Skip to main content

Installation Guide

Complete installation guide for IGN LiDAR HD Processing Library. Get up and running in minutes with our step-by-step instructions.

📋 Requirements​

  • Python 3.8+ (Python 3.9-3.11 recommended)
  • pip package manager
  • Operating System: Windows, Linux, or macOS
Check Python Version
python --version  # Should show Python 3.8 or higher

🚀 Standard Installation​

pip install ign-lidar-hd

Verify Installation​

# Check version
ign-lidar-hd --version

# Test CLI
ign-lidar-hd --help

Installation Options​

# Standard installation (CPU only)
pip install ign-lidar-hd

# With RGB augmentation support
pip install ign-lidar-hd[rgb]

# With all features (excluding GPU)
pip install ign-lidar-hd[all]

⚡ GPU Acceleration (Optional)​

Performance Boost: 5-10x faster feature computation

Prerequisites​

  1. NVIDIA GPU with CUDA support
  2. CUDA Toolkit 11.0+ installed
  3. GPU Memory: 4GB+ recommended

Verify GPU setup:

nvidia-smi  # Should display GPU information

Install GPU Support​

# Install base package first
pip install ign-lidar-hd

# Then add CuPy for your CUDA version
pip install cupy-cuda11x  # For CUDA 11.x
# OR
pip install cupy-cuda12x  # For CUDA 12.x

Advanced GPU (RAPIDS cuML)​

For maximum performance:

# Using conda (recommended for RAPIDS)
conda create -n ign-lidar python=3.10
conda activate ign-lidar
pip install ign-lidar-hd
conda install -c rapidsai -c conda-forge -c nvidia cuml

🔧 Development Installation​

From Source​

git clone https://github.com/sducournau/IGN_LIDAR_HD_DATASET.git
cd IGN_LIDAR_HD_DATASET
pip install -e .

With Development Dependencies​

pip install -e .[dev,test,docs]

🐍 Virtual Environments​

Using venv (Built-in)​

python -m venv ign-lidar-env
source ign-lidar-env/bin/activate  # Linux/macOS
# or
ign-lidar-env\Scripts\activate     # Windows
pip install ign-lidar-hd

Using conda​

conda create -n ign-lidar python=3.10
conda activate ign-lidar
pip install ign-lidar-hd

✅ Verify Installation​

Basic Verification​

# Test Python imports
import ign_lidar
print(f"IGN LiDAR HD version: {ign_lidar.__version__}")

# Test main classes
from ign_lidar import LiDARProcessor, IGNLiDARDownloader
print("✓ Installation successful!")

GPU Verification​

# Check GPU availability
from ign_lidar.features_gpu import GPU_AVAILABLE, CUML_AVAILABLE

print(f"GPU (CuPy) available: {GPU_AVAILABLE}")
print(f"RAPIDS cuML available: {CUML_AVAILABLE}")

if GPU_AVAILABLE:
    print("✓ GPU acceleration enabled!")
else:
    print("⚠️  GPU not detected - using CPU")

🔧 Troubleshooting​

Command Not Found​

# If ign-lidar-hd command is not found, try:
python -m ign_lidar.cli --help

Import Errors​

# Reinstall in development mode
pip install -e .

# Check Python path
python -c "import sys; print('\n'.join(sys.path))"

GPU Issues​

# Test CUDA availability
python -c "import cupy; print('CUDA works!')"

# Check CUDA version
nvcc --version

🚀 Next Steps​

Now that you're installed:

  1. 📖 Follow the Quick Start Guide
  2. 🖥️ Try Basic Usage Examples
  3. ⚡ Configure GPU acceleration (if available)
  4. 📋 Explore Pipeline Configuration

💡 Need Help?​