Setting Up Your Environment
Introduction¶
Learning Objectives¶
Hardware Requirements¶
Minimum Requirements¶
Recommended Requirements¶
Cloud Alternatives¶
Installing NVIDIA Drivers¶
macOS¶
Windows¶
Linux¶
sudo apt update
sudo ubuntu-drivers install
sudo apt install nvidia-driver-580
sudo dnf install https://download1.rpmfusion.org/free/fedora/rpmfusion-free-release-$(rpm -E %fedora).noarch.rpm \
https://download1.rpmfusion.org/nonfree/fedora/rpmfusion-nonfree-release-$(rpm -E %fedora).noarch.rpm
sudo dnf install akmod-nvidia
sudo pacman -S nvidia nvidia-utils
Verifying the Driver Installation¶
Installing Python with Miniconda¶
Windows Installation¶
curl https://repo.anaconda.com/miniconda/Miniconda3-latest-Windows-x86_64.exe -o .\miniconda.exe
start /wait "" .\miniconda.exe /S
del .\miniconda.exe
conda --version
python --version
macOS Installation¶
mkdir -p ~/miniconda3
curl https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-arm64.sh -o ~/miniconda3/miniconda.sh
bash ~/miniconda3/miniconda.sh -b -u -p ~/miniconda3
rm ~/miniconda3/miniconda.sh
source ~/miniconda3/bin/activate
conda init --all
conda --version
python --version
Linux Installation¶
mkdir -p ~/miniconda3
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh
bash ~/miniconda3/miniconda.sh -b -u -p ~/miniconda3
rm ~/miniconda3/miniconda.sh
source ~/miniconda3/bin/activate
conda init --all
conda --version
python --version
Creating a Conda Environment¶
conda create -n geoai python=3.13 -y
Installing GeoAI and PyTorch with GPU Support¶
Checking Your GPU¶
Installing GeoAI and PyTorch with CUDA¶
conda install -c conda-forge geoai segment-geospatial "pytorch=*=cuda*"
conda install -c conda-forge geoai segment-geospatial "pytorch=2.7.0=cuda128"
Installing GeoAI and PyTorch for CPU Only¶
conda install -c conda-forge geoai segment-geospatial
Verifying GPU Access¶
python -c "import torch; print(f'PyTorch {torch.__version__}'); print(f'CUDA available: {torch.cuda.is_available()}'); print(f'GPU: {torch.cuda.get_device_name(0)}' if torch.cuda.is_available() else 'CPU only')"
Installing uv as an Alternative Package Manager¶
curl -LsSf https://astral.sh/uv/install.sh | sh
source .venv/bin/activate
uv pip install geoai-py segment-geospatial jupyterlab
Setting Up Jupyter¶
import torch
import geoai
print(torch.cuda.is_available())
print(geoai.__version__)
Installing Visual Studio Code¶
Download and Installation¶
Recommended Extensions¶
code --install-extension ms-python.python
code --install-extension ms-toolsai.jupyter
code --install-extension charliermarsh.ruff
Verifying Your Setup¶
import sys
import importlib
print(f"Python version: {sys.version}\n")
# Check core packages
packages = {
"torch": "PyTorch",
"torchvision": "TorchVision",
"geoai": "GeoAI",
"leafmap": "Leafmap",
"geopandas": "GeoPandas",
"rasterio": "Rasterio",
"samgeo": "Segment-Geospatial",
"torchgeo": "TorchGeo",
}
for module_name, display_name in packages.items():
try:
mod = importlib.import_module(module_name)
version = getattr(mod, "__version__", "installed")
print(f" {display_name}: {version}")
except ImportError:
print(f" {display_name}: NOT FOUND")
# Check GPU availability
import torch
print(f"\nCUDA available: {torch.cuda.is_available()}")
if torch.cuda.is_available():
print(f"GPU device: {torch.cuda.get_device_name(0)}")
print(f"CUDA version: {torch.version.cuda}")
else:
print("Running in CPU-only mode.")
import leafmap
m = leafmap.Map(center=[40, -100], zoom=4)
m
Exercises¶
Exercise 1: Install and Verify Your Environment¶
Exercise 2: Check GPU Availability¶
Exercise 3: Explore Conda Environment Management¶
Exercise 4: Create an Interactive Map¶