C5W3A1 - Passing Everything but Output is Wrong

Course Q&A Deep Learning Specialization Sequence Models
1

Within the Neural Translation Lab,
I’m passing all of the test cases, submitted and got 100%,
However in Exercise 3 my results seem to be incorrect when using the supplied weighted values:

source: 3 May 1979
output: 1111111111

source: 5 April 09
output: 2222222222

source: 21th of August 2016
output: 2222222222

source: Tue 10 Jul 2007
output: 2222222222

source: Saturday May 9 2018
output: 2222222222

source: March 3 2001
output: 2222222222

source: March 3rd 2001
output: 2222222222

source: 1 March 2001
output: 2222222222

I’m happy I seem to be passing things… but I also would like to see it output correct dates!

2

Please click my name and message your notebook as an attachment.

3

Thanks for bringing this up. Based on your topic, I’ve asked the staff to improve the assignment by checking for exact values.

Please remember that unit tests don’t guarantee bug free code. The staff have ensured that tests meets their standards.

That said, there is a bug in post_activation_LSTM_cell. Please read the docs about LSTM and fix the invocation parameters and capture the correct return values.