Learn R Programming

keras (version 2.7.0)

layer_multi_head_attention: MultiHeadAttention layer

Description

This is an implementation of multi-headed attention based on "Attention is all you Need". If query, key, value are the same, then this is self-attention. Each timestep in query attends to the corresponding sequence in key, and returns a fixed-width vector.

Usage

layer_multi_head_attention(
  inputs,
  num_heads,
  key_dim,
  value_dim = NULL,
  dropout = 0,
  use_bias = TRUE,
  output_shape = NULL,
  attention_axes = NULL,
  kernel_initializer = "glorot_uniform",
  bias_initializer = "zeros",
  kernel_regularizer = NULL,
  bias_regularizer = NULL,
  activity_regularizer = NULL,
  kernel_constraint = NULL,
  bias_constraint = NULL,
  ...
)

Value

  • attention_output: The result of the computation, of shape [B, T, E], where T is for target sequence shapes and E is the query input last dimension if output_shape is None. Otherwise, the multi-head outputs are project to the shape specified by output_shape.

  • attention_scores: (Optional) multi-head attention coeffients over attention axes.

Call arguments

  • query: Query Tensor of shape [B, T, dim].

  • value: Value Tensor of shape [B, S, dim].

  • key: Optional key Tensor of shape [B, S, dim]. If not given, will use value for both key and value, which is the most common case.

  • attention_mask: a boolean mask of shape [B, T, S], that prevents attention to certain positions.

  • return_attention_scores: A boolean to indicate whether the output should be attention output if TRUE, or (attention_output, attention_scores) if FALSE. Defaults to FALSE.

  • training: Python boolean indicating whether the layer should behave in training mode (adding dropout) or in inference mode (no dropout). Defaults to either using the training mode of the parent layer/model, or FALSE (inference) if there is no parent layer.

Details

This layer first projects query, key and value. These are (effectively) a list of tensors of length num_attention_heads, where the corresponding shapes are [batch_size, , key_dim], [batch_size, , key_dim], [batch_size, , value_dim].

Then, the query and key tensors are dot-producted and scaled. These are softmaxed to obtain attention probabilities. The value tensors are then interpolated by these probabilities, then concatenated back to a single tensor.

Finally, the result tensor with the last dimension as value_dim can take an linear projection and return.