You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by jx...@apache.org on 2018/04/30 17:24:51 UTC
[incubator-mxnet] 02/03: Update rnn_layer.py
This is an automated email from the ASF dual-hosted git repository.
jxie pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git
commit 04e00c86c06024e4aea584e3af2248b6686521f1
Author: ThomasDelteil <th...@gmail.com>
AuthorDate: Fri Apr 20 08:37:46 2018 -0700
Update rnn_layer.py
---
python/mxnet/gluon/rnn/rnn_layer.py | 15 ++++++---------
1 file changed, 6 insertions(+), 9 deletions(-)
diff --git a/python/mxnet/gluon/rnn/rnn_layer.py b/python/mxnet/gluon/rnn/rnn_layer.py
index 53c9ec0..21b41d9 100644
--- a/python/mxnet/gluon/rnn/rnn_layer.py
+++ b/python/mxnet/gluon/rnn/rnn_layer.py
@@ -287,9 +287,8 @@ class RNN(_RNNLayer):
- **data**: input tensor with shape `(sequence_length, batch_size, input_size)`
when `layout` is "TNC". For other layouts dimensions are permuted accordingly.
Be aware that a `transpose` operation with a ndarray results in a new allocation of
- memory. For optimal performance and when applicable, consider transposing
- your layout to "TNC" before loading your data into
- a ndarray.
+ memory. For optimal performance and when applicable, consider transposing
+ your layout to "TNC" before loading your data into a ndarray.
- **states**: initial recurrent state tensor with shape
`(num_layers, batch_size, num_hidden)`. If `bidirectional` is True,
shape will instead be `(2*num_layers, batch_size, num_hidden)`. If
@@ -391,9 +390,8 @@ class LSTM(_RNNLayer):
- **data**: input tensor with shape `(sequence_length, batch_size, input_size)`
when `layout` is "TNC". For other layouts dimensions are permuted accordingly.
Be aware that a `transpose` operation with a ndarray results in a new allocation of
- memory. For optimal performance and when applicable, consider transposing
- your layout to "TNC" before loading your data into
- a ndarray.
+ memory. For optimal performance and when applicable, consider transposing
+ your layout to "TNC" before loading your data into a ndarray.
- **states**: a list of two initial recurrent state tensors. Each has shape
`(num_layers, batch_size, num_hidden)`. If `bidirectional` is True,
shape will instead be `(2*num_layers, batch_size, num_hidden)`. If
@@ -492,9 +490,8 @@ class GRU(_RNNLayer):
- **data**: input tensor with shape `(sequence_length, batch_size, input_size)`
when `layout` is "TNC". For other layouts dimensions are permuted accordingly.
Be aware that a `transpose` operation with a ndarray results in a new allocation of
- memory. For optimal performance and when applicable, consider transposing
- your layout to "TNC" before loading your data into
- a ndarray.
+ memory. For optimal performance and when applicable, consider transposing
+ your layout to "TNC" before loading your data into a ndarray.
- **states**: initial recurrent state tensor with shape
`(num_layers, batch_size, num_hidden)`. If `bidirectional` is True,
shape will instead be `(2*num_layers, batch_size, num_hidden)`. If
--
To stop receiving notification emails like this one, please contact
jxie@apache.org.