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