Music inference model - one-hot encoding

Hello, I am getting an error like “layer lstm expects 13 inputs, but it received 3 input tensors”. The problem is somewhere in one-hot encoding. Could someone help, pls?
{mentor edit: code removed}
inference_model = Model(inputs=[x0, a0, c0], outputs=outputs)

Never mind, have found the bug by myself :slight_smile:

Were you passing “out” to your argmax?

Hi, I don’t think this is a question for course 1 of the specialization, I think this is for course 5, right? I will change the post.

I suspect the problem is that 90 should not be a hard-coded value.