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 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 KerasTensors
tf.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.

API Definition and Usage

No response

Alternatives

No response

Risks

No response