tfa.text.CRFModelWrapper

View source on GitHub

A model grouping layers into an object with training/inference features.

tfa.text.CRFModelWrapper(
    base_model: tf.keras.Model,
    units: int,
    chain_initializer: tfa.types.Initializer = 'orthogonal',
    use_boundary: bool = True,
    boundary_initializer: tfa.types.Initializer = 'zeros',
    use_kernel: bool = True,
    **kwargs
)

There are two ways to instantiate a Model:

1 - With the "Functional API", where you start from Input, you chain layer calls to specify the model's forward pass, and finally you create your model from inputs and outputs:

import tensorflow as tf

inputs = tf.keras.Input(shape=(3,))
x = tf.keras.layers.Dense(4, activation=tf.nn.relu)(inputs)
outputs = tf.keras.layers.Dense(5, activation=tf.nn.softmax)(x)
model = tf.keras.Model(inputs=inputs, outputs=outputs)

A new Functional API model can also be created by using the intermediate tensors. This enables you to quickly extract sub-components of the model.

Example:

inputs = keras.Input(shape=(None, None, 3))
processed = keras.layers.RandomCrop(width=32, height=32)(inputs)
conv = keras.layers.Conv2D(filters=2, kernel_size=3)(processed)
pooling = keras.layers.GlobalAveragePooling2D()(conv)
feature = keras.layers.Dense(10)(pooling)

full_model = keras.Model(inputs, feature)
backbone = keras.Model(processed, conv)
activations = keras.Model(conv, feature)

Note that the backbone and activations models are not created with keras.Input objects, but with the tensors that are originated from keras.Input objects. Under the hood, the layers and weights will be shared across these models, so that user can train the full_model, and use backbone or activations to do feature extraction. The inputs and outputs of the model can be nested structures of tensors as well, and the created models are standard Functional API models that support all the existing APIs.

2 - By subclassing the Model class: in that case, you should define your layers in __init__() and you should implement the model's forward pass in call().

import tensorflow as tf

class MyModel(tf.keras.Model):

  def __init__(self):
    super().__init__()
    self.dense1 = tf.keras.layers.Dense(4, activation=tf.nn.relu)
    self.dense2 = tf.keras.layers.Dense(5, activation=tf.nn.softmax)

  def call(self, inputs):
    x = self.dense1(inputs)
    return self.dense2(x)

model = MyModel()

If you subclass Model, you can optionally have a training argument (boolean) in call(), which you can use to specify a different behavior in training and inference:

import tensorflow as tf

class MyModel(tf.keras.Model):

  def __init__(self):
    super().__init__()
    self.dense1 = tf.keras.layers.Dense(4, activation=tf.nn.relu)
    self.dense2 = tf.keras.layers.Dense(5, activation=tf.nn.softmax)
    self.dropout = tf.keras.layers.Dropout(0.5)

  def call(self, inputs, training=False):
    x = self.dense1(inputs)
    if training:
      x = self.dropout(x, training=training)
    return self.dense2(x)

model = MyModel()

Once the model is created, you can config the model with losses and metrics with model.compile(), train the model with model.fit(), or use the model to do prediction with model.predict().

self.input_spec = tf.keras.layers.InputSpec(ndim=4)

ValueError: Input 0 of layer conv2d is incompatible with the layer:
expected ndim=4, found ndim=1. Full shape received: [2]

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>]

inputs = tf.keras.layers.Input(shape=(3,))
outputs = tf.keras.layers.Dense(2)(inputs)
model = tf.keras.models.Model(inputs=inputs, outputs=outputs)
model.compile(optimizer="Adam", loss="mse", metrics=["mae"])
[m.name for m in model.metrics]
[]

x = np.random.random((2, 3))
y = np.random.randint(0, 2, (2, 2))
model.fit(x, y)
[m.name for m in model.metrics]
['loss', 'mae']

