Modular ImageBind - Load modules based on selected modailites #138
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
…ofile memory usage
facebook-github-bot
added
the
CLA Signed
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Outdated suggestions cannot be applied.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.
Note
This PR depends on #136 and includes it's changes. Please review #136 first.
This pull request introduces a modular implementation of ImageBind, enabling selective loading of modality-specific components for more flexible and efficient multimodal inference.
imagebind/model_splitter.py, which splits the ImageBind model by modality and saves individual modality-specific weights for streamlined deployment.ModularImageBindclass inimagebind/models/modular_imagebind_model.py, allowing dynamic loading of only the required modalities during inference.