merlin.models.tf.DenseResidualBlock

merlin.models.tf.DenseResidualBlock(low_rank_dim: Optional[int] = None, activation='relu', use_bias: bool = True, dropout: Optional[float] = None, normalization: Optional[Union[str, keras.engine.base_layer.Layer]] = 'batch_norm', depth: int = 1) → merlin.models.tf.blocks.core.base.Block[source]

A block that applies a dense residual block to the input.

Parameters

  • low_rank_dim (int) – The dimension of the low rank matrix.

  • activation (str) – The activation function to use.

  • use_bias (bool) – Whether to use a bias in the MLP.

  • dropout (float) – The dropout rate to use.

  • normalization (str or Layer) – The normalization layer to use.

  • depth (int) – The number of residual blocks to apply.