|View source on GitHub|
A layer that uses tf.einsum as the backing computation.
Compat aliases for migration
See Migration guide for more details.
tf.keras.layers.experimental.EinsumDense( equation, output_shape, activation=None, bias_axes=None, kernel_initializer='glorot_uniform', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, bias_constraint=None, **kwargs )
This layer can perform einsum calculations of arbitrary dimensionality.
An equation describing the einsum to perform. This equation must
be a valid einsum string of the form
||The expected shape of the output tensor (excluding the batch dimension and any dimensions represented by ellipses). You can specify None for any dimension that is unknown or can be inferred from the input shape.|
Activation function to use. If you don't specify anything, no
activation is applied (that is, a "linear" activation:
A string containing the output dimension(s) to apply a bias to.
Each character in the |