Course 5 Week 1 Assignment 3 Exercise 3

Course Q&A Deep Learning Specialization Sequence Models
1

My code did not return an error, but instead gave me numbers that are way above what it says is normal.

Normal
v

  • Your results may likely differ because Keras’ results are not completely predictable.
  • However, if you have trained your LSTM_cell with model.fit() for exactly 100 epochs as described above:
    • You should very likely observe a sequence of indices that are not all identical. Perhaps with the following values:
np.argmax(results[12]) = 26
np.argmax(results[17]) = 7
list(indices[12:18]) = [array([26]), array([18]), array([53]), array([27]), array([40]), array([7])]

My Result
v
np.argmax(results[12]) = 55
np.argmax(results[17]) = 82
list(indices[12:18]) = [array([55]), array([60]), array([1]), array([34]), array([20]), array([82])]

2

The only criteria is that not all predictions should be the same. See this text in the markdown: You should very likely observe a sequence of indices that are not all identical. Please go ahead with your submission.

3

@Adaramola_Samson Your notebook looks fine according to the current version of the assignment. Don’t forget to remove the shared file.

4

thank you, i appreciate the support

1 Like