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

Method TransformerEncoderStack

lingvo/core/batch_major_attention.py:9491–9500  ·  view source on GitHub ↗

Returns a stack of num_layers self-attention layers.

(self, name, num_layers=1)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

_testGraphMethod · 0.80

Calls 2

StackMethod · 0.95

Tested by 1

_testGraphMethod · 0.64