Attend the Women in ML Symposium on December 7 Register now

tfr.keras.saved_model.Signatures

Stay organized with collections Save and categorize content based on your preferences.

Defines signatures to support regress and predict serving.

This wraps the trained Keras model in two serving functions that can be saved with tf.saved_model.save or model.save, and loaded with corresponding signature names. The regress serving signature takes a batch of serialized tf.Examples as input, whereas the predict serving signature takes a batch of serialized ExampleListWithContext as input.

Example usage:

A ranking model can be saved with signatures as follows:

tf.saved_model.save(model, path, signatures=Signatures(model, ...)())

For regress serving, scores can be generated using REGRESS signature as follows:

loaded_model = tf.saved_model.load(path)
predictor = loaded_model.signatures[tf.saved_model.REGRESS_METHOD_NAME]
scores = predictor(serialized_examples)[tf.saved_model.REGRESS_OUTPUTS]

For predict serving, scores can be generated using PREDICT signature as follows:

loaded_model = tf.saved_model.load(path)
predictor = loaded_model.signatures[tf.saved_model.PREDICT_METHOD_NAME]
scores = predictor(serialized_elwcs)[tf.saved_model.PREDICT_OUTPUTS]

model A Keras ranking model.
context_feature_spec (dict) A mapping from feature keys to FixedLenFeature or RaggedFeature values for context in tensorflow.serving.ExampleListWithContext proto.
example_feature_spec (dict) A mapping from feature keys to FixedLenFeature or Ragged values for examples in tensorflow.serving.ExampleListWithContext proto.
mask_feature_name (str) Name of feature for example list masks.

name Returns the name of this module as passed or determined in the ctor.

name_scope Returns a tf.name_scope instance for this class.
non_trainable_variables Sequence of non-trainable variables owned by this module and its submodules.
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

trainable_variables Sequence of trainable variables owned by this module and its submodules.

variables Sequence of variables owned by this module and its submodules.

Methods

normalize_outputs

View source

Returns a dict of Tensors for outputs.

Args
default_key If outputs is a Tensor, use the default_key to make a dict.
outputs outputs to be normalized.

Returns
A dict maps from str-like key(s) to Tensor(s).

Raises
TypeError if outputs is not a Tensor nor a dict.

predict_tf_function

View source

Makes a tensorflow function for predict.

regress_tf_function

View source

Makes a tensorflow function for regress.

with_name_scope

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__

View source

Returns a dict of signatures.

Args
serving_default Specifies "regress" or "predict" as the serving_default signature.

Returns
A dict of signatures.