Skip to content

Koorye/Inspire-FAST

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Inspire-FAST

Official implementation of the paper "InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning".

Note: We are doing our best to improve this work. If you have any questions or suggestions, please feel free to create an issue in this repo or contact us at shihan.wu.koorye@outlook.com.

[Project] [ArXiv] [PDF] [Inspire]

News

  • 🔥May 23, 2025: Our paper has been updated for better clarity and readability. The optimized version is now available on arXiv.
  • 🔥May 21, 2025: The code is released and the paper is now available on arXiv.

Model Checkpoints

Model Dataset Checkpoint
FAST Libero90 Download
InspireVLA-FAST Libero90 Download

Installation

  1. Clone the repository.
git clone https://github.com/Koorye/Inspire-FAST.git
  1. Install dependencies.
cd LIBERO
pip install -r requirements.txt
pip install -e .
cd ..

cd lerobot-v2
pip install -e .
cd ..

pip install -e .

Evaluation with Pretrained Checkpoints

  1. Download pretrained checkpoints.
huggingface-cli download InspireVLA/fast-libero-90
huggingface-cli download InspireVLA/fast-inspire-libero-90
  1. Run evaluation.
task_suite_names=(
    libero_90 
    libero_goal 
    libero_spatial 
    libero_object 
    libero_10
)

for task_suite_name in "${task_suite_names[@]}"; do
    XLA_PYTHON_CLIENT_PREALLOCATE=false python scripts/parallel_libero_evaluator.py \
        --config-name your_config_name \
        --checkpoint-dir your/checkpoint/path \
        --task-suite-name $task_suite_name
done

Training Your Own Checkpoints

  1. Prepare your dataset.

See Dataset Preparation.

  1. Update the config file src/training/config.py, changing each repo_id in the _CONFIGS list.

  2. Train Baseline.

XLA_PYTHON_CLIENT_MEM_FRACTION=0.9 python scripts/train.py \
    pi0_fast_libero \
    --exp-name=pi0_fast_libero \
    --resume
XLA_PYTHON_CLIENT_MEM_FRACTION=0.9 python scripts/train.py \
    pi0_fast_real \
    --exp-name=pi0_fast_real \
    --resume
  1. Train Inspire on LIBERO.
XLA_PYTHON_CLIENT_MEM_FRACTION=0.9 python scripts/train_fast_vqa_libero.py \
    pi0_fast_libero \
    --exp-name=pi0_fast_libero \
    --resume
  1. Train Inspire on real-world.
XLA_PYTHON_CLIENT_MEM_FRACTION=0.9 python scripts/train_fast_vqa_real.py \
    pi0_fast_real \
    --exp-name=pi0_fast_real \
    --resume

Acknowledgements

Our work is built upon the following open-source projects: LIBERO, MiniVLA, Pi-0. We thank the authors for releasing their code. If you use our model and code, please consider citing these works as well.

About

Official implemetation of the paper "InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published