Class SymbolicTensor

tf.SymbolicTensor is a placeholder for a Tensor without any concrete value.

They are most often encountered when building a graph of Layers for a tf.LayersModel and the input data's shape, but not values are known.

Doc

Constructors

constructor

Properties

nodeIndex rank tensorIndex

Constructors

constructor

  • new SymbolicTensor(dtype, shape, sourceLayer, inputs, callArgs, name?, outputTensorIndex?): SymbolicTensor

  • Parameters

    • dtype: keyof DataTypeMap
    • shape: Shape
    • sourceLayer: Layer

      The Layer that produced this symbolic tensor.

    • inputs: SymbolicTensor[]

      The inputs passed to sourceLayer's call() method.

    • callArgs: Kwargs

      The keyword arguments passed to the call() method.

    • Optional name: string
    • Optional outputTensorIndex: number

      The index of this tensor in the list of outputs returned by apply().

    Returns SymbolicTensor

Properties

nodeIndex

nodeIndex: number

Replacement for _keras_history.

Readonly rank

rank: number

Rank/dimensionality of the tensor.

tensorIndex

tensorIndex: number

Replacement for _keras_history.

Settings

Member Visibility

Theme

On This Page

Generated using TypeDoc