spVIPES

Shared-private Variational Inference with Product of Experts and Supervision

Getting started

Please refer to the documentation. In particular, the

• API documentation.

Installation

You need to have Python 3.9 or newer installed on your system.

PyTorch installation

We strongly recommend using spVIPES with GPU acceleration. In Linux, check your NVIDIA drivers running:

nvidia-smi

You can then install a compatible PyTorch version from https://pytorch.org/get-started/previous-versions/. For example if your CUDA drivers are version 11.3, you should install PyTorch v1.12.1 with the following command:

pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113

Make sure your torch installation can see your CUDA device to take full advantage of GPU acceleration by running:

import torch

torch.cuda.is_available()

This should return True if everything is installed correctly.

spVIPES installation

To install spVIPES:

1. Install the latest release of spVIPES from PyPI <https://pypi.org/project/spVIPES/>_:

pip install spVIPES

2. Install the latest development version:

pip install git+https://github.com/nrclaudio/spVIPES.git@main

Tutorials

To get started, please refer to the basic spVIPES tutorial.

Contact

If you found a bug, please use the issue tracker.

Citation

t.b.a