Fix Clean_name() to replace dots with underscores instead of erasing#10
Open
AdityaDRathore wants to merge 1 commit intoML4EP:devfrom
Open
Fix Clean_name() to replace dots with underscores instead of erasing#10AdityaDRathore wants to merge 1 commit intoML4EP:devfrom
AdityaDRathore wants to merge 1 commit intoML4EP:devfrom
Conversation
Clean_name() in SOFIE_common.cxx erases dot characters from tensor names instead of replacing them with a safe character. This causes tensor name collisions when parsing TorchScript models whose ONNX graphs contain dotted intermediate names (e.g., 'input.1' and 'input1' both map to 'input1'). Add std::replace for '.' -> '_' consistent with existing '-' -> '_' treatment. This makes 'input.1' -> 'input_1' (distinct from 'input1'). Got this issue during testing of root-project/root#21528. Reported in root-project/root#21527.
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Clean_name() in SOFIE_common.cxx erases dot characters from tensor names instead of replacing them with a safe character. This causes tensor name collisions when parsing TorchScript models whose ONNX graphs contain dotted intermediate names (e.g., 'input.1' and 'input1' both map to 'input1').
Add std::replace for '.' -> '' consistent with existing '-' -> '' treatment. This makes 'input.1' -> 'input_1' (distinct from 'input1').
Got this issue during testing of root-project/root#21528.
Reported in root-project/root#21527.