Got AssertionError: Expected output: [7283, -9.92…] Your output: [7283, -0.61…] Got the symbol correctly, but the prob is wrong. Passed all unit tests before this point. Thank you for suggestions.

Thank you. I used NMTAttn variable instead of the global model variable. Otherwise, my next symbol would be 140. The padding also appeared OK. My question is how I could get the correct next symbol, but with a very different log probability. The expected log prob is -9.9290 (or 0.03%), and my comput…

Most probably the problem lies not in the model (if you passed previous tests and got the expected outputs) but the way you handle the outputs. For example, you might unnecessary applied softmax or other operations (your predicted token would still be correct, but the log probs wouldn’t). Does your …

Thank you. My output does not match your output in #6. My debugging display: Current output tokens: Token length: 0 The padded length is: 1 The padded is: [0] output: [[[0. 0. 0. … 0. 0. 0.]]] The log_probs is: [0. 0. 0. … 0. 0. 0.] The symbol is: 0 The log_prob of symbol is: 0.0 C…

This indicates that your model outputs are off, for the test case they should be (approximately): for the first step: [0] [[[-10.323489 -10.371064 -10.382686 … -10.290064 -10.399619 -10.410941]]] for the second step: [18477, 0] [[[-10.323489 -10.371064 -10.382686 … -10.290064 -10.399619 -…

Thank you. My model passed the unit test and it is displayed as follows: Serial_in2_out2[ Select[0,1,0,1]_in2_out4 Parallel_in2_out2[ Serial[ Embedding_33300_1024 LSTM_1024 LSTM_1024 ] Serial[ Serial[ ShiftRight(1) ] Embedding_33300_1024 LSTM_1024 ] ] PrepareAttentionInput_in3_out4 …

If someone else in the future encounters the same values (Your output: [7283, -0.61…]), you probably specified the wrong axis for LogSoftmax layer. You do not need to specify axis for the LogSoftmax layer in this Assignment (the default value (and correct) is -1, the last dimension of the tensor).

C4W1: UNQQ-C6: unittest.test_next_symbol failed

Course Q&A Natural Language Processing NLP with Attention Models

arvyzukai October 30, 2023, 11:02am 2

Hi @George_Hsieh

Make sure you do not use global model variable instead of NMTAttn variable. Also check your padding implementation. Here you could find hints what went wrong:

Cheers

Topic		Replies	Views
C4_W1_C6 next_symbol returns AssertionError NLP with Attention Models week-module-1	3	626	February 8, 2023
C4W1 next_symbol function not working NLP with Attention Models week-module-1	14	987	January 18, 2023
Assistant needed to solve a cryptic crror when implementing C6 NLP with Attention Models week-module-1	5	563	February 12, 2023
C4W1 - stuck in Ex6 NLP with Attention Models week-module-1	12	919	May 30, 2023
C4_W1_Q6 Output close to expected output but wrong NLP with Attention Models week-module-1	5	557	April 3, 2023

C4W1: UNQQ-C6: unittest.test_next_symbol failed

Related topics