inputs = tf.keras.layers.Input(shape=(3,))
d = tf.keras.layers.Dense(2, name='out')
output_1 = d(inputs)
output_2 = d(inputs)
model = tf.keras.models.Model(
   inputs=inputs, outputs=[output_1, output_2])
model.add_metric(
   tf.reduce_sum(output_2), name='mean', aggregation='mean')
model.compile(optimizer="Adam", loss="mse", metrics=["mae", "acc"])
model.fit(x, (y, y))
[m.name for m in model.metrics]
['loss', 'out_loss', 'out_1_loss', 'out_mae', 'out_acc', 'out_1_mae',
'out_1_acc', 'mean']

inputs = tf.keras.layers.Input(shape=(3,))
outputs = tf.keras.layers.Dense(2)(inputs)
model = tf.keras.models.Model(inputs=inputs, outputs=outputs)
model.compile(optimizer="Adam", loss="mse", metrics=["mae"])
model.metrics_names
[]

x = np.random.random((2, 3))
y = np.random.randint(0, 2, (2, 2))
model.fit(x, y)
model.metrics_names
['loss', 'mae']

inputs = tf.keras.layers.Input(shape=(3,))
d = tf.keras.layers.Dense(2, name='out')
output_1 = d(inputs)
output_2 = d(inputs)
model = tf.keras.models.Model(
   inputs=inputs, outputs=[output_1, output_2])
model.compile(optimizer="Adam", loss="mse", metrics=["mae", "acc"])
model.fit(x, (y, y))
model.metrics_names
['loss', 'out_loss', 'out_1_loss', 'out_mae', 'out_acc', 'out_1_mae',
'out_1_acc']

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

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))

add_metric

add_metric(
    value, name=None, **kwargs
)

Adds metric tensor to the layer.

This method can be used inside the call() method of a subclassed layer or model.

class MyMetricLayer(tf.keras.layers.Layer):
  def __init__(self):
    super(MyMetricLayer, self).__init__(name='my_metric_layer')
    self.mean = tf.keras.metrics.Mean(name='metric_1')

  def call(self, inputs):
    self.add_metric(self.mean(inputs))
    self.add_metric(tf.reduce_sum(inputs), name='metric_2')
    return inputs

This method can also be called directly on a Functional Model during construction. In this case, any tensor passed to this Model must be symbolic and be able to be traced back to the model's Inputs. These metrics become part of the model's topology and are tracked when you save the model via save().

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)
model.add_metric(math_ops.reduce_sum(x), name='metric_1')

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)
model.add_metric(tf.keras.metrics.Mean()(x), name='metric_1')

build

build(
    input_shape
)

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).

build_from_config

build_from_config(
    config
)

call

View source

call(
    inputs, training=None, mask=None, return_crf_internal=False
)

Calls the model on new inputs and returns the outputs as tensors.

In this case call() just reapplies all ops in the graph to the new inputs (e.g. build a new computational graph from the provided inputs).

compile

compile(
    optimizer='rmsprop',
    loss=None,
    metrics=None,
    loss_weights=None,
    weighted_metrics=None,
    run_eagerly=None,
    steps_per_execution=None,
    jit_compile=None,
    **kwargs
)

Configures the model for training.

Example:

model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=1e-3),
              loss=tf.keras.losses.BinaryCrossentropy(),
              metrics=[tf.keras.metrics.BinaryAccuracy(),
                       tf.keras.metrics.FalseNegatives()])

compile_from_config

compile_from_config(
    config
)

compute_crf_loss

View source

compute_crf_loss(
    potentials, sequence_length, kernel, y, sample_weight=None
)

compute_loss

compute_loss(
    x=None, y=None, y_pred=None, sample_weight=None
)

Compute the total loss, validate it, and return it.

Subclasses can optionally override this method to provide custom loss computation logic.

