W4 A1 | Exercise-7 | Assertion Error

Hi everyone,
I am getting frustrated with this exercise. I get for Exercise 7 the following assertion error

AssertionError Traceback (most recent call last)
----> 2 Decoder_test(Decoder, create_look_ahead_mask, create_padding_mask)

~/work/W4A1/public_tests.py in Decoder_test(target, create_look_ahead_mask, create_padding_mask)
221 assert tf.is_tensor(outd), “Wrong type for outd. It must be a dict”
222 assert np.allclose(tf.shape(outd), tf.shape(encoderq_output)), f"Wrong shape. We expected { tf.shape(encoderq_output)}"
→ 223 assert np.allclose(outd[1, 1], [-0.2715261, -0.5606001, -0.861783, 1.69390933]), “Wrong values in outd”
225 keys = list(att_weights.keys())

AssertionError: Wrong values in outd

I’ve already seen that there were couple of other reports for that, but none of them were helpful for me. I have checked the training flag in the dropout and the create padding and look ahead masks were not changed. All tests before that were passing. Is there something else I could check or discuss the code with someone.

1 Like

Hello, Michael.

Welcome to the community.

Are you still facing this issue?

If yes, then closely follow the list of attention weights that you are calling for the functions. Also, check whether you have placed blocks differently.