Installation

Requirements

FADVI requires Python 3.11 or higher and the following dependencies:

  • scvi-tools >= 1.3.0

  • PyTorch >= 1.8.0

  • NumPy

  • Pandas

  • scanpy

  • anndata

Installation Methods

From Source

To install the latest development version:

git clone https://github.com/liuwd15/fadvi.git
cd fadvi
pip install -e .

Verify Installation

To verify that FADVI is installed correctly:

import fadvi
print(fadvi.__version__)

If you encounter any issues, please open an issue on our GitHub repository.

GPU Support

FADVI automatically detects and uses GPU acceleration when available. To check if GPU is being used:

import torch
print(f"CUDA available: {torch.cuda.is_available()}")
print(f"Number of GPUs: {torch.cuda.device_count()}")

For optimal performance with large datasets, we recommend using a GPU with at least 8GB of memory.