C3W3_Assignment_Natural Language Processing with Sequence Models

One theory here would be that there is something structural wrong with your notebook. E.g. have you run it on some other platform and then re-uploaded it back to Coursera? That’s not a good idea as other platforms like Colab modify the JSON “metadata” in the notebook in a way that messes over the Coursera graders.

The way to test this theory would be to get a clean copy of the notebook and then very carefully “copy/paste” over just your completed code from the “YOUR CODE HERE” sections and then try submitting to the grader.

Actually one easier first step is:

Kernel → Restart and Clear Output
Submit to grader

That is an easy way to make sure it’s not some of the generated output that is confusing the grader. I’ve seen that happen sometimes. The point is that the grader does not need to see your generated output: it only needs to call your functions to test them.

If that doesn’t help, then try the “clean copy” method and let us know if that helps or not.

1 Like