Join TensorFlow at Google I/O, May 11-12 Register now

tfrs.layers.blocks.MLP

Sequential multi-layer perceptron (MLP) block.

tfrs.layers.blocks.MLP(
    units: List[int],
    use_bias: bool = True,
    activation: Optional[types.Activation] = 'relu',
    final_activation: Optional[types.Activation] = None,
    **kwargs
) -> None

units Sequential list of layer sizes.
use_bias Whether to include a bias term.
activation Type of activation to use on all except the last layer.
final_activation Type of activation to use on last layer.
**kwargs Extra args passed to the Keras Layer base class.

Methods

call

View source

call(
    x: tf.Tensor
) -> tf.Tensor

Performs the forward computation of the block.