C5W1A2 Excercise 2 - AssertionError: Wrong Values

Course Q&A Deep Learning Specialization Sequence Models
1

I am getting an AssertionError: Wrong values. I have checked the calculations and everything looks fine, yet I’m unable to get the required values. The following is my output :

Sampling:
list of sampled indices:
 [23, 16, 26, 26, 19, 25, 22, 16, 7, 11, 17, 26, 23, 23, 23, 18, 10, 6, 12, 2, 14, 24, 14, 17, 7, 18, 0]
list of sampled characters:
 ['w', 'p', 'z', 'z', 's', 'y', 'v', 'p', 'g', 'k', 'q', 'z', 'w', 'w', 'w', 'r', 'j', 'f', 'l', 'b', 'n', 'x', 'n', 'q', 'g', 'r', '\n']

---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
<ipython-input-9-a13d660e654a> in <module>
     19     print("\033[92mAll tests passed!")
     20 
---> 21 sample_test(sample)

<ipython-input-9-a13d660e654a> in sample_test(target)
     15     assert indices[-1] == char_to_ix['\n'], "All samples must end with \\n"
     16     assert min(indices) >= 0 and max(indices) < len(char_to_ix), f"Sampled indexes must be between 0 and len(char_to_ix)={len(char_to_ix)}"
---> 17     assert np.allclose(indices[0:6], [23, 16, 26, 26, 24, 3]), "Wrong values"
     18 
     19     print("\033[92mAll tests passed!")

AssertionError: Wrong values

I’ve been stuck on this assignment for a week now and would love it if anyone could help me out.
Thanks

2

Hi @shrekansal ,

If you are sure you have checked your calculations followed the formulas correctly, then, post that section of code in a direct message to me. I will have a look for you.

3

@Kic Thanks for your help, but I figured out the cause of the problem

4

Hey @shrekansal I stumbled upon your thread because I’m stuck with the same error. In my case, the six first indices are [23, 16, 15, 1, 7, 23] (it gets wrong by the third index). Do you have any clue on which mistake you found in your code?

5

Oh, just found my mistake. For future reference, in case anyone gets here facing similar problem, I figured it out after fixing two things:

  • x and a_prev must be column vectors,
  • y is a 2D array and, as one can find in the problem tips, np.random.choice asks for a 1D array summing to 1.
1 Like
6

Any help is greatly appreciated.
Here is my list of sampled indices:
[23, 16, 26, 26, 24, 3, 21, 1, 7, 24, 15, 3, 25, 20, 6, 13, 10, 8, 20, 12, 2, 0]

It fails after the first one (23). I believe my implementation of idx using np.random.choice is incorrect. I belive I’m implementing the probabilitieds or range wrongly. Thanks for your help

7

Hi @francktchafa ,

Please post a fresh query with error message to get a speedy response.