Skip to content

This library offers an implementation of PyTorch’s preprocessing and inference steps using the OpenVINO API, effectively serving as an adapter for PyTorch.

License

Notifications You must be signed in to change notification settings

LucaTamSapienza/torch_adapter

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

53 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

torch_adapter

The purpose of this project is to provide an adapter for PyTorch, entirely using the OpenVINO API. For now, only the preprocessing and inference steps are available.

Requirments:

  • python >= 3.9
  • venv

Important

If you encounter any issues or believe some dependencies are missing, please don't hesitate to contact me. Also, ensure to double-check each command to confirm that everything is functioning as expected.

Installation

You can either choose to install torch_adapter from pip (preferred) or build it from source.

I suggest creating a virtual environment before installing torch_adapter.

pip install torch_adapter

Or, if you want to work on the code, just follow these steps:

git clone [email protected]:LucaTamSapienza/torch_adapter.git
cd torch_adapter
python3.9 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

You may need to export your PYTHONPATH to point to the torch_adapter directory:

export PYTHONPATH=$PYTHONPATH:path_to_torch_adapter

Now you can check if everything works by running pytest tests/

About

This library offers an implementation of PyTorch’s preprocessing and inference steps using the OpenVINO API, effectively serving as an adapter for PyTorch.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages