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

Method forward

modules/decoder.py:71–115  ·  view source on GitHub ↗

args: padded_input: B x T encoder_padded_outputs: B x T x H encoder_input_lengths: B returns: pred: B x T x vocab gold: B x T

(self, padded_input, encoder_padded_outputs, encoder_input_lengths)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 5

preprocessMethod · 0.95
get_non_pad_maskFunction · 0.85
get_subsequent_maskFunction · 0.85
get_attn_key_pad_maskFunction · 0.85
get_attn_pad_maskFunction · 0.85

Tested by

no test coverage detected