ThomasDelteil commented on issue #12844: ERROR parameter summary of lstm layer URL: https://github.com/apache/incubator-mxnet/issues/12844#issuecomment-430791065 You can use the `.summary()` method of your gluon block: ```python import mxnet as mx 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() model.summary(mx.nd.ones((2, 3))) ``` ``` -------------------------------------------------------------------------------- Layer (type) Output Shape Param # ================================================================================ Input (2, 3) 0 Embedding-1 (2, 3, 10) 300 LSTM-2 (2, 3, 20) 2560 Dense-3 (2, 3, 5) 105 ================================================================================ Parameters in forward computation graph, duplicate included Total params: 2965 Trainable params: 2965 Non-trainable params: 0 Shared params in forward computation graph: 0 Unique parameters in model: 2965 -------------------------------------------------------------------------------- ```
---------------------------------------------------------------- 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
