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

Reply via email to