Example:

class MyModel(tf.keras.Model):

  def __init__(self, *args, **kwargs):
    super(MyModel, self).__init__(*args, **kwargs)
    self.loss_tracker = tf.keras.metrics.Mean(name='loss')

  def compute_loss(self, x, y, y_pred, sample_weight):
    loss = tf.reduce_mean(tf.math.squared_difference(y_pred, y))
    loss += tf.add_n(self.losses)
    self.loss_tracker.update_state(loss)
    return loss

  def reset_metrics(self):
    self.loss_tracker.reset_states()

  @property
  def metrics(self):
    return [self.loss_tracker]

tensors = tf.random.uniform((10, 10)), tf.random.uniform((10,))
dataset = tf.data.Dataset.from_tensor_slices(tensors).repeat().batch(1)

inputs = tf.keras.layers.Input(shape=(10,), name='my_input')
outputs = tf.keras.layers.Dense(10)(inputs)
model = MyModel(inputs, outputs)
model.add_loss(tf.reduce_sum(outputs))

optimizer = tf.keras.optimizers.SGD()
model.compile(optimizer, loss='mse', steps_per_execution=10)
model.fit(dataset, epochs=2, steps_per_epoch=10)
print('My custom loss: ', model.loss_tracker.result().numpy())

compute_mask

compute_mask(
    inputs, mask=None
)

Computes an output mask tensor.

compute_metrics

compute_metrics(
    x, y, y_pred, sample_weight
)

Update metric states and collect all metrics to be returned.

Subclasses can optionally override this method to provide custom metric updating and collection logic.

Example:

class MyModel(tf.keras.Sequential):

  def compute_metrics(self, x, y, y_pred, sample_weight):

    # This super call updates `self.compiled_metrics` and returns
    # results for all metrics listed in `self.metrics`.
    metric_results = super(MyModel, self).compute_metrics(
        x, y, y_pred, sample_weight)

    # Note that `self.custom_metric` is not listed in `self.metrics`.
    self.custom_metric.update_state(x, y, y_pred, sample_weight)
    metric_results['custom_metric_name'] = self.custom_metric.result()
    return metric_results

compute_output_shape

compute_output_shape(
    input_shape
)

Computes the output shape of the layer.

This method will cause the layer's state to be built, if that has not happened before. This requires that the layer will later be used with inputs that match the input shape provided here.

count_params

count_params()

Count the total number of scalars composing the weights.

evaluate

evaluate(
    x=None,
    y=None,
    batch_size=None,
    verbose='auto',
    sample_weight=None,
    steps=None,
    callbacks=None,
    max_queue_size=10,
    workers=1,
    use_multiprocessing=False,
    return_dict=False,
    **kwargs
)

Returns the loss value & metrics values for the model in test mode.

Computation is done in batches (see the batch_size arg.)

See the discussion of Unpacking behavior for iterator-like inputs for Model.fit.

export

export(
    filepath
)

Create a SavedModel artifact for inference (e.g. via TF-Serving).

This method lets you export a model to a lightweight SavedModel artifact that contains the model's forward pass only (its call() method) and can be served via e.g. TF-Serving. The forward pass is registered under the name serve() (see example below).

The original code of the model (including any custom layers you may have used) is no longer necessary to reload the artifact -- it is entirely standalone.

Example:

# Create the artifact
model.export("path/to/location")

# Later, in a different process / environment...
reloaded_artifact = tf.saved_model.load("path/to/location")
predictions = reloaded_artifact.serve(input_data)

If you would like to customize your serving endpoints, you can use the lower-level keras.export.ExportArchive class. The export() method relies on ExportArchive internally.

fit

fit(
    x=None,
    y=None,
    batch_size=None,
    epochs=1,
    verbose='auto',
    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,
    validation_batch_size=None,
    validation_freq=1,
    max_queue_size=10,
    workers=1,
    use_multiprocessing=False
)

Trains the model for a fixed number of epochs (dataset iterations).

