diff options
| author |  Dandelion Mané <dandelion@google.com> | 2017-03-10 14:43:23 -0800 |
|---|---|---|
| committer |  TensorFlower Gardener <gardener@tensorflow.org> | 2017-03-10 15:18:15 -0800 |
| commit | 0386a01ad3beb28364599d82199be1c0837b3fa9 (patch) | |
| tree | 3a1d2ef947a7bf37286efc0e8ff760e0401ab319 /tensorflow/python/ops/rnn.py | |
| parent | e73ceaebb209a1e577e7240fba41c692c89143d0 (diff) | |
Merge changes from github.
Change: 149800363
Diffstat (limited to 'tensorflow/python/ops/rnn.py')
| -rw-r--r-- | tensorflow/python/ops/rnn.py | 2 |
1 files changed, 0 insertions, 2 deletions
diff --git a/tensorflow/python/ops/rnn.py b/tensorflow/python/ops/rnn.py index 6129c4ed93..a83fb9fb48 100644 --- a/tensorflow/python/ops/rnn.py +++ b/tensorflow/python/ops/rnn.py @@ -305,8 +305,6 @@ def bidirectional_dynamic_rnn(cell_fw, cell_bw, inputs, sequence_length=None, transposes at the beginning and end of the RNN calculation. However, most TensorFlow data is batch-major, so by default this function accepts input and emits output in batch-major form. - dtype: (optional) The data type for the initial state. Required if - either of the initial states are not provided. scope: VariableScope for the created subgraph; defaults to "bidirectional_rnn" |