jwave
A JAX-based research framework for differentiable and parallelizable acoustic simulations, running on CPU, GPU, and TPU.
What is jwave?
j-Wave is a library of simulators for acoustic applications, designed as a collection of modular blocks that can be easily integrated into machine learning pipelines. It is heavily inspired by and partially ports the established k-Wave simulator to JAX, enabling high-performance, hardware-accelerated acoustic simulations for research and development. The library prioritizes differentiability, just-in-time compilation, and execution on GPUs/TPUs.
Researchers and developers in acoustics, medical imaging (e.g., photoacoustics), and computational physics who need differentiable, GPU-accelerated simulation tools for integration with machine learning workflows. It is also suitable for those familiar with k-Wave seeking JAX-based performance and automatic differentiation capabilities.
Developers choose j-Wave for its seamless integration with JAX's ecosystem, offering automatic differentiation for gradient-based optimization and hardware acceleration across CPUs, GPUs, and TPUs without code changes. Its modular design and port of k-Wave functionality provide a familiar yet modernized tool for differentiable acoustic simulations.
Overview
A JAX-based research framework for differentiable and parallelizable acoustic simulations, on CPU, GPUs and TPUs
Use Cases
Best For
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
