# erikwijmans/Pointnet2_PyTorch

PyTorch implementation of Pointnet2/Pointnet++

Repository: https://github.com/erikwijmans/Pointnet2_PyTorch
Canonical: https://ross.abutalabs.com/products/pointnet2_pytorch
Language: Python
License: Unlicense
License Family: permissive
Topics: pointnet2, pytorch, point-cloud, pytorch-lightning, hydra
Last push: 2026-05-18T21:41:21+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 83, release rhythm 8, longevity 100
- inputs: {"age_days": 3172, "days_push": 107, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1812, forks 399 (observed 2026-08-28T04:05:39.653483+00:00)

## What it is
A PyTorch implementation of Pointnet2/Pointnet++ for deep learning on point clouds, including custom CUDA ops for GPU-only execution. It supports multi-GPU training and example classification and semantic segmentation training scripts built with PyTorch Lightning and Hydra.

## Use cases
- train pointnet++ models in pytorch
- classify 3d point clouds with deep learning
- semantic segmentation of point clouds
- run pointnet2 cuda ops in pytorch
- multi-gpu training of point cloud networks

## When to choose
- you need a PyTorch port of Pointnet++ with CUDA ops
- you want reference implementations of classification or semantic segmentation on point clouds
- you are pinned to older PyTorch versions (1.4/1.5) where this was tested

## When to avoid
- you need maintained code or issue support - the project is explicitly unmaintained
- you lack a CUDA GPU - custom ops are GPU-only
- you need recent PyTorch compatibility - it was tested only up to PyTorch 1.5

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning
- domain: machine-learning, computer-vision
- platform: python
- tags: point-cloud, pointnet2, pytorch, cuda-ops, semantic-segmentation, point-cloud-classification, gpu, linux

## Member repositories
- erikwijmans/Pointnet2_PyTorch (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:39.653483+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:21:12.806280+00:00, confidence not recorded.
  - readme: https://github.com/erikwijmans/Pointnet2_PyTorch (fetched 2026-08-28T04:05:39.653483+00:00, sha b5f3c626bb40)
- Data as of 2026-08-30T08:39:29.467469+00:00.