W1A3 music_inference_model: unknown error

Course Q&A Deep Learning Specialization Sequence Models
1

I run this code:

LSTM_cell = LSTM(n_a, return_state = True)
inference_model = music_inference_model(LSTM_cell, densor, Ty = 50)

here are my x.shape before the error:

after argmax: Tensor(“ArgMax_212:0”, shape=(None,), dtype=int64)
after one_hot: Tensor(“OneHot_211:0”, shape=(None, 90), dtype=float32)
after RepeatVector: (None, 1, 90)

and then some warnings:

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_8” was not an Input tensor, it was generated by layer repeat_vector_249.
Note that input tensors are instantiated via tensor = tf.keras.Input(shape).
The tensor that caused the issue was: repeat_vector_249/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_8” was not an Input tensor, it was generated by layer lstm_61.
Note that input tensors are instantiated via tensor = tf.keras.Input(shape).
The tensor that caused the issue was: lstm_61/PartitionedCall_49:0
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_8” was not an Input tensor, it was generated by layer lstm_61.
Note that input tensors are instantiated via tensor = tf.keras.Input(shape).
The tensor that caused the issue was: lstm_61/PartitionedCall_49:3

then i had this error:

---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
<ipython-input-30-c55ce93f25e1> in <module>
      1 LSTM_cell = LSTM(n_a, return_state = True)
----> 2 inference_model = music_inference_model(LSTM_cell, densor, Ty = 50)

<ipython-input-29-1f6385a6058a> in music_inference_model(LSTM_cell, densor, Ty)
     66     print(f"\tx: {x.shape}")
     67     print("\t", len(outputs))
---> 68     inference_model = Model(inputs=[x, a, c], outputs=outputs)
     69 
     70     ### 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 tell me why. ths

2

The inputs you specified are incorrect. Should be [x0, a0, c0].
“x” is the output tensor, you can’t use it as the model input.