CODEWITHSUNDEEP
python-3.xkeras
KIC
KIC

Reputation: 6121

looking for a matrix inverse in keras

I want to implement a custom layer in keras. Unfortunately one part of the calculation requires the pseudo inverse (to solve x = (A'A)⁻¹A'b). Now I am missing the functionality of K.inverse. Is there a way I can solve an OLS equation using the keras backend?

def call(inputs, **kwargs):
    A = ...
    b = ...
    return K.inverse(K.transpose(A) @ A) @ K.transpose(A) @ b

Maybe I can read it back to numpy arrays do the inverse and then feed it back to a tensor or similar?

Upvotes: 2

Views: 708

Answers (1)

SajanGohil
SajanGohil

Reputation: 969

you can use tensorflow's inverse(tf.linalg.inv) inside a keras Lambda layer, that way, you don't have to create a custom layer, just a custom function.

Upvotes: 1

Related Questions