MCPcopy Create free account
hub / github.com/benoitsteiner/tensorflow-opencl / static_bidirectional_rnn

Function static_bidirectional_rnn

tensorflow/python/ops/rnn.py:1364–1457  ·  view source on GitHub ↗

Creates a bidirectional recurrent neural network. Similar to the unidirectional case above (rnn) but takes input and builds independent forward and backward RNNs with the final forward and backward outputs depth-concatenated, such that the output will have the format [time][batch][cell_fw.o

(cell_fw,
                             cell_bw,
                             inputs,
                             initial_state_fw=None,
                             initial_state_bw=None,
                             dtype=None,
                             sequence_length=None,
                             scope=None)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 7

_like_rnncellFunction · 0.85
static_rnnFunction · 0.85
tupleFunction · 0.85
variable_scopeMethod · 0.80
flattenMethod · 0.80
concatMethod · 0.80
_reverse_seqFunction · 0.70

Tested by

no test coverage detected