Neural Machine Translation with Attention Error

Course Q&A Deep Learning Specialization Sequence Models
1

When building the modelf function the dimensions of my first two input layers seem to be backwards. I followed the instructions and cannot see where I’m going wrong.

2

Did you modify the code in the cell after the modelf() function, where it calls model = target(…)?

It should look like this:

# UNIT TEST
from test_utils import *

def modelf_test(target):
    m = 10
    Tx = 30
    n_a = 32
    n_s = 64
    len_human_vocab = 37
    len_machine_vocab = 11
    
    
    model = target(Tx, Ty, n_a, n_s, len_human_vocab, len_machine_vocab)
3

I have not. The code matches what you posted.

4

The output is slightly odd… “Repeat Vector” is in front of “Bidirectional”.
The most possible case is that you switched the first and second parameter for “concatenate” in one_step_attention(). The order is important. So, please revisit your implementation of “one_step_attention()”.

By the way, pasting your code in here is not recommended. Please remove them, thank you.