Week1-Jazz Improvisation with LSTM

Course Q&A Deep Learning Specialization Sequence Models
1

Hi,
I’m encountering the following error while using an LSTM model:
“AttributeError: The layer ‘lstm_1’ has multiple inbound nodes, with different input shapes. Hence the notion of ‘input shape’ is ill-defined for the layer. Use get_input_shape_at(node_index) instead.”

The error occurs in this part of my music_inference_model function:
index = tf.math.argmax(out, axis=-1)
x = tf.one_hot(index, depth=n_values)
x = RepeatVector(1)(x)
How can I resolve this issue? I’ve double-checked the code with the RepeatVector and one_hot operations, but I think there might be an issue with how the model shape is defined. How can I properly define the input shape for the LSTM layer?

Thank you in advance for your help.

2

If you search the forums for “multiple inbound nodes LSTM”, you’ll find lots of hits. E.g. here’s one.

If that’s not enough to get you to a solution, please check your DMs for a message from me about how to proceed.