parametric_umap_pytorch

last update: 14/01/2022

---

Introduction

This is a simple reproduce of ParametricUMAP based on PyTorch. I mainly took two sorces for reference, umap library source code and parametric_umap tutorial.

---

Prerequisite

!pip install llvmlite>=0.34.0
!pip install --upgrade pynndescent
!pip install https://github.com/lmcinnes/umap/archive/0.5dev.zip
!pip install torch

---

Performance and Examples

Minist Dataset

Fashion Minist Dataset

---

Citation

@article {NBC2020,
    author = {Sainburg, Tim and McInnes, Leland and Gentner, Timothy Q.},
    title = {Parametric UMAP: learning embeddings with deep neural networks for representation and semi-supervised learning},
    journal = {ArXiv e-prints},
    archivePrefix = "arXiv",
    eprint = {2009.12981},
    primaryClass = "stat.ML",
    keywords = {Statistics - Machine Learning,
                Computer Science - Computational Geometry,
                Computer Science - Learning},
    year = 2020,
    }