KeOps Logo
1.5
  • Why using KeOps?
  • Getting started
  • Changelog and Road map
  • Contributing

KeOps

  • Formulas and syntax
  • Autodiff engine

PyKeOps

  • Python bindings for KeOps
  • Tutorials, applications
  • Examples
    • Numpy API
      • Sum reduction
      • GPU Selection
      • Block-sparse reductions
      • Arg-K-Min reduction
      • KernelSolve reduction
      • KernelSolve reduction (with LazyTensors)
      • SumSoftMaxWeight reduction
      • SumSoftMaxWeight reduction (with LazyTensors)
    • Pytorch API
      • Advanced syntax in formulas
      • Anisotropic kernels
      • Sum reduction
      • LogSumExp reduction
      • Vectorial LogSumExp reduction
      • Multi GPU
      • Block-sparse reductions
      • GPU Selection
      • KernelSolve reduction
      • KernelSolve reduction (with LazyTensors)
      • SumSoftMaxWeight reduction
  • Benchmarks
  • API

RKeOps

  • R binding for KeOps

KeOpsLab

  • Matlab binding for KeOps

KeOps++

  • C++ API for KeOps

How does it work?

  • Autodiff and GPUs
  • Efficient CUDA schemes
  • Generic formulas
  • Conclusion
KeOps
  • »
  • Examples
  • Edit on GitHub

Examples¶

These short examples showcase the features of the pykeops.numpy and pykeops.torch modules, from automatic differentiation to block-sparse reductions.

Note

If you run a KeOps script for the first time, the internal engine may take a few minutes to compile all the relevant formulas. Do not worry: this work is done once and for all as KeOps stores the resulting shared object files (‘.so’) in a cache directory.

Numpy API¶

Sum reduction

Sum reduction¶

GPU Selection

GPU Selection¶

Block-sparse reductions

Block-sparse reductions¶

Arg-K-Min reduction

Arg-K-Min reduction¶

KernelSolve reduction

KernelSolve reduction¶

KernelSolve reduction (with LazyTensors)

KernelSolve reduction (with LazyTensors)¶

SumSoftMaxWeight reduction

SumSoftMaxWeight reduction¶

SumSoftMaxWeight reduction (with LazyTensors)

SumSoftMaxWeight reduction (with LazyTensors)¶

Pytorch API¶

Advanced syntax in formulas

Advanced syntax in formulas¶

Anisotropic kernels

Anisotropic kernels¶

Sum reduction

Sum reduction¶

LogSumExp reduction

LogSumExp reduction¶

Vectorial LogSumExp reduction

Vectorial LogSumExp reduction¶

Multi GPU

Multi GPU¶

Block-sparse reductions

Block-sparse reductions¶

GPU Selection

GPU Selection¶

KernelSolve reduction

KernelSolve reduction¶

KernelSolve reduction (with LazyTensors)

KernelSolve reduction (with LazyTensors)¶

SumSoftMaxWeight reduction

SumSoftMaxWeight reduction¶

Download all examples in Python source code: _auto_examples_python.zip

Download all examples in Jupyter notebooks: _auto_examples_jupyter.zip

Gallery generated by Sphinx-Gallery

Next Previous

© Copyright 2018-2021, Benjamin Charlier, Jean Feydy, Joan A. Glaunès. Last updated on Apr 12, 2021.