feat: add support for single-scale ViT models via adapter#1265
Open
ha405 wants to merge 1 commit intoqubvel-org:mainfrom
Open
feat: add support for single-scale ViT models via adapter#1265ha405 wants to merge 1 commit intoqubvel-org:mainfrom
ha405 wants to merge 1 commit intoqubvel-org:mainfrom
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR adds support for timm Vision Transformer (ViT) models by implementing a ViTFeatureAdapter #1244 to generate the multi-scale features required by SMP decoders.
Key Changes:
ViTFeatureAdapter: Converts single-scale features (e.g., 1/16) into a hierarchical scale (1/4, 1/8, 1/16, 1/32) using learnable up/down-sampling.
Auto-Detection:
TimmUniversalEncoder
now automatically detects and adapts ViT-style models.
Testing: Added
tests/encoders/test_vit_adapter.py
with full coverage for ViT architectures.
All existing and new encoder tests passed.