Course 5, Week 3, Assignment 1, Exercise 2 summary(model)

Course Q&A Deep Learning Specialization Sequence Models
1

I get an error because my summary(model) does not match what is expected:
[[‘InputLayer’, [(None, 64)], 0], [‘InputLayer’, [(None, 30, 37)], 0], [‘RepeatVector’, (None, 30, 64), 0, 30], [‘Bidirectional’, (None, 30, 64), 17920], [‘Concatenate’, (None, 30, 128), 0], [‘Dense’, (None, 30, 10), 1290, ‘tanh’], [‘Dense’, (None, 30, 1), 11, ‘relu’], [‘Activation’, (None, 30, 1), 0], [‘Dot’, (None, 1, 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’]]

My first input is X which has shape (None, 30, 37) and then my next two inputs are s0, c0 which have shape (None, 64) so I don’t understand why the summary is switching the order of inputs. Also, my model calls Bidirectional before RepeatVector (in one_step_attention), so I don’t understand why those are also switched in my model summary. Any help would be appreciated.

2

I figured out the issue-- in one_step_attention, I didn’t read the following important comment, and switched the order of these:

For grading purposes, please list ‘a’ first and ‘s_prev’ second, in this order.