I'm getting dimensions mismatch for the matrices /Improvise_a_Jazz_Solo_with_an_LSTM_Network_v4

Course Q&A Deep Learning Specialization Sequence Models
1

Step 2.A: select the "t"th time step vector from X.

    x = Lambda(lambda x: X[:,t,:])(X)
    #x = Lambda(lambda z: z[:, t, :])(X)

Step 2.B: Use reshaper to reshape x to be (1, n_values) (≈1 line)

    x = reshaper(x)

Error :

Test failed at index 1
Expected value

[‘Lambda’, (None, 90), 0]

does not match the input value:

[‘TensorFlowOpLayer’, [(None, 90)], 0]

what am I doing wrong ? the Reshape function must maintain the shapes to be [None,90] I believe there is type mismatch rather than matrices dimension mismatch
reshaper = Reshape((1, n_values))

2

Do not use a Lambda function to slice X to get ‘x’.
Just use array slicing.

2 Likes