Unpacking behavior for iterator-like inputs: A common pattern is to pass a tf.data.Dataset, generator, or tf.keras.utils.Sequence to the x argument of fit, which will in fact yield not only features (x) but optionally targets (y) and sample weights. Keras requires that the output of such iterator-likes be unambiguous. The iterator should return a tuple of length 1, 2, or 3, where the optional second and third elements will be used for y and sample_weight respectively. Any other type provided will be wrapped in a length one tuple, effectively treating everything as 'x'. When yielding dicts, they should still adhere to the top-level tuple structure. e.g. ({"x0": x0, "x1": x1}, y). Keras will not attempt to separate features, targets, and weights from the keys of a single dict. A notable unsupported data type is the namedtuple. The reason is that it behaves like both an ordered datatype (tuple) and a mapping datatype (dict). So given a namedtuple of the form: namedtuple("example_tuple", ["y", "x"]) it is ambiguous whether to reverse the order of the elements when interpreting the value. Even worse is a tuple of the form: namedtuple("other_tuple", ["x", "y", "z"]) where it is unclear if the tuple was intended to be unpacked into x, y, and sample_weight or passed through as a single element to x. As a result the data processing code will simply raise a ValueError if it encounters a namedtuple. (Along with instructions to remedy the issue.)

from_config

View source

@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).

get_build_config

get_build_config()

get_compile_config

get_compile_config()

get_config

View source

get_config()

Returns the config of the Model.

Config is a Python dictionary (serializable) containing the configuration of an object, which in this case is a Model. This allows the Model to be be reinstantiated later (without its trained weights) from this configuration.

Note that get_config() does not guarantee to return a fresh copy of dict every time it is called. The callers should make a copy of the returned dict if they want to modify it.

Developers of subclassed Model are advised to override this method, and continue to update the dict from super(MyModel, self).get_config() to provide the proper configuration of this Model. The default config will return config dict for init parameters if they are basic types. Raises NotImplementedError when in cases where a custom get_config() implementation is required for the subclassed model.

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).

get_metrics_result

get_metrics_result()

Returns the model's metrics values as a dict.

If any of the metric result is a dict (containing multiple metrics), each of them gets added to the top level returned dict of this method.

get_weight_paths

get_weight_paths()

Retrieve all the variables and their paths for the model.

The variable path (string) is a stable key to identify a tf.Variable instance owned by the model. It can be used to specify variable-specific configurations (e.g. DTensor, quantization) from a global view.

This method returns a dict with weight object paths as keys and the corresponding tf.Variable instances as values.

Note that if the model is a subclassed model and the weights haven't been initialized, an empty dict will be returned.

Example:

class SubclassModel(tf.keras.Model):

  def __init__(self, name=None):
    super().__init__(name=name)
    self.d1 = tf.keras.layers.Dense(10)
    self.d2 = tf.keras.layers.Dense(20)

  def call(self, inputs):
    x = self.d1(inputs)
    return self.d2(x)

model = SubclassModel()
model(tf.zeros((10, 10)))
weight_paths = model.get_weight_paths()
# weight_paths:
# {
#    'd1.kernel': model.d1.kernel,
#    'd1.bias': model.d1.bias,
#    'd2.kernel': model.d2.kernel,
#    'd2.bias': model.d2.bias,
# }

# Functional model
inputs = tf.keras.Input((10,), batch_size=10)
x = tf.keras.layers.Dense(20, name='d1')(inputs)
output = tf.keras.layers.Dense(30, name='d2')(x)
model = tf.keras.Model(inputs, output)
d1 = model.layers[1]
d2 = model.layers[2]
weight_paths = model.get_weight_paths()
# weight_paths:
# {
#    'd1.kernel': d1.kernel,
#    'd1.bias': d1.bias,
#    'd2.kernel': d2.kernel,
#    'd2.bias': d2.bias,
# }

get_weights

get_weights()

Retrieves the weights of the model.

load_weights

load_weights(
    filepath, skip_mismatch=False, by_name=False, options=None
)

Loads all layer weights from a saved files.

The saved file could be a SavedModel file, a .keras file (v3 saving format), or a file created via model.save_weights().

By default, 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.

Partial weight loading

If you have modified your model, for instance by adding a new layer (with weights) or by changing the shape of the weights of a layer, you can choose to ignore errors and continue loading by setting skip_mismatch=True. In this case any layer with mismatching weights will be skipped. A warning will be displayed for each skipped layer.

Weight loading by name

If your weights are saved as a .h5 file created via model.save_weights(), you can use the argument by_name=True.

In this case, 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.

