Add swinv2 to NormalizedConfigManager mapping - #2462
Open
RudrenduPaul wants to merge 1 commit into
Open
Conversation
Swinv2Config exposes image_size and num_channels like other vision configs (e.g. donut-swin), so map it to NormalizedVisionConfig to fix the KeyError raised when using swinv2 with ONNX Runtime optimization. Fixes huggingface#2140
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
Fixes #2140.
NormalizedConfigManagerraises aKeyErrorfor theswinv2model typebecause it is missing from the
_confmapping inoptimum/utils/normalized_config.py. This breaks ONNX Runtimeoptimization for Swin Transformer V2 models.
This PR adds a single entry mapping
"swinv2"toNormalizedVisionConfig,following the same pattern already used for the sibling
"donut-swin"entry.
Swinv2Configexposesimage_sizeandnum_channelsattributes(see
transformers/models/swinv2/configuration_swinv2.py), which isexactly what
NormalizedVisionConfigexpects (IMAGE_SIZE = "image_size",NUM_CHANNELS = "num_channels"), so no new normalized config class isneeded.
Change
Single-line addition, alphabetically ordered per the file's contribution
convention:
Before submitting
Swinv2Configattributes (image_size,num_channels)match
NormalizedVisionConfigexpectationsruff checkon the modified file — all checks passedoptimum/utils/normalized_config.pyCloses #2140