You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by gi...@git.apache.org on 2017/07/31 18:33:32 UTC
[GitHub] szha commented on a change in pull request #7264: gluon conv rnns
szha commented on a change in pull request #7264: gluon conv rnns
URL: https://github.com/apache/incubator-mxnet/pull/7264#discussion_r130425435
##########
File path: tests/python/unittest/test_gluon_rnn.py
##########
@@ -192,6 +196,59 @@ def test_rnn_cells():
net.add(gluon.rnn.GRUCell(100, input_size=100))
check_rnn_forward(net, mx.nd.ones((8, 3, 200)))
+ net = gluon.rnn.SequentialRNNCell()
+ net.add(gluon.rnn.ConvLSTMCell(100, input_shape=(200, 5, 7)))
+ net.add(gluon.rnn.ConvRNNCell(100, input_shape=(100, 5, 7)))
+ net.add(gluon.rnn.ConvGRUCell(100, input_shape=(100, 5, 7)))
+ check_rnn_forward(net, mx.nd.ones((8, 3, 200, 5, 7)))
+
+
+def test_convrnn():
+ cell = gluon.rnn.ConvRNNCell(hidden_size=10, input_shape=(3, 16, 10),
+ h2h_kernel=(3, 3), h2h_dilate=(1, 1),
+ i2h_kernel=(3, 3), i2h_stride=(1, 1),
+ i2h_pad=(1, 1), i2h_dilate=(1, 1),
+ prefix='rnn_')
Review comment:
Good call. I was able to discover some issues when testing it.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services