[Executor][Bugfix] Properly return and unflatten outputs from GraphExecutor #7604
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
masahi
approved these changes
Mar 6, 2021
|
thanks @altanh |
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
May 6, 2021
…ecutor (apache#7604) * properly return and unflatten outputs from GraphExecutor * lint * cleaner approach, not sure what I was thinking before * remove unused import * forgot copyto cpu * make solution even cleaner using iterator
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
May 11, 2021
…ecutor (apache#7604) * properly return and unflatten outputs from GraphExecutor * lint * cleaner approach, not sure what I was thinking before * remove unused import * forgot copyto cpu * make solution even cleaner using iterator
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Outdated suggestions cannot be applied.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.
Previously, if a graph module returned nested tuples (which end up being flattened per #6809), the GraphExecutor would not unflatten the result and instead naively returned only the first
kof the flattened outputs (wherek = original top-level tuple size). This PR fixes the output behavior of GraphExecutor to be the same as the VMExecutor ,by returning the outputs unflattened into nested lists respecting the original return type structure.cc @masahi @jroesch
I'm not super happy with the unflattening code, let me know if there's an easier/cleaner approach.Edit: I think it's clean enough now