Repository files navigation

Meent is an Electromagnetic(EM) simulation package with Python, composed of three main parts:

• Modeling
• EM simulation
• Optimization

Meent provides three libraries as a backend:

• NumPy
  • The fundamental package for scientific computing with Python
  • Easy and lean to use
• JAX
  • Autograd and XLA, brought together for high-performance machine learning research.
• PyTorch
  • A Python package that provides two high-level features: Tensor computation with strong GPU acceleration and Deep neural networks built on a tape-based autograd system

*In 32bit operation, operations on numbers of 8>= digit difference fail without warning or error.Use only when you do understand what you are doing.
**As of now(2023.03.19), GPU-native Eigendecomposition is not implemented in JAX and PyTorch.It's enforced to run on CPUs and send back to GPUs.

Numpy is simple and light to use. Suggested as a baseline with small ~ medium scale optics problem.
JAX and PyTorch is recommended for cases having large scale or optimization part.
If you want parallelized computing with multiple devices(e.g., GPUs), JAX is ready for that.
But since JAX does jit compilation, it takes much time at the first run.

pip install meent

JAX and PyTorch is needed for advanced utilization.

importmeent# backend 0 = Numpy# backend 1 = JAX# backend 2 = PyTorchbackend=1mee=meent.call_mee(backend=backend, ...)

Jupyter notebooks are prepared intutorials to give a brief introduction.

Comprehensive examples of computational optics with Meent can be found inexamples folder.

To cite this repository:

@article{kim2024meent,title={Meent: Differentiable Electromagnetic Simulator for Machine Learning},author={Kim, Yongha and Jung, Anthony W. and Kim, Sanmun and            Octavian, Kevin and Heo, Doyoung and Park, Chaejin and            Shin, Jeongmin and Nam, Sunghyun and Park, Chanhyung and            Park, Juho and Han, Sangjun and Lee, Jinmyoung and            Kim, Seolho and Jang, Min Seok and Park, Chan Y.},journal={arXiv preprint arXiv:2406.12904},year={2024}}