Error

[langmusi]

Hello! I am trying your code to learn how to build a RNN for my project.
I got an error when I ran this row of the code output = training_memory_layer(output)
NotImplementedError: Cannot convert a symbolic Tensor (lstm/strided_slice:0) to a numpy array. This error may indicate that you're trying to pass a Tensor to a NumPy call, which is not supported

where output is:
<KerasTensor: shape=(None, 259, 27) dtype=float32 (created by layer 'concat')>

What does the code here:
# training sample: calibration sequence sans the final element sample = training[:-1].values samples.append(sample)
Here I got a list of array of samples.
Do you know what is the problem? Thanks