View source on GitHub |
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
Methods
call
call(
x: tf.Tensor
) -> tf.Tensor
Performs the forward computation of the block.