All values are 0

Good day to all. The program does not throw errors, but the results do not match
my results:
gradients[“dx”][1][2] = [0. 0. 0. 0.]
gradients[“dx”].shape = (3, 10, 4)
gradients[“da0”][2][3] = 0.0
gradients[“da0”].shape = (5, 10)
gradients[“dWax”][3][1] = 0.0
gradients[“dWax”].shape = (5, 3)
gradients[“dWaa”][1][2] = 0.0
gradients[“dWaa”].shape = (5, 5)
gradients[“dba”][4] = [0.]
gradients[“dba”].shape = (5, 1)

Expected Output:

gradients[“dx”][1][2] = [-2.07101689 -0.59255627 0.02466855 0.01483317]
gradients[“dx”].shape = (3, 10, 4)
gradients[“da0”][2][3] = -0.314942375127
gradients[“da0”].shape = (5, 10)
gradients[“dWax”][3][1] = 11.2641044965
gradients[“dWax”].shape = (5, 3)
gradients[“dWaa”][1][2] = 2.30333312658
gradients[“dWaa”].shape = (5, 5)
gradients[“dba”][4] = [-0.74747722]
gradients[“dba”].shape = (5, 1)

Thank you for your time

Which exercise it is? Week and assignment number? And, is it ungraded section?

1 Like

Thanks everyone! I found a mistake! In gradients = rnn_cell_backward(da[:, :, t], caches[t]), I replaced da[:, :, t] with da_prevt.
lol