Note that only topological loading (by_name=False) is supported when loading weights from the .keras v3 format or from the TensorFlow SavedModel format.

make_predict_function

make_predict_function(
    force=False
)

Creates a function that executes one step of inference.

This method can be overridden to support custom inference logic. This method is called by Model.predict and Model.predict_on_batch.

Typically, this method directly controls tf.function and tf.distribute.Strategy settings, and delegates the actual evaluation logic to Model.predict_step.

This function is cached the first time Model.predict or Model.predict_on_batch is called. The cache is cleared whenever Model.compile is called. You can skip the cache and generate again the function with force=True.

make_test_function

make_test_function(
    force=False
)

Creates a function that executes one step of evaluation.

This method can be overridden to support custom evaluation logic. This method is called by Model.evaluate and Model.test_on_batch.

Typically, this method directly controls tf.function and tf.distribute.Strategy settings, and delegates the actual evaluation logic to Model.test_step.

This function is cached the first time Model.evaluate or Model.test_on_batch is called. The cache is cleared whenever Model.compile is called. You can skip the cache and generate again the function with force=True.

make_train_function

make_train_function(
    force=False
)

Creates a function that executes one step of training.

This method can be overridden to support custom training logic. This method is called by Model.fit and Model.train_on_batch.

Typically, this method directly controls tf.function and tf.distribute.Strategy settings, and delegates the actual training logic to Model.train_step.

This function is cached the first time Model.fit or Model.train_on_batch is called. The cache is cleared whenever Model.compile is called. You can skip the cache and generate again the function with force=True.

predict

predict(
    x,
    batch_size=None,
    verbose='auto',
    steps=None,
    callbacks=None,
    max_queue_size=10,
    workers=1,
    use_multiprocessing=False
)

Generates output predictions for the input samples.

Computation is done in batches. This method is designed for batch processing of large numbers of inputs. It is not intended for use inside of loops that iterate over your data and process small numbers of inputs at a time.

For small numbers of inputs that fit in one batch, directly use __call__() for faster execution, e.g., model(x), or model(x, training=False) if you have layers such as tf.keras.layers.BatchNormalization that behave differently during inference. You may pair the individual model call with a tf.function for additional performance inside your inner loop. If you need access to numpy array values instead of tensors after your model call, you can use tensor.numpy() to get the numpy array value of an eager tensor.

Also, note the fact that test loss is not affected by regularization layers like noise and dropout.

See the discussion of Unpacking behavior for iterator-like inputs for Model.fit. Note that Model.predict uses the same interpretation rules as Model.fit and Model.evaluate, so inputs must be unambiguous for all three methods.

predict_on_batch

predict_on_batch(
    x
)

Returns predictions for a single batch of samples.

predict_step

predict_step(
    data
)

The logic for one inference step.

This method can be overridden to support custom inference logic. This method is called by Model.make_predict_function.

This method should contain the mathematical logic for one step of inference. This typically includes the forward pass.

Configuration details for how this logic is run (e.g. tf.function and tf.distribute.Strategy settings), should be left to Model.make_predict_function, which can also be overridden.

reset_metrics

reset_metrics()

Resets the state of all the metrics in the model.

Examples:

inputs = tf.keras.layers.Input(shape=(3,))
outputs = tf.keras.layers.Dense(2)(inputs)
model = tf.keras.models.Model(inputs=inputs, outputs=outputs)
model.compile(optimizer="Adam", loss="mse", metrics=["mae"])

x = np.random.random((2, 3))
y = np.random.randint(0, 2, (2, 2))
_ = model.fit(x, y, verbose=0)
assert all(float(m.result()) for m in model.metrics)

model.reset_metrics()
assert all(float(m.result()) == 0 for m in model.metrics)

reset_states

reset_states()

save

save(
    filepath, overwrite=True, save_format=None, **kwargs
)

Saves a model as a TensorFlow SavedModel or HDF5 file.

See the Serialization and Saving guide for details.

