C5W1A3 Exercise 2

Course Q&A Deep Learning Specialization Sequence Models
1

Hi,

I am try to complete the music_inference_model function but keep getting the following error and warning thrown from
inference_model = music_inference_model(LSTM_cell, densor, Ty = 50)

The error is:

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_2" was not an Input tensor, it was generated by layer repeat_vector_49.
Note that input tensors are instantiated via `tensor = tf.keras.Input(shape)`.
The tensor that caused the issue was: repeat_vector_49/Tile: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_2" 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_79:0
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_2" 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_79:3
---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
<ipython-input-15-0bba7a7c9ee3> in <module>
      1 # LSTM_cell = LSTM(n_a, return_state = True)
----> 2 inference_model = music_inference_model(LSTM_cell, densor, Ty = 50)

<ipython-input-14-5476633b37c7> in music_inference_model(LSTM_cell, densor, Ty)
     58 
     59     # Step 3: Create model instance with the correct "inputs" and "outputs" (≈1 line)
---> 60     inference_model = Model(inputs = [x, a, c], outputs=outputs)
     61 
     62     ### 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:

Please note, this is the full error, I have not forgotten to copy-paste whatever might follow the AssertionError. I am not sure how to debug this.

Is the warning supposed to show up? I have not made any changes to how x and x0 are defined in the provided code and, as instructed, am not using x0 when calling LSTM_cell.

Since half of the code we are asked to write ourselves is similar to the code in the djmodel() I am assuming there is an issue with step 2D. In this step, I have called the argmax function on out on the last axis (I think) and called one_hot with input x with the correct depth parameter.

Any help is appreciated!

2

At line 60, your list of inputs to the Model() layer is incorrect.

5 Likes