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

Slight rewording in Keras Layers RNN docs: backward compatible reason --> backward compatibility

Browse Source 
PiperOrigin-RevId: 358023469
Change-Id: Ic941c08bdee19946fe09c62777d35e614e3b8adc
This commit is contained in:
A. Unique TensorFlower 2021-02-17 13:43:53 -08:00 committed by TensorFlower Gardener
parent 5cdb9a43aa
commit 7716b719e5
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tensorflow/python/keras/layers/recurrent.py
View File

@ -236,7 +236,7 @@ class RNN(Layer):
`batch_size` is a scalar tensor that represents the batch size `batch_size` is a scalar tensor that represents the batch size
of the inputs. `dtype` is `tf.DType` that represents the dtype of of the inputs. `dtype` is `tf.DType` that represents the dtype of
the inputs. the inputs.
For backward compatible reason, if this method is not implemented For backward compatibility, if this method is not implemented
by the cell, the RNN layer will create a zero filled tensor with the by the cell, the RNN layer will create a zero filled tensor with the
size of [batch_size, cell.state_size]. size of [batch_size, cell.state_size].
In the case that `cell` is a list of RNN cell instances, the cells In the case that `cell` is a list of RNN cell instances, the cells