how to get a Cartesian product

[saintthor]

Please make sure that the boxes below are checked before you submit your issue.
If your issue is an implementation question, please ask your question on StackOverflow or on the Keras Slack channel instead of opening a GitHub issue.

Thank you!

• Check that you are up-to-date with the master branch of Keras. You can update with:
  pip install git+git://github.com/keras-team/keras.git --upgrade --no-deps

• Check that your version of TensorFlow is up-to-date. The installation instructions can be found here.

• Provide a link to a GitHub Gist of a Python script that can reproduce your issue (or just copy the script here if it is short).

[saintthor]

I need a keras layer to do such calculation:

def f( [a, b], [c, d] ):
return [ac, ad, bc, bd]

what is the easiest way?

[paulbonnard]

use https://www.tensorflow.org/api_docs/python/tf/math/multiply

[kashyapraval]

https://www.tensorflow.org/api_docs/python/tf/math/multiply

that would rather return [ac, bd].
matrix multiplication and extending rows there after should help.
[a, b].T X [c, d] that returns a matrix of shape(2,2)
X stands for matrix multiplication

[saintthor]

https://www.tensorflow.org/api_docs/python/tf/math/multiply

that would rather return [ac, bd].
matrix multiplication and extending rows there after should help.
[a, b].T X [c, d] that returns a matrix of shape(2,2)
X stands for matrix multiplication

thanks. I use K.batch_dot( [[a], [b]], [c,d] ) to do this. is it the easiest way?