lanking520 commented on issue #12844: ERROR parameter summary of lstm layer URL: https://github.com/apache/incubator-mxnet/issues/12844#issuecomment-430819961 > Hi @soeque1, > > You can now use `model.summary()` to get the summary. > > ``` > import mxnet as mx > import numpy as np > > model = mx.gluon.nn.HybridSequential() > with model.name_scope(): > model.add(mx.gluon.nn.Embedding(30, 10)) > model.add(mx.gluon.rnn.LSTM(20)) > model.add(mx.gluon.nn.Dense(5, flatten=False)) > > model.initialize() > data = np.random.randint(low=0, high=30, size=(2,3)) > data = mx.nd.array(data) > model.summary(data) > ``` > @lanking520 what version of MXNet are you using? LSTMs weren't hybridizable before v1.3. I use mxnet 1.2 and I think that could be the reason. @soeque1 Are you still facing the issue now?
---------------------------------------------------------------- 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: [email protected] With regards, Apache Git Services
