tfm.nlp.layers.ReZeroTransformer

Transformer layer with ReZero.

tfm.nlp.layers.ReZeroTransformer(
    num_attention_heads,
    inner_dim=768,
    inner_activation=tfm.utils.activations.gelu,
    dropout_rate=0.0,
    attention_dropout_rate=0.0,
    output_range=None,
    kernel_initializer='glorot_uniform',
    bias_initializer='zeros',
    kernel_regularizer=None,
    bias_regularizer=None,
    activity_regularizer=None,
    kernel_constraint=None,
    bias_constraint=None,
    use_layer_norm=False,
    share_rezero=True,
    **kwargs
)

This layer implements the Transformer from "Attention Is All You Need". (https://arxiv.org/abs/1706.03762). The residual connection implements the ReZero method. (https://arxiv.org/abs/2003.04887)

num_attention_heads Number of attention heads.
inner_dim The output dimension of the first Dense layer in a two-layer feedforward network.
inner_activation The activation for the first Dense layer in a two-layer feedforward network.
dropout_rate Dropout probability for the post-attention and output dropout.
attention_dropout_rate Dropout probability for within the attention layer.
output_range the sequence output range, [0, output_range) by slicing the target sequence. None means the target sequence is not sliced.
kernel_initializer Initializer for dense layer kernels.
bias_initializer Initializer for dense layer biases.
kernel_regularizer Regularizer for dense layer kernels.
bias_regularizer Regularizer for dense layer biases.
activity_regularizer Regularizer for dense layer activity.
kernel_constraint Constraint for dense layer kernels.
bias_constraint Constraint for dense layer kernels.
use_layer_norm If add layer_norm on top of the ReZero.
share_rezero If attention layer and FFN layer share the same alpha.

Methods

call

View source

call(
    inputs, output_range: Optional[tf.Tensor] = None
) -> tf.Tensor

This is where the layer's logic lives.

The call() method may not create state (except in its first invocation, wrapping the creation of variables or other resources in tf.init_scope()). It is recommended to create state, including tf.Variable instances and nested Layer instances, in __init__(), or in the build() method that is called automatically before call() executes for the first time.

Args
inputs Input tensor, or dict/list/tuple of input tensors. The first positional inputs argument is subject to special rules:

  • inputs must be explicitly passed. A layer cannot have zero arguments, and inputs cannot be provided via the default value of a keyword argument.
  • NumPy array or Python scalar values in inputs get cast as tensors.
  • Keras mask metadata is only collected from inputs.
  • Layers are built (build(input_shape) method) using shape info from inputs only.
  • input_spec compatibility is only checked against inputs.
  • Mixed precision input casting is only applied to inputs. If a layer has tensor arguments in *args or **kwargs, their casting behavior in mixed precision should be handled manually.
  • The SavedModel input specification is generated using inputs only.
  • Integration with various ecosystem packages like TFMOT, TFLite, TF.js, etc is only supported for inputs and not for tensors in positional and keyword arguments.
*args Additional positional arguments. May contain tensors, although this is not recommended, for the reasons above.
**kwargs Additional keyword arguments. May contain tensors, although this is not recommended, for the reasons above. The following optional keyword arguments are reserved:
  • training: Boolean scalar tensor of Python boolean indicating whether the call is meant for training or inference.
  • mask: Boolean input mask. If the layer's call() method takes a mask argument, its default value will be set to the mask generated for inputs by the previous layer (if input did come from a layer that generated a corresponding mask, i.e. if it came from a Keras layer with masking support).

    • Returns
    A tensor or list/tuple of tensors.

    reset_rezero

    View source

    reset_rezero()