Course5 Week3-assignment1-modelf

Course Q&A Deep Learning Specialization Sequence Models
1

Hey there,

I have been stuck in this block for a long time and I check through all the similar threads but I still cannot find any bug in my codes, could anyone give me a hand? Really appreciate it.

Here’s the error message:

WARNING:tensorflow:Functional inputs must come from `tf.keras.Input` (thus holding past layer metadata), they cannot be the output of a previous non-Input layer. Here, a tensor specified as input to "functional_1" was not an Input tensor, it was generated by layer lstm.
Note that input tensors are instantiated via `tensor = tf.keras.Input(shape)`.
The tensor that caused the issue was: lstm/PartitionedCall_19:0
WARNING:tensorflow:Functional inputs must come from `tf.keras.Input` (thus holding past layer metadata), they cannot be the output of a previous non-Input layer. Here, a tensor specified as input to "functional_1" was not an Input tensor, it was generated by layer lstm.
Note that input tensors are instantiated via `tensor = tf.keras.Input(shape)`.
The tensor that caused the issue was: lstm/PartitionedCall_19:3
---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
<ipython-input-13-d6a140825d8e> in <module>
     34 
     35 
---> 36 modelf_test(modelf)

<ipython-input-13-d6a140825d8e> 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-12-2101083d2371> in modelf(Tx, Ty, n_a, n_s, human_vocab_size, machine_vocab_size)
     50 
     51     # Step 3: Create model instance taking three inputs and returning the list of outputs. (≈ 1 line)
---> 52     model = Model(inputs=[X,s,c], outputs=outputs)
     53 
     54     ### END CODE HERE ###

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py in __new__(cls, *args, **kwargs)
    240       # Functional model
    241       from tensorflow.python.keras.engine import functional  # pylint: disable=g-import-not-at-top
--> 242       return functional.Functional(*args, **kwargs)
    243     else:
    244       return super(Model, cls).__new__(cls, *args, **kwargs)

/opt/conda/lib/python3.7/site-packages/tensorflow/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
    455     self._self_setattr_tracking = False  # pylint: disable=protected-access
    456     try:
--> 457       result = method(self, *args, **kwargs)
    458     finally:
    459       self._self_setattr_tracking = previous_value  # pylint: disable=protected-access

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/functional.py in __init__(self, inputs, outputs, name, trainable)
    113     #     'arguments during initialization. Got an unexpected argument:')
    114     super(Functional, self).__init__(name=name, trainable=trainable)
--> 115     self._init_graph_network(inputs, outputs)
    116 
    117   @trackable.no_automatic_dependency_tracking

/opt/conda/lib/python3.7/site-packages/tensorflow/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
    455     self._self_setattr_tracking = False  # pylint: disable=protected-access
    456     try:
--> 457       result = method(self, *args, **kwargs)
    458     finally:
    459       self._self_setattr_tracking = previous_value  # pylint: disable=protected-access

/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/functional.py in _init_graph_network(self, inputs, outputs)
    182       # It's supposed to be an input layer, so only one node
    183       # and one tensor output.
--> 184       assert node_index == 0
    185       assert tensor_index == 0
    186       self._input_layers.append(layer)

AssertionError:
2

To create a model, we specify “input” and “output”. In your case, “outputs” is OK. But, “inputs” is not initial parameters to be passed to the model. What you specified is the Ty-th “s” and “c”. Please revisit this point.

3

Yes, I think I am passing the Ty-th “s” and “c” but still not working, what I wrote is:

model = Model(inputs=[X,s,c], outputs=outputs)
4

That is wrong. As I wrote,

To create a model, we specify “input” and “output”. In your case, “outputs” is OK. But, “inputs” is not initial parameters to be passed to the model

You need to set the “input” to the network, not updated s/c by the network. If you look at the code, you will find which is the initial one.

5

Oh, sorry I misunderstand you before, now I figured it out. Thank you so much for your time!