[Week 4] Exercise 4 Encoder Layer

Course Q&A Deep Learning Specialization Sequence Models
1

I’m getting the following error:

AssertionError Traceback (most recent call last)
in
1 # UNIT TEST
----> 2 EncoderLayer_test(EncoderLayer)

~/work/W4A1/public_tests.py in EncoderLayer_test(target)
92 [[ 0.23017104, -0.98100424, -0.78707516, 1.5379084 ],
93 [-1.2280797 , 0.76477575, -0.7169283 , 1.1802323 ],
—> 94 [ 0.14880152, -0.48318022, -1.1908402 , 1.5252188 ]]), “Wrong values when training=True”
95
96 encoded = encoder_layer1(q, False, np.array([[1, 1, 0]]))

AssertionError: Wrong values when training=True

I’m following the process from: Transformer model for language understanding  |  Text  |  TensorFlow

Only difference with the tensorflow tutorial is our MultiHeadAttention has a dropout parameter included (so no need to add dropout in first stage).

Any ideas why my values are off?

2

Be very careful about using TensorFlow’s tutorials. These assignments do not necessarily follow the tutorials.

3

I’m a little lost though, because my output is somewhat close to result in unit test.
Could I sent private message to instructors with my code?