W1A3E2 Getting an error message and I don't know how to fix it

I am lost here and don’t know what my mistake could be anymore.If someone could help me, I would be very happy. I have seen that earlier others had also problems with this exercise and resetting the kernel helped them. This did help for Exercise 1, which I was also stuck on, but does not seem to be the problem for Exercise 2. Also the dimensions of x seem to be true during the execution of the function.

I get the following 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_4” was not an Input tensor, it was generated by layer repeat_vector_149.
Note that input tensors are instantiated via tensor = tf.keras.Input(shape).
The tensor that caused the issue was: repeat_vector_149/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_4” was not an Input tensor, it was generated by layer lstm_50.
Note that input tensors are instantiated via tensor = tf.keras.Input(shape).
The tensor that caused the issue was: lstm_50/PartitionedCall:2
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_4” was not an Input tensor, it was generated by layer lstm_50.
Note that input tensors are instantiated via tensor = tf.keras.Input(shape).
The tensor that caused the issue was: lstm_50/PartitionedCall:3

AssertionError Traceback (most recent call last)
in
1 ### YOU CANNOT EDIT THIS CELL
----> 2 inference_model = music_inference_model(LSTM_cell, densor, Ty = 50)

in music_inference_model(LSTM_cell, densor, Ty)
60
61 # Step 3: Create model instance with the correct “inputs” and “outputs” (≈1 line)
—> 62 inference_model = Model(inputs=[x, a, c], outputs = outputs)
63
64 ### 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)
183 # and one tensor output.
184 assert node_index == 0
→ 185 assert tensor_index == 0
186 self._input_layers.append(layer)
187 self._input_coordinates.append((layer, node_index, tensor_index))

AssertionError:

Thanks for your help.

Check this:

model = Model(inputs=[input_x, initial_hidden_state, initial_cell_state], outputs=the_outputs)

Hint: What are the notations for initial_hidden_state, initial_cell_state?

1 Like

Thank you very much! If I use the initial values, it works perfectly. I somehow missed this all the time… :smiley: