Commit 0cbec638 authored by Boris Bonev's avatar Boris Bonev
Browse files

Updates to Readme

parent b1bc9942
...@@ -36,11 +36,11 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. ...@@ -36,11 +36,11 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
<!-- ## What is torch-harmonics? --> <!-- ## What is torch-harmonics? -->
`torch_harmonics` is a differentiable implementation of the Spherical Harmonic transform in PyTorch. It uses quadrature rules to compute the projection onto the associated Legendre polynomials and FFTs for the projection onto the harmonic basis. This algorithm tends to outperform others with better asymptotic scaling for most practical purposes. `torch_harmonics` is a differentiable implementation of the Spherical Harmonic transform in PyTorch. It was originally implemented to enable Spherical Fourier Neural Operators (SFNO). It uses quadrature rules to compute the projection onto the associated Legendre polynomials and FFTs for the projection onto the harmonic basis. This algorithm tends to outperform others with better asymptotic scaling for most practical purposes.
`torch_harmonics` uses PyTorch primitives to implement these operations, making it fully differentiable. Moreover, the quadrature can be distributed onto multiple ranks making it spatially distributed. `torch_harmonics` uses PyTorch primitives to implement these operations, making it fully differentiable. Moreover, the quadrature can be distributed onto multiple ranks making it spatially distributed.
`torch_harmonics` has been used to implement a variety of differentiable PDE solvers which generated the animations below. Moreover, it has enabled the development of spherical Fourier Neural Operators (SFNOs). `torch_harmonics` has been used to implement a variety of differentiable PDE solvers which generated the animations below. Moreover, it has enabled the development of Spherical Fourier Neural Operators (SFNOs) [1].
<table border="0" cellspacing="0" cellpadding="0"> <table border="0" cellspacing="0" cellpadding="0">
...@@ -59,6 +59,12 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. ...@@ -59,6 +59,12 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
## Installation ## Installation
Download directyly from PyPI:
```
pip install torch-harmonics
```
Build in your environment using the Python package: Build in your environment using the Python package:
``` ```
...@@ -68,7 +74,6 @@ pip install ./torch_harmonics ...@@ -68,7 +74,6 @@ pip install ./torch_harmonics
Alternatively, use the Dockerfile to build your custom container after cloning: Alternatively, use the Dockerfile to build your custom container after cloning:
``` ```
git clone git@github.com:NVIDIA/torch-harmonics.git git clone git@github.com:NVIDIA/torch-harmonics.git
cd torch_harmonics cd torch_harmonics
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment