This package provides highly-efficient pairwise metrics for PyTorch.

torchpairwise is a collection of general purpose pairwise metric functions that behave similar to torch.cdist (which only implements $L_p$ distance). Instead, we offer a lot more metrics ported from other packages such as scipy.spatial.distance and sklearn.metrics.pairwise. For task-specific metrics (e.g. for evaluation of classification, regression, clustering, ...), you should be in the wrong place, please head to the TorchMetrics repo.

Written in torch's C++ API, the main differences are that our metrics:

• are all (except some boolean distances) differentiable with backward formulas manually derived, implemented, and verified with torch.autograd.gradcheck.
• are batched and can exploit GPU parallelization.
• can be integrated seamlessly within PyTorch-based projects, all functions are torch.jit.script-able.

These metrics are usually used to compute kernel for machine learning algorithms.

Furthermore, we provide a convenient wrapper function analoguous to torch.cdist excepts that it takes a string metric: str = "minkowski" indicating the desired metric to be used as the third argument, and extra metric-specific arguments are passed as keywords.

import torch, torchpairwise

# directed_hausdorff_distances is a pairwise 2d metric
x1 = torch.rand(10, 6, 3)
x2 = torch.rand(8, 5, 3)

generator = torch.Generator().manual_seed(1)
output = torchpairwise.cdist(x1, x2,
                             metric="directed_hausdorff",
                             shuffle=True,  # kwargs exclusive to directed_hausdorff
                             generator=generator)

Note that pairwise metrics on the second table are currently not allowed keys for cdist because they are not dist. We have a similar plan for pdist (which is equivalent to calling cdist(x1, x1) but avoid storing duplicated positions). However, that requires a total overhaul of existing C++/Cuda kernels and won't be available soon.

• Add more metrics (contact me or create a feature request issue).
• Add memory-efficient argkmin for retrieving pairwise neighbors' distances and indices without storing the whole pairwise distance matrix.
• Add an equivalence of torch.pdist with metric: str = "minkowski" argument.
• (Unlikely) Support sparse layouts.

• torch>=2.7.0,<2.8.0 (torch>=1.9.0 if compiled from source)

Since torch extensions are not forward compatible, I have to fix a maximum version for the PyPI package and regularly update it on GitHub (but I am not always available). If you use a different version of torch or your platform is not supported, please follow the instructions to install from source.

To install prebuilt wheels from torchpairwise, simply run:

pip install torchpairwise

Note that the Linux and Windows wheels in PyPI are compiled with torch==2.7.0 and Cuda 12.8. We only do a non-strict version checking and a warning will be raised if torch's and torchpairwise's Cuda versions do not match.

Make sure your machine has a C++17 and a Cuda compiler installed, then clone the repo and run:

pip install .

The basic usecase is very straight-forward if you are familiar with sklearn.metrics.pairwise and scipy.spatial.distance:

import numpy as np
import sklearn.metrics.pairwise as sklearn_pairwise

x1 = np.random.rand(10, 5)
x2 = np.random.rand(12, 5)

output = sklearn_pairwise.cosine_similarity(x1, x2)
print(output)

import torch
import torchpairwise

x1 = torch.rand(10, 5, device='cuda')
x2 = torch.rand(12, 5, device='cuda')

output = torchpairwise.cosine_similarity(x1, x2)
print(output)

import numpy as np
import scipy.spatial.distance as distance

x1 = np.random.binomial(
    1, p=0.6, size=(10, 5)).astype(np.bool_)
x2 = np.random.binomial(
    1, p=0.7, size=(12, 5)).astype(np.bool_)

output = distance.cdist(x1, x2, metric='jaccard')
print(output)

import torch
import torchpairwise

x1 = torch.bernoulli(
    torch.full((10, 5), fill_value=0.6, device='cuda')).to(torch.bool)
x2 = torch.bernoulli(
    torch.full((12, 5), fill_value=0.7, device='cuda')).to(torch.bool)

output = torchpairwise.jaccard_distances(x1, x2)
print(output)

Please check the tests folder where we will add more examples.

@software{hoang_nhat_tran_2025_14699364,
  author       = {Hoang-Nhat Tran},
  title        = {inspiros/torchpairwise: v0.2.0},
  month        = jan,
  year         = 2025,
  publisher    = {Zenodo},
  version      = {v0.2.0},
  doi          = {10.5281/zenodo.14699364},
  url          = {https://doi.org/10.5281/zenodo.14699364},
  swhid        = {swh:1:dir:14f42479843d299e136d10046bc7a12ea20da3ad
                   ;origin=https://doi.org/10.5281/zenodo.14699363;vi
                   sit=swh:1:snp:a3d823c1213301aca562bfd3d8c5a4a6d126
                   9bca;anchor=swh:1:rel:075a27f09a969eb7a1d8235b2264
                   1d8e347ab554;path=inspiros-torchpairwise-3af3663
                  },
}

The code is released under the MIT license. See LICENSE.txt for details.