Output error in last exercise of assignment 3

here is the output attached for the predict_and_sample exercise of assignment 3

(1, 90)
np.argmax(results[12]) = 0
np.argmax(results[17]) = 0
list(indices[12:18]) = [0, 0, 0, 0, 0, 0]

could anyone please resolve why I am getting all zeros

Which week in Course 5? (I’m going to assume it is Week 1).

Since your values for “indices” are wrong, I suspect there is an error in your code for the indices.
What axis argument did you use there?

indices = np.argmax(pred,axis = 0)
this is the indices part

axis = 0 is wrong. Try axis = -1.

1 Like

Earlier I tried axis=-1 but it showed an error

axis=-1 is correct.
If you got an error, it’s because of some other problem in your code.

SIR shall I dm you the code??
if yes please specify which part…

Just post your code here for the function that has the np.argmax() statement in it.

sir here is the code

indices = np.argmax(pred,axis = -1)

and this is the error displayed

IndexError                                Traceback (most recent call last)
<ipython-input-22-e3fa72710400> in <module>
      1 results, indices = predict_and_sample(inference_model, x_initializer, a_initializer, c_initializer)
----> 3 print("np.argmax(results[12]) =", np.argmax(results[12]))
      4 print("np.argmax(results[17]) =", np.argmax(results[17]))
      5 print("list(indices[12:18]) =", list(indices[12:18]))

IndexError: index 12 is out of bounds for axis 0 with size 1

1 Like

Sir please explain the error I am unable to figure it out

I’m getting a different error for the same code:- indices = np.argmax(pred,axis = -1)

ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()


I’m already monitoring the thread. You don’t need to ping me specifically.

Which week and assignment number?
Which function?

The Week 1 Jazz Assignment, in the predict and sample function

Perhaps your “pred” values are not correct.

It would help if you post the entire error stack including the assert message.