You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The graph executor currently doesn't allow modules to have state. If we have a tensor where the outer dimension is time, then we are forced to run all the frames through each node, like so:
tensor= ... # Time x Batch x ...module(tensor)
We might want to support iterative application, which is for instance necessary for real-time modules:
tensor= ... # Time x Batch x ...state=Noneforframeintensor:
out, new_state=module(frame)
This is the (functional) model Norse is following, so we would have to make sure this also works for libraries with mutable state (where the state variable is not explicitly passed).
The text was updated successfully, but these errors were encountered:
Jegp
linked a pull request
Oct 21, 2023
that will
close
this issue
The graph executor currently doesn't allow modules to have state. If we have a tensor where the outer dimension is time, then we are forced to run all the frames through each node, like so:
We might want to support iterative application, which is for instance necessary for real-time modules:
This is the (functional) model Norse is following, so we would have to make sure this also works for libraries with mutable state (where the
state
variable is not explicitly passed).The text was updated successfully, but these errors were encountered: