English

CodeJeNN: A simple C++ neural network generator for physics applications

Computational Physics 2026-07-02 v1 Machine Learning

Abstract

Machine learning has shown speedups for numerical methods in physics applications, but integrating Python-based libraries into high-performance C++ solvers creates performance bottlenecks. We present CodeJeNN, which bridges this gap by auto-generating self-contained C++ code from trained Keras models for inference. This eliminates external dependencies through minimal inlined functions, allowing seamless integration into existing frameworks. We describe the Keras-to-C++ workflow, supported architectures, and limitations. CodeJeNN is demonstrated through inference benchmarks against Keras in eager and JIT modes and a CFD test case modeling viscosity in a hydrogen-air mixing layer, showing speedups without sacrificing accuracy.

Cite

@article{arxiv.2607.02746,
  title  = {CodeJeNN: A simple C++ neural network generator for physics applications},
  author = {Jay Arcities and Pavel Popov and Eric J Ching and Kamal Viswanath and Ryan F Johnson},
  journal= {arXiv preprint arXiv:2607.02746},
  year   = {2026}
}