Course 5: Week 1: Dinosaur Exercise 4 list index out of range in rnn_forward

Course Q&A Deep Learning Specialization Sequence Models
1

Hi,

Trying to implement the model() function for exercise 4, but I’m receiving an index error: list index out of range in the rnn_forward function when I run my cells for exercise 4.

Here’s the output with my code censored with ‘<myCode>’.

j =  0 idx =  0
single_example = turiasaurus
single_example_chars ['t', 'u', 'r', 'i', 'a', 's', 'a', 'u', 'r', 'u', 's']
single_example_ix [20, 21, 18, 9, 1, 19, 1, 21, 18, 21, 19]
 X =  [None, 20, 21, 18, 9, 1, 19, 1, 21, 18, 21, 19] 
 Y =        [20, 21, 18, 9, 1, 19, 1, 21, 18, 21, 19, 0] 

Iteration: 0, Loss: 23.087336

Nkzxwtdmfqoeyhsqwasjkjvu
Kneb
Kzxwtdmfqoeyhsqwasjkjvu
Neb
Zxwtdmfqoeyhsqwasjkjvu
Eb
Xwtdmfqoeyhsqwasjkjvu


---------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
<ipython-input-12-725c093d6b91> in <module>
----> 1 parameters, last_name = model(data.split("\n"), ix_to_char, char_to_ix, 22001, verbose = True)
      2 
      3 assert last_name == 'Trodonosaurus\n', "Wrong expected output"
      4 print("\033[92mAll tests passed!")

<ipython-input-11-1dca6d0b0775> in model(data_x, ix_to_char, char_to_ix, num_iterations, n_a, dino_names, vocab_size, verbose)
     61         # Perform one optimization step: Forward-prop -> Backward-prop -> Clip -> Update parameters
     62         # Choose a learning rate of 0.01
---> 63         curr_loss, gradients, a_prev = <myCode>
     64 
     65         ### END CODE HERE ###

<ipython-input-9-fca0aba78113> in optimize(X, Y, a_prev, parameters, learning_rate)
     32 
     33     # Forward propagate through time (≈1 line)
---> 34     loss, cache = <myCode>
     35 
     36     # Backpropagate through time (≈1 line)

~/work/W1A2/utils.py in rnn_forward(X, Y, a0, parameters, vocab_size)
    100 
    101         # Update the loss by substracting the cross-entropy term of this time-step from it.
--> 102         loss -= np.log(y_hat[t][Y[t],0])
    103 
    104     cache = (y_hat, a, x)

IndexError: list index out of range

I re-ran all the cells before this one and all the tests passed, so doubt there’s anything wrong with any of the prior functions.

I re-read all the steps and still can’t figure out why I’m receiving this index-out-of-range error. I assume Y[t] is the problem?

Any help would be much appreciated, thanks.

2

Hi @aPerson ,

The problem arises in rnn_forward(), an utility function that is provided for you.
Try refresh the kernel and rerun the code from start to see if it helps.

4

Typically that’s an invalid assumption. Passing the unit tests does not prove that your code is perfect.

5

Nevermind, I figured it out. This error occurred on the second iteration and turns out I was setting Y incorrectly. Thanks anyway.

6

Hi @aPerson ,

Great to hear you have got it sorted. Thanks.