Jerryzcn commented on issue #9977: Cpu lstm inference
URL: https://github.com/apache/incubator-mxnet/pull/9977#issuecomment-371954306
@szha I think
https://github.com/apache/incubator-mxnet/blob/master/tests/python/gpu/test_operator_gpu.py#L1527
check for consistency? Although the inputs
Jerryzcn commented on issue #9977: Cpu lstm inference
URL: https://github.com/apache/incubator-mxnet/pull/9977#issuecomment-371608311
```
x = nd.ones(shape=(800,1,40))
model = mx.gluon.nn.Sequential()
with model.name_scope():
model.add(mx.gluon.rnn.LSTM(320, num_layers=4,
Jerryzcn commented on issue #9977: Cpu lstm inference
URL: https://github.com/apache/incubator-mxnet/pull/9977#issuecomment-371608311
x = nd.ones(shape=(800,1,40))
model = mx.gluon.nn.Sequential()
with model.name_scope():
model.add(mx.gluon.rnn.LSTM(320, num_layers=4,
Jerryzcn commented on issue #9977: Cpu lstm inference
URL: https://github.com/apache/incubator-mxnet/pull/9977#issuecomment-371608311
`x = nd.ones(shape=(800,1,40))
model = mx.gluon.nn.Sequential()
with model.name_scope():
model.add(mx.gluon.rnn.LSTM(320, num_layers=4,
Jerryzcn commented on issue #9977: Cpu lstm inference
URL: https://github.com/apache/incubator-mxnet/pull/9977#issuecomment-371594599
Network: 4 layer biLSTM with 320 hidden unit, with input shape of 800,1,40.
Machine: C4.2xlarge OMP_NUM_THREADS=4 Ubuntu
uname -a
Linux ip-xxx
Jerryzcn commented on issue #9977: Cpu lstm inference
URL: https://github.com/apache/incubator-mxnet/pull/9977#issuecomment-370121842
@pengzhao-intel This is great, we can definitely collaborate. The reason I
am sending this PR is for one of our own project. and we would like to have
