Week 1 Dinosaurus Island rnn_forward throws error

Course Q&A Deep Learning Specialization Sequence Models
1

My optimize functions passes all tests. However, when I call optimize from the model function, the supplied function rnn_forward throws this error:
IndexError: only integers, slices (:), ellipsis (...), numpy.newaxis (None) and integer or boolean arrays are valid indices

Thanks.

2

P.S. I already validated that my X is a list of characters, with ‘None’ in the first position, and my Y is an equal-length list of numbers with 0 in the last position. This is what I understood the instructions to intend.

3

X uses [None] and single_example_ix
Y is a copy of X starting from position 1, then with ix_newline appended.

4

Thanks–that change makes my code run, but I still get wrong values. Any clue what it could be?

Also, the directions are confusing to me–they explicitly state that X is a list of CHARACTERS, not integers, as seems to be correct:

Create the list of input characters: X
  • rnn_forward uses the None value as a flag to set the input vector as a zero-vector.
  • Prepend the list [ None ] in front of the list of input characters.
  • There is more than one way to prepend a value to a list. One way is to add two lists together: ['a'] + ['b']
5

That probably should say “Create the list of input character indices: X”.

The previous step - Convert list of characters to a list of integers: single_example_ix
converts the characters into character indices.

The the “X” values are character indices, not the original characters. That’s what “list of integers” means.

6

Thank you very much for the hint. I had exactly the same error. After I correct the code accordingly, I still get the following error, could you please help me? Thank you very much!

----> 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!")

in model(data_x, ix_to_char, char_to_ix, num_iterations, n_a, dino_names, vocab_size, verbose)
84 if j % 2000 == 0:
85
—> 86 print('Iteration: %d, Loss: f' (j, loss) + ‘\n’)
87
88 # The number of dinosaur names to print

TypeError: only size-1 arrays can be converted to Python scalars

for debug purpose I printed the following labels:
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]

7

This thread is 6 months old. I recommend you start a new thread for your question.