C5_W4_A1 scaled_dot_product_attention assistance requested

Course Q&A Deep Learning Specialization Sequence Models
1

I am struggling solving this exercise. I have implemented what should be the right steps. I cannot get past a Wrong Masked Weights error. I would greatly appreciate guidance:

AssertionError                            Traceback (most recent call last)
<ipython-input-118-00665b20febb> in <module>
      1 # UNIT TEST
----> 2 scaled_dot_product_attention_test(scaled_dot_product_attention)

~/work/W4A1/public_tests.py in scaled_dot_product_attention_test(target)
     73     assert np.allclose(weights, [[0.30719590187072754, 0.5064803957939148, 0.0, 0.18632373213768005],
     74                                  [0.3836517333984375, 0.3836517333984375, 0.0, 0.2326965481042862],
---> 75                                  [0.3836517333984375, 0.3836517333984375, 0.0, 0.2326965481042862]]), "Wrong masked weights"
     76     assert np.allclose(attention, [[0.6928040981292725, 0.18632373213768005],
     77                                    [0.6163482666015625, 0.2326965481042862],

AssertionError: Wrong masked weights
2

You have posted in the General Discussions forum.

Please use the “pencil” tool in the thread title to move your post to the forum for the course you’re attending.

Thanks!

3

This suggests an error in how your code is using the “mask” variable in this part of the code:

image
image854×146 5.9 KB

image

4

Thanks. I messed up the order of operations, placing the -1e9 inside the parentheses instead of outside.