thomelane commented on issue #12844: ERROR parameter summary of lstm layer
URL: 
https://github.com/apache/incubator-mxnet/issues/12844#issuecomment-431418733
 
 
   You can use `.summary()` for this example too @soeque1 .
   
   ```python
   import mxnet as mx
   from mxnet import gluon
   from mxnet.gluon import HybridBlock, nn, rnn
   
   
   class MyModel(gluon.HybridBlock):
       def __init__(self, vocab_size, num_embed, **kwargs):
           super(MyModel, self).__init__(**kwargs)
           with self.name_scope():
               self.embed = nn.Embedding(input_dim=vocab_size, 
output_dim=num_embed)
               self.lstm = rnn.LSTM(20)
               self.out = nn.Dense(2)
               
       def hybrid_forward(self, F ,inputs):
           em_out = self.embed(inputs)
           lstm_out = self.lstm(em_out) 
           return(self.out(lstm_out))
   
       
   model = MyModel(vocab_size=20, num_embed=50)
   model.initialize(mx.init.Xavier())
   data = mx.nd.array(np.random.randint(low=0, high=20, size=(2,3)))
   model.summary(data)
   ```
   
   ```
   
--------------------------------------------------------------------------------
           Layer (type)                                Output Shape         
Param #
   
================================================================================
                  Input                                      (2, 3)             
  0
            Embedding-1                                  (2, 3, 50)            
1000
                 LSTM-2                                  (2, 3, 20)            
5760
                Dense-3                                      (2, 2)             
122
              MyModel-4                                      (2, 2)             
  0
   
================================================================================
   Parameters in forward computation graph, duplicate included
      Total params: 6882
      Trainable params: 6882
      Non-trainable params: 0
   Shared params in forward computation graph: 0
   Unique parameters in model: 6882
   
--------------------------------------------------------------------------------
   ```

----------------------------------------------------------------
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