C5 W1 A3 - Music Inference Model issue: Graph disconnected: cannot obtain value for tensor

Course Q&A Deep Learning Specialization Sequence Models
1

I am having trouble on the assignment right now because I saw this error
ValueError: Graph disconnected: cannot obtain value for tensor Tensor("input_2:0", shape=(None, 1, 90), dtype=float32) at layer "lstm_1". The following previous layers were accessed without issue: [] While the error in the code it pointed towards inference_model = Model(inputs=[x, a0, c0], outputs=outputs)

I don’t understand how to solve this since I have got all the dimensions correctly, I don’t know where this error came from.

It also have a weird warning after it finish its run:

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)`.

Here is my code below:

# mentor edit - code removed

I have no idea how to address this problem

Best regards,

2

You have asked this same question several times. Mentor Tom gave you an answer on this other version of the question.

Your code for the inputs variable to the Model is incorrect. Please read again what Tom said.

3

Very sorry about the inconvenience, since my last post was removed for a while and I thought it will not be recovered, thus made a new post.