Installation

Prerequisites

• Python >= 3.12
• CUDA-capable GPU (recommended for performance)

Install from GitHub

pip install git+https://github.com/singer-yang/DeepLens.git

Development Install

git clone https://github.com/singer-yang/DeepLens.git
cd DeepLens
pip install -e .

Conda Environment (Recommended)

conda create -n deeplens python=3.12
conda activate deeplens
pip install -e .

Verify GPU Support

import torch
print(torch.cuda.is_available())  # Should print True

Run the GeoLens Demo

The root-level demo loads a geometric lens, runs layout/spot/MTF/distortion analysis, and renders a chart with both ray tracing and PSF-map simulation:

python 0_hello_geolens.py

Troubleshooting

torch.cuda.is_available() returns False: Install PyTorch with CUDA support following pytorch.org.

Import errors after install: Make sure you're using Python >= 3.12:

python --version

Missing dependencies: The package installs all required dependencies automatically. If you encounter issues, try:

pip install -e ".[dev]"