Another problem with 'Improvise a Jazz Solo with an LSTM Network

[shamim]

I am getting error in 'music_inference_model with the message:

AttributeError: The layer “lstm_3” has multiple inbound nodes, with different output shapes. Hence the notion of “output shape” is ill-defined for the layer. Use get_output_shape_at(node_index) instead.
I need assistance.

Thanks

Abdus Shamim Khan

[TMosh]

Try searching the discussion forum for the phrase “multiple inbound nodes”. You’ll find a lot of threads about this error.

[shamim]

I did not see any specific solution for ‘multiple inbound nodes’ in the discussion forum. Can you please suggest way around this problem. Thanks, I will appreciate your assistance.

[TMosh]

Try this thread.

C5 W1 A3: Jazz Improvisation with LSTM (Problem and Tips)

For djmodel(). check these common issues: slicing X correctly. using the “reshaper()” and “densor()” functions with the appropriate arguments. used LSTM_cell() with the appropriate “inputs=” and “initial_state=[… ]” arguments. For music_inference_model(), the common errors are: Instruction 2.D tells you for argmax, use the arguments ‘out’ and ‘axis=-1’, and it says for onehot to use the arguments ‘x’ and ‘depth=n_values’. Instruction 2.E gives you the exact code to use for RepeatVector. Fo…

[shamim]

Thanks for your assistance. I got it correct.

Shamim