Lstm_forward not enough values to unpack

Course Q&A Deep Learning Specialization Sequence Models
1

I have a problem with shape of x in this function. I do not understand why the shape is incorrect.
The function describes x a having this shape:

x – Input data for every time-step, of shape (n_x, m, T_x)

Then I retrieved the dimensions as such:

Retrieve dimensions from shapes of x and parameters[‘Wy’] (≈2 lines)

n_x, m, T_x = x.shape

And I get this error:

ValueError                                Traceback (most recent call last)
<ipython-input-89-5b9326f2c416> in <module>
     14 parameters_tmp['by'] = np.random.randn(2, 1)
     15 
---> 16 a_tmp, y_tmp, c_tmp, caches_tmp = lstm_forward(x_tmp, a0_tmp, parameters_tmp)
     17 print("a[4][3][6] = ", a_tmp[4][3][6])
     18 print("a.shape = ", a_tmp.shape)

<ipython-input-88-4979097eb753> in lstm_forward(x, a0, parameters)
     51         xt = x[:,:,t]
     52         # Update next hidden state, next memory state, compute the prediction, get the cache (≈1 line)
---> 53         a_next, c_next, yt, cache = rnn_forward(xt,a_next,parameters)
     54         # Save the value of the new "next" hidden state in a (≈1 line)
     55         a[:,:,t] = a_next

<ipython-input-84-952eeea79dce> in rnn_forward(x, a0, parameters)
     26 
     27     # Retrieve dimensions from shapes of x and parameters["Wya"]
---> 28     n_x, m, T_x = x.shape
     29     n_y, n_a = parameters["Wya"].shape
     30 

ValueError: not enough values to unpack (expected 3, got 2)

Why x.shape is only getting 2 dimensions as output ??

2

Why are you calling rnn_forward from inside lstm_forward ?

---> 53         a_next, c_next, yt, cache = rnn_forward(xt,a_next,parameters)
3

oh yes, I’m mixing up architectures. My bad, I have solved the problem . thanks