MCPcopy Create free account
hub / github.com/audioku/meta-transfer-learning / forward

Method forward

modules/encoder.py:53–80  ·  view source on GitHub ↗

args: padded_input: B x T x D input_lengths: B return: output: B x T x H

(self, padded_input, input_lengths)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 2

get_non_pad_maskFunction · 0.85
get_attn_pad_maskFunction · 0.85

Tested by

no test coverage detected