UNQ_C6: can't pass test

I am quite sure I have the solution implemented correctly but I have the following error:

Output must be a tuple of size 2 containing a integer and a float number
Expected output: [7283, -9.929085731506348]
0 Tests passed
2 Tests failed

Moreover, I got the following error when I try to run the sample_decode test:

NameError: name ‘logsoftmax_sample’ is not defined

I found out the reason:

Somehow my notebook is corrupted that the LogSoftmax_sample function is embedded into the commentary area.

Thanks. I can’t get the results now.

In Jupyter notebooks you can toggle the cell type from code to markdown or raw NBConvert. If a code cell has inadvertently been converted to markdown, you can switch it back with the Cell-Cell Type-Code menu option. (Saves the trouble of refreshing the notebook and starting the coding over)

I still cannot pass the question. I’ve used both the functions in the Jupyter notebook as well as tl.logsoftmax_sample(log_probs,temperature).

I figured out the problem. I was using NMTAttn(input_tokens, padded_with_batch), instead of NMTAttn((input_tokens, padded_with_batch)). It now works.