Skip to content

Installation Guide

uv Setup

We recommend using uv for high-performance environment management.

Minimal installation (library only)

Use this if you want to import plex-pipe into your own scripts.

# Create a virtual environment
uv venv --python 3.12

# Install for CPU-only
uv pip install "plex_pipe[all-cpu] @ git+https://github.com/StallaertLab/plex-pipe.git"

# OR: Install with GPU support (requires CUDA 12.6 compatible drivers)
uv pip install "plex_pipe[all-gpu] @ git+https://github.com/StallaertLab/plex-pipe.git"

Full setup (with example notebooks)

Use this if you want to run the provided analysis notebooks and explore the example workflows:

# Clone the repository to get the notebooks and source
git clone https://github.com/StallaertLab/plex-pipe.git
cd plex-pipe
# Build the environment based on your hardware:

# For CPU-only:
uv sync --extra all-cpu

# OR: Install with GPU support (requires CUDA 12.6 compatible drivers)
uv sync --extra all-gpu

Note

To avoid UnicodeDecodeError when running interactive notebooks on Windows, you must enable Python's UTF-8 mode. Create a file named .env in the project root with this line:

PYTHONUTF8=1

Conda Step-by-Step Setup

This guide covers the setup for PlexPipe with GPU support. Following these steps in order is critical to ensure that the segmentation engines (InstanSeg, Cellpose) can access your hardware acceleration.

Install Miniconda or Anaconda.

1. Create a Clean Environment

Open your terminal (PowerShell or Anaconda Prompt) and create a fresh environment.

conda create -n plex-pipe-gpu python=3.12 git -c conda-forge -y
conda activate plex-pipe-gpu

2. Identify and Install PyTorch (CUDA Check)

Before installing, you must check which CUDA version your driver supports. Run the following command:

nvidia-smi
Look at the top-right corner of the table for "CUDA Version: XX.X".

Install pytorch-cuda version that matches your CUDA version. For example for CUDA 12.8:

pip3 install torch torchvision --index-url https://download.pytorch.org/whl/cu128

3. Install Segmentation Libraries

pip install cellpose instanseg-torch

3. Install Napari

We install napari with the [all] extra to ensure the GUI and Qt backend are included, followed by instanseg.

pip install "napari[all]"

4. Clone and Install PlexPipe

Instead of installing directly, clone the repository to your computer so you can access the provided examples and notebooks.

cd analysis-pipelines

Clone the repository

git clone https://github.com/StallaertLab/plex-pipe.git
cd plex-pipe

pip install -e .