PistonY opened a new issue #14762: How to make nn.HybridSequential handel 
multiple input/output layer?(Gluon)
URL: https://github.com/apache/incubator-mxnet/issues/14762
 
 
   For example I have a custom layer defind as
   ```python
   class my_layer(nn.HybridBlock):
       def __init__(self, **kwargs):
           super(my_layer, self).__init__(**kwargs)
           self.conv1 = nn.Conv2D(32, 1, 1)
           self.conv2 = nn.Conv2D(32, 1, 1)
       
       def hybrid_forward(self, F, x1, x2):
           y1 = self.conv1(x1)
           y2 = self.conv2(x2)
           return y1, y2
   ```
   And if use `nn.HybridSequential`
   ```python
   seq = nn.HybridSequential(my_layer(), my_layer())
   ```
   Then make data and run would raise an error
   ```
   HybridBlock requires the first argument to forward be either Symbol or 
NDArray, but got <class 'tuple'>
   ```
   
   Do you have any way to fix this?

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to 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