onnx: implement LSTM op #2268
Merged
onnx: implement LSTM op #2268
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
ah, I just found the LSTM implementation in candle-nn, don't know how I missed it before, I think I'll try to use that instead of the one here. |
use candle-nn LSTM
|
Thanks and sorry for the delay. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I'm not sure if, at this point, the simple_eval is the right place to put all this code. It's the thing I implemented, but I could use some direction from code maintainer where this makes sense to add to the codebase.
It was a bit trickier to test this as the docs don't really give inputs/outputs, their tests simply match against an alternative implementation of LSTM. So I've done basically the same thing, where I checked that the implementation here matches the output of pytorch's LSTM node.