# WangYueFt/dgcnn

Repository: https://github.com/WangYueFt/dgcnn
Canonical: https://ross.abutalabs.com/products/dgcnn
Language: Python
License: MIT
License Family: permissive
Last push: 2022-05-20T07:11:52+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3133, "days_push": 1566, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1846, forks 445 (observed 2026-08-28T04:05:43.466887+00:00)

## What it is
Author's reference implementation of Dynamic Graph CNN (DGCNN), a neural network module called EdgeConv for learning on 3D point clouds. It provides TensorFlow and PyTorch code for point cloud classification, semantic segmentation, and part segmentation.

## Use cases
- classify 3d point clouds with deep learning
- semantic segmentation of point clouds
- part segmentation of 3d shapes
- implement edgeconv in my model
- benchmark point cloud models on modelnet
- reproduce dgcnn paper results

## When to choose
- you need a proven baseline for point cloud classification or segmentation
- you want to use or extend the EdgeConv module
- you are reproducing the DGCNN paper or comparing against it

## When to avoid
- you need actively maintained code with recent dependency support
- you want a high-level API rather than research scripts
- your task is not point cloud based

## Facets
- artifact type: library
- maturity: maintenance
- function: deep-learning, machine-learning
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: point-clouds, edgeconv, pytorch, tensorflow, classification, segmentation, research-code, linux, gpu

## Member repositories
- WangYueFt/dgcnn (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:43.466887+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 2026-08-30T03:17:52.179063+00:00, confidence not recorded.
  - readme: https://github.com/WangYueFt/dgcnn (fetched 2026-08-28T04:05:43.466887+00:00, sha 03b120b06776)
- Data as of 2026-08-30T08:39:29.467469+00:00.