Task-conditioned Helios model#181
Open
ryspark wants to merge 23 commits into
Open
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Main contribution is
TaskConditionedHelios, an alternative to theHeliosencoder that handles loading/forward pass of task embeddings. For now, these task embeddings are computed via a sentence embedding model on top of information extracted from each task'srslearnconfig. This depends on functionality from thisheliosPR, which may take some time to get merged, so merging this should be held off as well.Second contribution is a MoE-style ViT moved over from
rslearn, used for the decoder portion of a finetuned model.Lastly, adds high-level documentation for using the multitask code across
helios,rslearn, andrslearn_projects.Other changes include extra tests, a custom checkpointer that allows restoring partial checkpoints, and updates to
one_off_projects.