Week 5, Assignment 2

Everything runs smoothly but my network seems to learn faster than the reference solution. I’ve double and triple-checked things such as the learning rate and clip-values (-5 to 5). Anyone else end up in this place?

Iteration: 22000, Loss: 20.578871

Hutusaurus
Euca
Eustrioppn
Hocamptopanceus
Xuspeodon
Elacropechus
Uspeodon


AssertionError Traceback (most recent call last)
in
1 parameters, last_name = model(data.split("\n"), ix_to_char, char_to_ix, 22001, verbose = True)
2
----> 3 assert last_name == ‘Trodonosaurus\n’, “Wrong expected output”
4 print("\033[92mAll tests passed!")

AssertionError: Wrong expected output

Since you’re getting an assert due to having the wrong output, I’d say you should look for errors in your code.

Yes of course. :slight_smile: I’ve done so many times already line by line, carefully comparing my code to the descriptions and numerous hints. Not seeing it. I noticed many of the hints seemed to be in response to mistakes other students have made so was checking in to see if anyone has gone down this same path and has an idea.

Thanks for the response. It wasn’t helpful but at least I know you read this.

If found the bug. Will send you a PM with the details.