will raise a nicely-formatted error: ValueError: Input 0 of layer conv2d is incompatible with the layer: expected ndim=4, found ndim=1. Full shape received: [2] Input checks that can be specified via input_spec include: Structure (e.g. a single input, a list of 2 inputs, etc) Shape Rank (ndim) Dtype For more information, see tf.keras.layers.InputSpec.
losses	List of losses added using the add_loss() API. Variable regularization tensors are created when this property is accessed, so it is eager safe: accessing losses under a tf.GradientTape will propagate gradients back to the corresponding variables. class MyLayer(tf.keras.layers.Layer): def call(self, inputs): self.add_loss(tf.abs(tf.reduce_mean(inputs))) return inputs l = MyLayer() l(np.ones((10, 1))) l.losses [1.0] inputs = tf.keras.Input(shape=(10,)) x = tf.keras.layers.Dense(10)(inputs) outputs = tf.keras.layers.Dense(1)(x) model = tf.keras.Model(inputs, outputs) # Activity regularization. len(model.losses) 0 model.add_loss(tf.abs(tf.reduce_mean(x))) len(model.losses) 1 inputs = tf.keras.Input(shape=(10,)) d = tf.keras.layers.Dense(10, kernel_initializer='ones') x = d(inputs) outputs = tf.keras.layers.Dense(1)(x) model = tf.keras.Model(inputs, outputs) # Weight regularization. model.add_loss(lambda: tf.reduce_mean(d.kernel)) model.losses [<tf.Tensor: shape=(), dtype=float32, numpy=1.0>]
metrics	List of metrics attached to the layer.
name	Name of the layer (string), set in the constructor.
name_scope	Returns a tf.name_scope instance for this class.
non_trainable_weights	List of all non-trainable weights tracked by this layer. Non-trainable weights are not updated during training. They are expected to be updated manually in call().
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.
resolved_object	Returns the callable object to which handle resolved in __init__.
submodules	Sequence of all sub-modules. Submodules are modules which are properties of this module, or found as properties of modules which are properties of this module (and so on). a = tf.Module() b = tf.Module() c = tf.Module() a.b = b b.c = c list(a.submodules) == [b, c] True list(b.submodules) == [c] True list(c.submodules) == [] True
supports_masking	Whether this layer supports computing a mask using compute_mask.
trainable_weights	List of all trainable weights tracked by this layer. Trainable weights are updated via gradient descent during training.
variable_dtype	Alias of Layer.dtype, the dtype of the weights.
weights	Returns the list of all layer variables/weights.

Methods

add_loss

add_loss(
    losses, **kwargs
)

Add loss tensor(s), potentially dependent on layer inputs.

Some losses (for instance, activity regularization losses) may be dependent on the inputs passed when calling a layer. Hence, when reusing the same layer on different inputs a and b, some entries in layer.losses may be dependent on a and some on b. This method automatically keeps track of dependencies.

This method can be used inside a subclassed layer or model's call function, in which case losses should be a Tensor or list of Tensors.

Example:

class MyLayer(tf.keras.layers.Layer):
  def call(self, inputs):
    self.add_loss(tf.abs(tf.reduce_mean(inputs)))
    return inputs

The same code works in distributed training: the input to add_loss() is treated like a regularization loss and averaged across replicas by the training loop (both built-in Model.fit() and compliant custom training loops).

The add_loss method can also be called directly on a Functional Model during construction. In this case, any loss Tensors passed to this Model must be symbolic and be able to be traced back to the model's Inputs. These losses become part of the model's topology and are tracked in get_config.

Example:

inputs = tf.keras.Input(shape=(10,))
x = tf.keras.layers.Dense(10)(inputs)
outputs = tf.keras.layers.Dense(1)(x)
model = tf.keras.Model(inputs, outputs)
# Activity regularization.
model.add_loss(tf.abs(tf.reduce_mean(x)))

If this is not the case for your loss (if, for example, your loss references a Variable of one of the model's layers), you can wrap your loss in a zero-argument lambda. These losses are not tracked as part of the model's topology since they can't be serialized.

Example:

inputs = tf.keras.Input(shape=(10,))
d = tf.keras.layers.Dense(10)
x = d(inputs)
outputs = tf.keras.layers.Dense(1)(x)
model = tf.keras.Model(inputs, outputs)
# Weight regularization.
model.add_loss(lambda: tf.reduce_mean(d.kernel))

Args
losses	Loss tensor, or list/tuple of tensors. Rather than tensors, losses may also be zero-argument callables which create a loss tensor.
**kwargs	Used for backwards compatibility only.

build

build(
    input_shape
)

Creates the variables of the layer (for subclass implementers).

This is a method that implementers of subclasses of Layer or Model can override if they need a state-creation step in-between layer instantiation and layer call. It is invoked automatically before the first execution of call().

This is typically used to create the weights of Layer subclasses (at the discretion of the subclass implementer).

Args
input_shape	Instance of TensorShape, or list of instances of TensorShape if the layer expects a list of inputs (one instance per input).

build_from_config

build_from_config(
    config
)

Builds the layer's states with the supplied config dict.

By default, this method calls the build(config["input_shape"]) method, which creates weights based on the layer's input shape in the supplied config. If your config contains other information needed to load the layer's state, you should override this method.

Args
config	Dict containing the input shape associated with this layer.

compute_mask

compute_mask(
    inputs, mask=None
)

Computes an output mask tensor.

Args
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).

compute_output_shape

View source

compute_output_shape(
    input_shape
)

Computes the output shape of the layer.

This relies on the output_shape provided during initialization, if any, else falls back to the default behavior from keras.layers.Layer.

Args
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.

