experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Update the docstring for Bidirectional wrapper wrt to the layer used.

Browse Source 
For any custom layer to work with Bidirectional wrapper, the layer need to support "go_backwards" as its init parameter and property.

PiperOrigin-RevId: 293904336
Change-Id: Id65eff898e3acc6d33897f4671c042167f178958
This commit is contained in:
Scott Zhu 2020-02-07 15:10:23 -08:00 committed by TensorFlower Gardener
parent bb27042bae
commit 8ff354d254
1 changed files with 21 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
tensorflow/python/keras/layers/wrappers.py
View File

@ -353,21 +353,30 @@ class Bidirectional(Wrapper):
"""Bidirectional wrapper for RNNs.
Arguments:
layer: `Recurrent` instance.
merge_mode: Mode by which outputs of the
forward and backward RNNs will be combined.
One of {'sum', 'mul', 'concat', 'ave', None}.
If None, the outputs will not be combined,
they will be returned as a list.
backward_layer: Optional `Recurrent` instance to be used to handle
backwards input processing. If `backward_layer` is not provided,
the layer instance passed as the `layer` argument will be used to
generate the backward layer automatically.
layer: `keras.layers.RNN` instance, such as `keras.layers.LSTM` or
`keras.layers.GRU`. It could also be a `keras.layers.Layer` instance
that meets the following criteria:
1. Be a sequence-processing layer (accepts 3D+ inputs).
2. Have a `go_backwards`, `return_sequences` and `return_state`
attribute (with the same semantics as for the `RNN` class).
3. Have an `input_spec` attribute.
4. Implement serialization via `get_config()` and `from_config()`.
Note that the recommended way to create new RNN layers is to write a
custom RNN cell and use it with `keras.layers.RNN`, instead of
subclassing `keras.layers.Layer` directly.
merge_mode: Mode by which outputs of the forward and backward RNNs will be
combined. One of {'sum', 'mul', 'concat', 'ave', None}. If None, the
outputs will not be combined, they will be returned as a list. Default
value is 'concat'.
backward_layer: Optional `keras.layers.RNN`, or keras.layers.Layer` instance
to be used to handle backwards input processing. If `backward_layer` is
not provided, the layer instance passed as the `layer` argument will be
used to generate the backward layer automatically.
Note that the provided `backward_layer` layer should have properties
matching those of the `layer` argument, in particular it should have the
same values for `stateful`, `return_states`, `return_sequence`, etc.
In addition, `backward_layer` and `layer` should have
different `go_backwards` argument values.
In addition, `backward_layer` and `layer` should have different
`go_backwards` argument values.
A `ValueError` will be raised if these requirements are not met.
Call arguments: