Skip to content

README.md

Latest commit

 

History

History
71 lines (56 loc) · 3.25 KB

README.md

File metadata and controls

71 lines (56 loc) · 3.25 KB

ACT: Action Chunking with Transformers

ACT (Action Chunking with Transformers) is a robotic policy model that is trained to predict the next chunk of actions that the robotic hand is expected to perform.

This is based on the implementation of ACT found here. This repository contains scripts for optimized on-device export suitable to run on Qualcomm® devices. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Setup

1. Install System-Level Dependencies

Linux

sudo apt install libegl-dev

Windows

You can export this model on windows without extra system dependencies. To run the demo, you will need to install LibEGL libraries. Options include ANGLE or Mesa3D. This is not a well-tested path; we recommend using WSL or a Linux machine for the demo.

2. Install the package

Install the package via pip:

# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
pip install dm_control==1.0.36 --no-deps
pip install "qai-hub-models[act]"

3. Configure Qualcomm® AI Hub Workbench

Sign-in to Qualcomm® AI Hub Workbench with your Qualcomm® ID. Once signed in navigate to Account -> Settings -> API Token.

With this API token, you can configure your client to run models on the cloud hosted devices.

qai-hub configure --api_token API_TOKEN

Navigate to docs for more information.

Run CLI Demo

Run the following simple CLI demo to verify the model is working end to end:

python -m qai_hub_models.models.act.demo

More details on the CLI tool can be found with the --help option. See demo.py for sample usage of the model including pre/post processing scripts. Please refer to our general instructions on using models for more usage instructions.

By default, the demo will run locally in PyTorch. Pass --eval-mode on-device to the demo script to run the model on a cloud-hosted target device.

Export for on-device deployment

To run the model on Qualcomm® devices, you must export the model for use with an edge runtime such as TensorFlow Lite, ONNX Runtime, or Qualcomm AI Engine Direct. Use the following command to export the model:

python -m qai_hub_models.models.act.export

Additional options are documented with the --help option.

License

  • The license for the original implementation of ACT can be found here.

References

Community