POT:Python最优传输
gromov-wasserstein 开源项目推荐(11 个)
gromov-wasserstein 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 全部 11
GitHub 共 11 个仓库,已全部展示Optimal transport tools implemented with the JAX framework, to solve large scale matching problems of any flavor.
Official PyTorch implementation of the ICCV 2023 paper: From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection.
Improving word mover’s distance by leveraging self-attention matrix (Published in EMNLP 2023 Findings)
TorchGW — Fast Sampled Gromov-Wasserstein optimal transport in pure PyTorch. GPU-accelerated with Triton fused Sinkhorn kernels. 3-175x faster than POT.
该项目在 GitHub 上没有填写描述
Inexact projected gradient for Gromov-Wasserstein optimal transport, with reproducible paper examples.
Registration-free supervised tensor-PLS (RAW-PLS) for unaligned multiparametric MRI: each scan is a point cloud transported onto a learnable cross-subject template via supervised fused Gromov-Wasserstein, then read out with a low-rank geometry head. No registration, interpretable, with identifiability and consistency guarantees. On BraTS.
Zero-Shot Cross-Subject BCI Foundation Transport & Continuous Multi-Modal Biometric Liveness Mesh. Gromov-Wasserstein manifold alignment, sub-15mW spike sparsification, and P300/optical jitter anti-spoofing.
Official Implementation of 'Joint Metric Space Embedding by Unbalanced OT with Gromov-Wasserstein Marginal Penalization'
(GSI'25) Gromov Wasserstein Multi-Dimensional Scaling
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 11 个项目;原始页面见 https://github.com/topics/gromov-wasserstein。
- 该话题在 GitHub 上共有 11 个仓库, 本站收录的是其中最热门的 11 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 11 个项目累计 3727 Star,覆盖 3 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。