xitorch
is a PyTorch-based library of differentiable functions and functionals that
can be widely used in scientific computing applications as well as deep learning.
The documentation can be found at: https://xitorch.readthedocs.io/
linalg
: Linear algebra and sparse linear algebra moduleoptimize
: Optimization and root finder moduleintegrate
: Quadrature and integration module
- python 3.6 or higher
- pytorch 1.6 or higher (install here)
After fulfilling all the requirements, type the commands below to install xitorch
git clone https://github.com/xitorch/xitorch/
cd xitorch
python -m pip install -e .
Neural mirror design (example 01):
Initial velocity optimization in molecular dynamics (example 02):