C5_W4_A1_Transformer_Subclass_v1, assertion error in the last class

Course Q&A Deep Learning Specialization Sequence Models
1

I have a problem in the subject assignment, all the exercises pass but the last one gives assertion error.(wrong value)

---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
<ipython-input-25-a562b46d78e0> in <module>
      1 # UNIT TEST
----> 2 Transformer_test(Transformer, create_look_ahead_mask, create_padding_mask)

~/work/W4A1/public_tests.py in Transformer_test(target, create_look_ahead_mask, create_padding_mask)
    286     assert np.allclose(translation[0, 0, 0:8],
    287                        [0.017416516, 0.030932948, 0.024302809, 0.01997807,
--> 288                         0.014861834, 0.034384135, 0.054789476, 0.032087505]), "Wrong values in translation"
    289 
    290     keys = list(weights.keys())

AssertionError: Wrong values in translation

I found also that if I changed block1 and block2 in the class

class Decoder(tf.keras.layers.Layer):

the test still pass? :slightly_frowning_face:

2

This means there is an error somewhere in your code, in either the Encoder or the Decoder.

3

But why it passes the test if there are errors?, I will try to find it.

4

@TMosh can you help me I can’t find it. I don’t know why I’m blind to see it.

5

The tests in the notebook do not catch every possible error.