MCPcopy Create free account
hub / github.com/tensorflow/lingvo / _TransformerLayerBlock

Method _TransformerLayerBlock

lingvo/core/self_attention_layer.py:343–351  ·  view source on GitHub ↗

(inputs, paddings) -> (encoded, paddings).

(
      self, name, feed_forward_qdomain=None, layer_idx=None
  )

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

TransformerStackMethod · 0.95

Calls 3

SelfAttentionMethod · 0.95
FeedforwardMethod · 0.95
_SeqMethod · 0.45

Tested by

no test coverage detected