C4_W1_Q6 Output close to expected output but wrong

Course Q&A Natural Language Processing NLP with Attention Models
1

I’m stuck here for a few hours. No matter what I do, the output is still a few digits different from the expected output. What is wrong here, please help. I attached the error message below

AssertionError Traceback (most recent call last)
in
1 # UNIT TEST
2 # test_next_symbol
----> 3 w1_unittest.test_next_symbol(next_symbol, NMTAttn)

~/work/w1_unittest.py in test_next_symbol(target, model)
557 next_de_tokens = target(the_model, tokens_en, [18477], 0.0)
558 # print(‘next_de_tokens’, next_de_tokens)
→ 559 assert np.allclose([next_de_tokens[0], next_de_tokens[1]], [7283, -9.929085731506348]), f"Expected output: [{7283}, {-9.929085731506348}], your output: [{next_de_tokens[0]}, {next_de_tokens[1]}]"
560
561 print(“\033[92m All tests passed”)

AssertionError: Expected output: [7283, -9.929085731506348], your output: [7283, -9.819931983947754]

2

Hi @Frank_wu1

Most common mistake is using global variable model instead of the passed parameter NMTAttn.

Could that be your problem?

3

No, it was not my problem.

4

You can private message me (by clicking on my nickname) with your notebook attached and I can try to help.

5

Hi @arvyzukai , I get a similar situation, the output is slight different as below:
AssertionError: Expected output: [7283, -9.929085731506348], your output: [7283, -9.864036560058594]… I just message you with my lap ID. Many thanks as well.

6

Hi @EdmondChan

Mentors cannot access your learners’ notebooks by IDs (only staff members can). Before you private message me your notebook, please check these cases.