How could one extract the model's representation instead of getting a prediction? #127
Unanswered
DanielMaksimov
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hello, I am currently trying out Moirai to classify different multivariate time series.
In order to do so, I would have to get the representation of every input time series.
I tried to look up the code and especially the forward function, but I struggle to see when it is called and what I should change to get the hidden layer representation. I also thought about changing the Moirai module and remove all the layers after the norm layer, but I couldn't manage that either.
If anyone could give me pointers as to what particular section of code needs change that would really help.
Any piece of advice is welcome!
Beta Was this translation helpful? Give feedback.
All reactions