Course 5: Week 1 - Assignment 3 (Jazz) - Exercise 1

Course Q&A Deep Learning Specialization Sequence Models
23

hi, it works for me.
Can you explain why?, pls
Thank you and Best regards,
AnPham

24

Which “it” are you referring to? This thread covers a lot of topics.

25

Hi! I had the same problem, so I restarted the kernel and now it gives error. I can send code in DM. Any ideas why it happening?

Test failed at index 1
Expected value

[‘TensorFlowOpLayer’, [(30, 90)], 0]

does not match the input value:

[‘TensorFlowOpLayer’, [(None, 90)], 0]

AssertionError Traceback (most recent call last)
in
3 # UNIT TEST
4 output = summary(model)
----> 5 comparator(output, djmodel_out)

~/work/W1A3/test_utils.py in comparator(learner, instructor)
26 “\n\n does not match the input value: \n\n”,
27 colored(f"{a}", “red”))
—> 28 raise AssertionError(“Error in test”)
29 print(colored(“All tests passed!”, “green”))
30

AssertionError: Error in test

26

the error was in x = X[t, :] instead it should be x = X[:, t, :], but I dont realy get why. X = Input(shape=(Tx, n_values)) sets in the function and it is 2Dims , but here we referencing to a global var X with 3Dims?

27

When you declare the input like that, it does not include the “samples” dimension: you are just declaring the shape of the individual tensor values. The input to the model will be batches (even if stochastic minibatches) that include the samples dimension.