Programming Assignment: Transformers Architecture with TensorFlow-Exercise 6 - DecoderLayer

Course Q&A Deep Learning Specialization Deep Learning Resources
1

Hi,
I am stuck with “Programming Assignment: Transformers Architecture with TensorFlow” Exercise 6 - DecoderLayer.
I get the error message:
AssertionError Traceback (most recent call last)
in
1 # UNIT TEST
----> 2 DecoderLayer_test(DecoderLayer, create_look_ahead_mask)

~/work/W4A1/public_tests.py in DecoderLayer_test(target, create_look_ahead_mask)
179
180 assert np.allclose(attn_w_b1[0, 0, 1], [0.5271505, 0.47284946, 0.], atol=1e-2), “Wrong values in attn_w_b1. Check the call to self.mha1”
→ 181 assert np.allclose(attn_w_b2[0, 0, 1], [0.32048798, 0.390301, 0.28921106]), “Wrong values in attn_w_b2. Check the call to self.mha2”
182 assert np.allclose(out[0, 0], [-0.22109576, -1.5455486, 0.852692, 0.9139523]), “Wrong values in out”
183

AssertionError: Wrong values in attn_w_b2. Check the call to self.mha2

2

Searching on this forum for 0.5271505, 0.47284946, 0 does produce some results that seem informative to your problem. If none of those help, please click my name and message your notebook as an attachment.

3

Thank you very much for your reply. I found the same issue in another discussion. Thankfully, my problem is solved.

4

Good to know. Please update this thread with the link that helped resolve your problem to help other learners.