Set Weights dynamically for the inference session #13642
Unanswered
fedemarche
asked this question in
Other Q&A
Replies: 1 comment
-
We also would have great benefit if was possible to change at runtime as we do using set_weight of Keras models. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi.
I have a question regarding the InferenceSession.
I was wondering if it is possible to maintain the same InferenceSession instantiation and switch the underlying set of weights of the Model given an equal one but with just different kernel weights. In order so to dynamically switch weights at run time.
Is it possible currently?
There is any workaround?
is it possible at all?
Thank you
Beta Was this translation helpful? Give feedback.
All reactions