Repository navigation
Add GR00T notebook and fix LIBERO checkpoint comparisons - #36
Merged
Merged
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds the supplied GR00T N1.7 Jupyter lab under
notebooks/gr00t/, with an index that puts it alongside the ABC/XDOF notebook and a dedicated Python/kernel setup guide.The notebook now selects a matching evaluation task for each LIBERO suite. Its default learning run saves checkpoints at steps 50 and 100; command generation and plotting reject missing checkpoints or two paths resolving to the same checkpoint. The CPU/data path remains usable without checkpoints, and GPU commands remain explicitly manual. Generated files are ignored and the notebook ships without outputs.
The required regression run also exposed an ABC decoder incompatibility with FFmpeg 9. Replacing the removed
-vsync 0option with-fps_mode passthroughrestores frame decoding without changing frame-order semantics.Validation: notebook schema and all 39 code cells checked; 20 new regression cases cover suite selection, checkpoint scheduling and comparison guards; all 39 focused notebook/conversion tests pass, including real FFmpeg decoding. Installed formatting, security, secret and documentation hooks plus the full Python suite run before publication. No GR00T training or GPU rollout was executed, and no model-performance result is claimed.