MultiHeadAttention layer.

Inherits From: Layer, Module

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.

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