SavedModel format arguments: include_optimizer: Only applied to SavedModel and legacy HDF5 formats. If False, do not save the optimizer state. Defaults to True. signatures: Only applies to SavedModel format. Signatures to save with the SavedModel. See the signatures argument in tf.saved_model.save for details. options: Only applies to SavedModel format. tf.saved_model.SaveOptions object that specifies SavedModel saving options. save_traces: Only applies to SavedModel format. When enabled, the SavedModel will store the function traces for each layer. This can be disabled, so that only the configs of each layer are stored. Defaults to True. Disabling this will decrease serialization time and reduce file size, but it requires that all custom layers/models implement a get_config() method.

Example:

model = tf.keras.Sequential([
    tf.keras.layers.Dense(5, input_shape=(3,)),
    tf.keras.layers.Softmax()])
model.save("model.keras")
loaded_model = tf.keras.models.load_model("model.keras")
x = tf.random.uniform((10, 3))
assert np.allclose(model.predict(x), loaded_model.predict(x))

Note that model.save() is an alias for tf.keras.models.save_model().

save_spec

save_spec(
    dynamic_batch=True
)

Returns the tf.TensorSpec of call args as a tuple (args, kwargs).

This value is automatically defined after calling the model for the first time. Afterwards, you can use it when exporting the model for serving:

model = tf.keras.Model(...)

@tf.function
def serve(*args, **kwargs):
  outputs = model(*args, **kwargs)
  # Apply postprocessing steps, or add additional outputs.
  ...
  return outputs

# arg_specs is `[tf.TensorSpec(...), ...]`. kwarg_specs, in this
# example, is an empty dict since functional models do not use keyword
# arguments.
arg_specs, kwarg_specs = model.save_spec()

model.save(path, signatures={
  'serving_default': serve.get_concrete_function(*arg_specs,
                                                 **kwarg_specs)
})

save_weights

save_weights(
    filepath, overwrite=True, save_format=None, options=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.

While the formats are the same, do not mix save_weights and tf.train.Checkpoint. Checkpoints saved by Model.save_weights should be loaded using Model.load_weights. Checkpoints saved using tf.train.Checkpoint.save should be restored using the corresponding tf.train.Checkpoint.restore. Prefer tf.train.Checkpoint over save_weights for training checkpoints.

The TensorFlow format matches objects and variables by starting at a root object, self for save_weights, and greedily matching attribute names. For Model.save this is the Model, and for Checkpoint.save this is the Checkpoint even if the Checkpoint has a model attached. This means saving a tf.keras.Model using save_weights and loading into a tf.train.Checkpoint with a Model attached (or vice versa) will not match the Model's variables. See the guide to training checkpoints for details on the TensorFlow format.

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)]

summary

summary(
    line_length=None,
    positions=None,
    print_fn=None,
    expand_nested=False,
    show_trainable=False,
    layer_range=None
)

Prints a string summary of the network.

test_on_batch

test_on_batch(
    x, y=None, sample_weight=None, reset_metrics=True, return_dict=False
)

Test the model on a single batch of samples.

test_step

View source

test_step(
    data
)

The logic for one evaluation step.

This method can be overridden to support custom evaluation logic. This method is called by Model.make_test_function.

This function should contain the mathematical logic for one step of evaluation. This typically includes the forward pass, loss calculation, and metrics updates.

Configuration details for how this logic is run (e.g. tf.function and tf.distribute.Strategy settings), should be left to Model.make_test_function, which can also be overridden.

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={}).

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.

train_on_batch

train_on_batch(
    x,
    y=None,
    sample_weight=None,
    class_weight=None,
    reset_metrics=True,
    return_dict=False
)

Runs a single gradient update on a single batch of data.

train_step

View source

train_step(
    data
)

The logic for one training step.

This method can be overridden to support custom training logic. For concrete examples of how to override this method see Customizing what happens in fit. This method is called by Model.make_train_function.

This method should contain the mathematical logic for one step of training. This typically includes the forward pass, loss calculation, backpropagation, and metric updates.

Configuration details for how this logic is run (e.g. tf.function and tf.distribute.Strategy settings), should be left to Model.make_train_function, which can also be overridden.

unpack_training_data

View source

unpack_training_data(
    data
)

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)>

__call__

__call__(
    *args, **kwargs
)