A representation of a Keras in/output during Functional API construction.
KerasTensors are tensor-like objects that represent the symbolic inputs
and outputs of Keras layers during Functional model construction. They are
comprised of the tf.TypeSpec of the (Composite)Tensor that will be
consumed/produced in the corresponding location of the Functional model.
KerasTensors are intended as a private API, so users should never need to
directly instantiate KerasTensors.
Building Functional Models with KerasTensorstf.keras.Input produces KerasTensors that represent the symbolic inputs
to your model.
Passing a KerasTensor to a tf.keras.Layer__call__ lets the layer know
that you are building a Functional model. The layer call will
infer the output signature and return KerasTensors with tf.TypeSpecs
corresponding to the symbolic outputs of that layer call. These output
KerasTensors will have all of the internal KerasHistory metadata attached
to them that Keras needs to construct a Functional Model.
Background and Feature Description
A representation of a Keras in/output during Functional API construction.
KerasTensors are tensor-like objects that represent the symbolic inputs and outputs of Keras layers during Functional model construction. They are comprised of thetf.TypeSpecof the (Composite)Tensor that will be consumed/produced in the corresponding location of the Functional model.KerasTensors are intended as a private API, so users should never need to directly instantiate
KerasTensors.Building Functional Models with KerasTensors
tf.keras.InputproducesKerasTensors that represent the symbolic inputs to your model.Passing a
KerasTensorto atf.keras.Layer__call__lets the layer know that you are building a Functional model. The layer call will infer the output signature and returnKerasTensors withtf.TypeSpecs corresponding to the symbolic outputs of that layer call. These outputKerasTensors will have all of the internal KerasHistory metadata attached to them that Keras needs to construct a Functional Model.API Definition and Usage
No response
Alternatives
No response
Risks
No response