Course - 5 - Week 4- Encoder asserts "Wrong values"

Course Q&A Deep Learning Specialization Sequence Models
1

Getting failed at UNQ_C5 function.

assert np.allclose(encoderq_output.numpy(), 
                   [[[-0.40172306,  0.11519244, -1.2322885,   1.5188192 ],
                     [ 0.4017268,   0.33922842, -1.6836855,   0.9427304 ],
                     [ 0.4685002,  -1.6252842,   0.09368491,  1.063099  ]],
                    [[-0.3489219,   0.31335592, -1.3568854,   1.3924513 ],
                     [-0.08761203, -0.1680029,  -1.2742313,   1.5298463 ],
                     [ 0.2627198,  -1.6140151,   0.2212624 ,  1.130033  ]]]), "Wrong values"

failed at the above validation. Any inputs will be appreciated.

2

Do you still need an answer to this question?

3

Hi, thanks fr checking. I’ve figured out the issue and completed the certification

4

Hi, @sankarg I got the same problem. How did you solve it? Could you help me?

5

I’ve also figured it out, was just a stupid error from me. btw whoever has this problem, check this out: Pedagogy of C5-W4-A1 (-Ex4: Encoder Layer)

6

I still could not figure out the problem. It seems to me that it is related to the random initializations, even when I print self.mha = MultiHeadAttention(num_heads=num_heads, key_dim=embedding_dim, dropout=dropout_rate), I get different valeus every time

7

This thread is two years old. Please start a new one and share your full error.