Nerual Machine Translation ipnb

Course Q&A Deep Learning Specialization Sequence Models
1

Having an issue with the Modelf function. Everything looks correct but…

output:

AttributeError                            Traceback (most recent call last)
<ipython-input-42-9b52ab27df8a> in <module>
     32 
     33 
---> 34 modelf_test(modelf)

<ipython-input-42-9b52ab27df8a> in modelf_test(target)
     11 
     12 
---> 13     model = target(Tx, Ty, n_a, n_s, len_human_vocab, len_machine_vocab)
     14 
     15     print(summary(model))

<ipython-input-41-2d81ae6b9d56> in modelf(Tx, Ty, n_a, n_s, human_vocab_size, machine_vocab_size)
     51     # Step 3: Create model instance taking three inputs and returning the list of outputs. (≈ 1 line)
     52     model = Model(inputs=[X,s0,c0], outputs = outputs)
---> 53     print(summary(model))
     54     ### END CODE HERE ###
     55 

~/work/W3A1/test_utils.py in summary(model)
     36     result = []
     37     for layer in model.layers:
---> 38         descriptors = [layer.__class__.__name__, layer.output_shape, layer.count_params()]
     39         if (type(layer) == Conv2D):
     40             descriptors.append(layer.padding)

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in output_shape(self)
   2190                            'ill-defined for the layer. '
   2191                            'Use `get_output_shape_at(node_index)` '
-> 2192                            'instead.' % self.name)
   2193 
   2194   @property

AttributeError: The layer "concatenate" has multiple inbound nodes, with different output shapes. Hence the notion of "output shape" is ill-defined for the layer. Use `get_output_shape_at(node_index)` instead.
2

There are lots of possible causes.

3

Solved, kernel restart required.

1 Like