-
Notifications
You must be signed in to change notification settings - Fork 26
Updates documentation to improve clarity #10
Conversation
… and automation for the EO-1 project (#5) (#6) * Add initial project structure with configuration files, datasets, and example scripts * Update .gitignore to include new demo data paths, modify pre-commit configuration to exclude additional directories, and enhance README with more examples and installation instructions. Adjust dataset handling in pipeline configuration and dataset classes for improved training flexibility. Remove deprecated demo scripts and refine evaluation scripts for clarity. * Update .gitignore to include demo data paths, enhance README with additional examples, and modify Libero benchmark configuration files for improved clarity and structure. Adjust training scripts and evaluation settings across various experiments for consistency. * Remove fast testing workflow configuration from GitHub Actions * Update pre-commit configuration to refine exclusions, enhance README with structured examples, and remove unused imports in the EO model script. Co-authored-by: dlqu_0010 <[email protected]>
…d in eo1-dev branch
…y and performance.
…rations for improved clarity, and adjust training scripts for consistency across experiments. Enhance README documentation for better guidance on dataset preparation and training processes.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This pull request introduces several updates to documentation, configuration, and dataset examples to improve clarity, usability, and consistency for the EO-1 unified embodied foundation model.
Key changes include:
- Updated repository references to use the new "EO-1" name throughout documentation and setup instructions
- Enhanced documentation with detailed YAML examples, improved experiment descriptions, and clearer fine-tuning guidance
- Minor code cleanups and dataset modifications to support improved documentation
Reviewed Changes
Copilot reviewed 21 out of 31 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| tools/openloop.py | New tool for visualizing inference action trajectories with trained models |
| scripts/train.py | Updated import path and improved checkpoint naming format |
| scripts/test_vlm.py | New test script for vision-language model evaluation |
| scripts/eval_policy.py | Updated default paths and simplified model initialization |
| pyproject.toml | Added specific transformers version dependency |
| getting_started/2_train_finetune.ipynb | Complete rewrite with comprehensive training and fine-tuning documentation |
| experiments/*/README.md | Updated dataset download scripts and configuration examples |
| experiments/*/train.sh | Simplified training configurations and removed debug code |
| experiments/1_demo/data-demo.yaml | Enhanced with detailed multimodal and robot control configuration |
| eo/model/ files | Updated model imports and improved code organization |
| demo_data/refcoco/refcoco.jsonl | Updated dataset with new bounding box examples |
| README.md | Enhanced usage examples, updated repository references, and improved documentation structure |
| .github/settings.yml | Removed repository configuration file |
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
…dit checks for improved security analysis.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
Copilot reviewed 18 out of 25 changed files in this pull request and generated 3 comments.
Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.
EO-Robotics
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
check all files, testing passed
This pull request introduces several updates to documentation, configuration, and dataset examples to improve clarity, usability, and consistency for the EO-1 unified embodied foundation model. The most important changes focus on updating repository references, refining experiment and dataset instructions, enhancing fine-tuning guidance, and improving multimodal data configuration. There are also minor code and dataset cleanups to support these improvements.
Documentation and Configuration Improvements:
README.mdand setup instructions to use the newEO-1repository name, ensuring consistency for users cloning and setting up the project.README.md, clarifying the scope and purpose of each experiment and adding links to relevant scripts and directories for easier navigation. [1] [2]README.md, splitting action sampling and multimodal reasoning into separate steps and updating API calls for clarity and correctness.Repository and Dataset Maintenance:
.github/settings.ymlfile, eliminating repository-level configuration and branch protection rules that are now obsolete or managed elsewhere.demo_data/refcoco/refcoco.jsonldataset by removing duplicate and less relevant entries and adding new bounding box annotation examples for improved multimodal data diversity.Minor Code Cleanups:
eo/data/lerobot_dataset.pyto ensure it only prints when delta action mode is set, and fixed a commented-out line in thepost_processmethod to correctly sort feature keys. [1] [2] [3]Roadmap Updates:
README.mdto reflect the release of EO-1 pretraining, finetune scripts, and documentation, and clarified upcoming releases and planned features.