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).

from_config

@classmethod
from_config(
    config
)

Creates a layer from its config.

This method is the reverse of get_config, capable of instantiating the same layer from the config dictionary. It does not handle layer connectivity (handled by Network), nor weights (handled by set_weights).

Args
config	A Python dictionary, typically the output of get_config.

Returns
A layer instance.

get_build_config

get_build_config()

Returns a dictionary with the layer's input shape.

This method returns a config dict that can be used by build_from_config(config) to create all states (e.g. Variables and Lookup tables) needed by the layer.

By default, the config only contains the input shape that the layer was built with. If you're writing a custom layer that creates state in an unusual way, you should override this method to make sure this state is already created when TF-Keras attempts to load its value upon model loading.

Returns
A dict containing the input shape associated with the layer.

get_config

View source

get_config()

Returns a serializable dict of keras layer configuration parameters.

get_weights

get_weights()

Returns the current weights of the layer, as NumPy arrays.

The weights of a layer represent the state of the layer. This function returns both trainable and non-trainable weight values associated with this layer as a list of NumPy arrays, which can in turn be used to load state into similarly parameterized layers.

For example, a Dense layer returns a list of two values: the kernel matrix and the bias vector. These can be used to set the weights of another Dense layer:

layer_a = tf.keras.layers.Dense(1,
  kernel_initializer=tf.constant_initializer(1.))
a_out = layer_a(tf.convert_to_tensor([[1., 2., 3.]]))
layer_a.get_weights()
[array([[1.],
       [1.],
       [1.]], dtype=float32), array([0.], dtype=float32)]
layer_b = tf.keras.layers.Dense(1,
  kernel_initializer=tf.constant_initializer(2.))
b_out = layer_b(tf.convert_to_tensor([[10., 20., 30.]]))
layer_b.get_weights()
[array([[2.],
       [2.],
       [2.]], dtype=float32), array([0.], dtype=float32)]
layer_b.set_weights(layer_a.get_weights())
layer_b.get_weights()
[array([[1.],
       [1.],
       [1.]], dtype=float32), array([0.], dtype=float32)]

Returns
Weights values as a list of NumPy arrays.

load_own_variables

load_own_variables(
    store
)

Loads the state of the layer.

You can override this method to take full control of how the state of the layer is loaded upon calling keras.models.load_model().

Args
store	Dict from which the state of the model will be loaded.

save_own_variables

save_own_variables(
    store
)

Saves the state of the layer.

You can override this method to take full control of how the state of the layer is saved upon calling model.save().

Args
store	Dict where the state of the model will be saved.

set_weights

set_weights(
    weights
)

Sets the weights of the layer, from NumPy arrays.

The weights of a layer represent the state of the layer. This function sets the weight values from numpy arrays. The weight values should be passed in the order they are created by the layer. Note that the layer's weights must be instantiated before calling this function, by calling the layer.

For example, a Dense layer returns a list of two values: the kernel matrix and the bias vector. These can be used to set the weights of another Dense layer:

layer_a = tf.keras.layers.Dense(1,
  kernel_initializer=tf.constant_initializer(1.))
a_out = layer_a(tf.convert_to_tensor([[1., 2., 3.]]))
layer_a.get_weights()
[array([[1.],
       [1.],
       [1.]], dtype=float32), array([0.], dtype=float32)]
layer_b = tf.keras.layers.Dense(1,
  kernel_initializer=tf.constant_initializer(2.))
b_out = layer_b(tf.convert_to_tensor([[10., 20., 30.]]))
layer_b.get_weights()
[array([[2.],
       [2.],
       [2.]], dtype=float32), array([0.], dtype=float32)]
layer_b.set_weights(layer_a.get_weights())
layer_b.get_weights()
[array([[1.],
       [1.],
       [1.]], dtype=float32), array([0.], dtype=float32)]

Args
weights	a list of NumPy arrays. The number of arrays and their shape must match number of the dimensions of the weights of the layer (i.e. it should match the output of get_weights).

Raises
ValueError	If the provided weights list does not match the layer's specifications.

with_name_scope

@classmethod
with_name_scope(
    method
)

Decorator to automatically enter the module name scope.

class MyModule(tf.Module):
  @tf.Module.with_name_scope
  def __call__(self, x):
    if not hasattr(self, 'w'):
      self.w = tf.Variable(tf.random.normal([x.shape[1], 3]))
    return tf.matmul(x, self.w)

Using the above module would produce tf.Variables and tf.Tensors whose names included the module name:

mod = MyModule()
mod(tf.ones([1, 2]))
<tf.Tensor: shape=(1, 3), dtype=float32, numpy=..., dtype=float32)>
mod.w
<tf.Variable 'my_module/Variable:0' shape=(2, 3) dtype=float32,
numpy=..., dtype=float32)>

Args
method	The method to wrap.

Returns
The original method wrapped such that it enters the module's name scope.

__call__

__call__(
    *args, **kwargs
)

Wraps call, applying pre- and post-processing steps.

Args
*args	Positional arguments to be passed to self.call.
**kwargs	Keyword arguments to be passed to self.call.

Returns
Output tensor(s).

Note

The following optional keyword arguments are reserved for specific uses: training: Boolean scalar tensor of Python boolean indicating whether the call is meant for training or inference. mask: Boolean input mask. If the layer's call method takes a mask argument (as some Keras layers do), its default value will be set to the mask generated for inputs by the previous layer (if input did come from a layer that generated a corresponding mask, i.e. if it came from a TF-Keras layer with masking support. If the layer is not built, the method will call build.

Raises
ValueError	if the layer's call method returns None (an invalid value).
RuntimeError	if super().__init__() was not called in the constructor.