tfm.nlp.layers.TalkingHeadsAttention

Implements Talking-Heads Attention.

tfm.nlp.layers.TalkingHeadsAttention(
    num_heads,
    key_dim,
    value_dim=None,
    dropout=0.0,
    use_bias=True,
    output_shape=None,
    attention_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 is an implementation of Talking-Heads Attention based on the paper Talking-Heads Attention (https://arxiv.org/abs/2003.02436): it enhanced multi-head attention by including linearprojections across the attention-heads dimension, immediately before and after the softmax operation.

See the base class tf.keras.layers.MultiHeadAttention for more details.

num_heads Number of attention heads.
key_dim Size of each attention head for query and key.
value_dim Size of each attention head for value.
dropout Dropout probability.
use_bias Boolean, whether the dense layers use bias vectors/matrices.
output_shape The expected shape of an output tensor, besides the batch and sequence dims. If not specified, projects back to the key feature dim.
attention_axes axes over which the attention is applied. None means attention over all axes, but batch, heads, and features.
return_attention_scores bool, if True, returns the multi-head attention scores as an additional output argument.
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.

Methods

call

call(
    query,
    value,
    key=None,
    attention_mask=None,
    return_attention_scores=False,
    training=None
)

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 in __init__(), or the build() method that is called automatically before call() executes 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.