C5 W4 A1: Positional_encoding - Sum of square pairs must be 1

Course Q&A Deep Learning Specialization Sequence Models
1

I’m stuck with the error:

AssertionError Traceback (most recent call last)
in
29
30
—> 31 positional_encoding_test(positional_encoding)

<ipython-input-76-848c64b9c901> in positional_encoding_test(target)
     12 
     13     ones = sin_part ** 2  +  cos_part ** 2
---> 14     assert np.allclose(ones, np.ones((1, position, d_model // 2))), "Sum of square pairs must be 1 = sin(a)**2 + cos(a)**2"
     15 
     16     angs = np.arctan(sin_part / cos_part)

AssertionError: Sum of square pairs must be 1 = sin(a)**2 + cos(a)**2

the previous test for get_angles ran fine.

2

Hey @petermoser,

It seems that you have an issue with initializing the initial values for sine and cosine functions. Please, check this post for some details on that.

3

are you saying that my sin / cos calcuation, e.g.:
angle_rads[:, 0::2] = np.sin(angle_rads[:, 0::2])
is wrong or that the initial values in angle_rads are wrong?
As mentioned, the tests for get_angles ran fine.

4

If tests for the get_angles function ran fine, the problem seems to be in the sin / cos calcuation. Check that you pass different columns of the angle_rads matrix as arguments to sine and cosine functions. Each column provides values for a single curve.

Please, remove the code from your post. That’s against the rules.

5

I’m having the same problem and I don’t quite understand what you’re saying. I’m passing the columns of angle rads to the sin and cos functions using 0::2 for both, when I try messing with them I get shape errors or steps backward, any help would be greatly appreciated.

edit, the only thing that responds with the same “sum of square pairs must = …” is -1::1

6

That’s a problem. 0::2 works for sine. 1::2 works for cosine - because sin uses (2i) and cos uses (2i + 1).

7

when I use 1::2 for cosine it doesn’t work. gives me a previous error .“Did you apply sin and cos to even and odd parts respectively?”.

8

There is other code that is involved, the 1::2 is just the indexing portion.

10 
    # START CODE HERE
# code removed
    # END CODE HERE
1 Like