[Week 3] Machine Translation: Code help

Course Q&A Deep Learning Specialization Sequence Models
1

For the model function I cannot figure out for the life of me why my code does not get the right output. I follow the instructions and keep getting this as my output:

[[‘InputLayer’, [(None, 30, 37)], 0], [‘Bidirectional’, (None, 30, 64), 17920], [‘Dense’, (None, 30, 10), 650, ‘tanh’], [‘Dense’, (None, 30, 1), 11, ‘relu’], [‘Activation’, (None, 30, 1), 0], [‘Dot’, (None, 1, 64), 0], [‘InputLayer’, [(None, 64)], 0], [‘InputLayer’, [(None, 64)], 0], [‘LSTM’, [(None, 64), (None, 64), (None, 64)], 33024, [(None, 1, 64), (None, 64), (None, 64)], ‘tanh’], [‘Dense’, (None, 11), 715, ‘softmax’]]

any hints or ideas on how to fix it?

3

Note, I deleted my previous reply, it was incorrect.

4

Does your one_step_attention() function use the “repeator()” helper function?

Because that’s what causes “RepeatVector()” to appear in the model, and it’s missing from your model summary.

Same for the “concatenator()” helper function.

5

yes they’re both in there. I passed all the tests for that one its just modelf that’s acting funny

6

Passing the tests in the notebook does not mean your code is perfect.

In fact the tests for one_step_attention() are very sparse.

7

Update for students who may find this thread:

Be sure that your one_step_attention() uses the correct arguments for each function call. The notebook’s test cases do not check for this.