Wek 1 excercise 3 (jazz)

Course Q&A Deep Learning Specialization Sequence Models
1

Hi!

In jazz asignment, section 2A puts:

  • 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,:]

What s the alternative in keras? i didnt find any viable option, and var1 = array1[:,1,:] just work in the function.

I am missing something?

Thanks. Felipe.

2

It’s just a hint that you can do the slicing using [:,t,:]

3

Thanks. but there is no another option with keras, specific of keras and not included in numpy, right?

4

I think you can ignore that whole keras vs. numpy hint. There is nothing special or unusual about slicing using keras.