Question about djmodel in Week 1 Programming Assignment 3

Course Q&A Deep Learning Specialization Sequence Models
1

Regarding Exercise 1 - djmodel, I’m confused about instruction 2A and 2B:

2A. Select the 't' time-step vector from `X` .

* X has the shape (m, Tx, n_values).
* The shape of the 't' selection should be (n_values,).
* Recall that if you were implementing in numpy instead of Keras, 
you would extract a slice from a 3D numpy array like this:

var1 = array1[:,1,:]

2B. Reshape `x` to be (1, n_values).

Use the `reshaper()` layer. This is a function that takes the 
previous layer as its input argument.

I’m confused as to why the shape of the ‘t’ selection should be (n_values,) instead of (m, n_values), since the example given array1[:,1,:] returns a 2D array. I’m also not sure how the reshaper() handles batches.

2

The hint there is that you’re supposed to replace the ‘1’ with ‘t’, which is the iterator variable in the for-loop.

3

Is it correct to say that the output of reshaper() is a tensor with shape (m, 1, nvalues)?

4

That seems correct to me.