MLCMultiheadAttentionLayer
A multihead, scaled dot-product attention layer that attends to one or more entries in the input key-value pairs.
Declaration
class MLCMultiheadAttentionLayerOverview
The dimensions of projections are as follows:
- Query
(1, headCount, keyDimension/headCount, modelDimension)- Key
(1, headCount, keyDimension/headCount, modelDimension)- Value
(1, headCount, valueDimension/headCount, modelDimension)- Output
(1, 1, modelDimension, valueDimension)
``