How can I use tensorflow.python.ops in Keras?

Question

I'm looking to do SVD for a custom optimizer in Keras (specifically, I want to port the the Shampoo optimizer to Keras.

In Tensorflow, I would use tensorflow.python.ops.linalg_ops.svd(), however, there is no function like this in keras.backend.

Can SVD be carried out in a purely Keras setting, or can I somehow use the Tensorflow function directly (and if so, how)?

EDIT: Just for future reference, there actually exists a wrapper function allowing the direct use of a native tf optimizer in Keras:

import keras as ks
from tensorflow.contrib.opt import AdamWOptimizer

tfopt = AdamWOptimizer()
ksopt = ks.optimizers.TFOptimizer(tfopt)

Unfortunately though, it does not seem to work with the Shampoo optimizer specifically.

Answer 1

If you are using keras with a tensorflow backend, than keras backend is tensorflow.
This means that when you call a method from keras backend, it actually calls a method of tensorflow.

Therefore you could use both keras backend operations and tensorflow together and interchangeably.

For example, in the given code:

tensor = ...
m = K.mean(tensor)
...

I could change the line K.mean(tensor) to tf.mean(tensor)

tensor = ...
m = tf.mean(tensor)
...

So you can just use the tensorflow SVD operation as you would use it if it was a function of keras backend :)

For example if you would like to have

tensor = ...
res = K.some_submodule.svd(tensor)
...

Than you can instead just do

tensor = ...
res = tensorflow.python.ops.linalg_ops.svd(tensor)
...