# facebookresearch/SparseConvNet

Submanifold sparse convolutional networks

Repository: https://github.com/facebookresearch/SparseConvNet
Canonical: https://ross.abutalabs.com/products/sparseconvnet
Homepage: https://github.com/facebookresearch/SparseConvNet
Language: C++
License: NOASSERTION
License Family: other
Archived: true
Last push: 2024-01-09T01:47:27+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3344, "days_push": 968, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2145, forks 334 (observed 2026-08-28T04:06:18.709923+00:00)

## What it is
A PyTorch library for training Submanifold Sparse Convolutional Networks, providing spatially-sparse convolutions that operate efficiently on sparse input data. It supports 1-10 dimensional inputs and enables computationally efficient VGG/ResNet/DenseNet-style networks where active sites remain unchanged across layers.

## Use cases
- train sparse convolutional networks on 3D point clouds
- build efficient ConvNets on sparse high-dimensional data
- process handwriting or line-like 2D data with sparse convolutions
- run semantic segmentation on LiDAR scans
- apply sparse convolutions to space-time (3+1)D data

## When to choose
- your input data is spatially sparse, such as point clouds or sparse voxel grids
- you need submanifold convolutions to keep active-site counts constant across layers
- you want a PyTorch-integrated sparse convolution library

## When to avoid
- you need active maintenance or new feature development, as the repository was archived in March 2025
- your data is dense and standard dense convolutions are efficient enough
- you need a library with broad community support and recent updates

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, image-processing
- domain: deep-learning, machine-learning, computer-vision
- platform: python
- tags: sparse-convolution, pytorch, submanifold-convolution, 3d-point-clouds, convolutional-networks, linux, macos, gpu

## Member repositories
- facebookresearch/SparseConvNet (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:18.709923+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 2026-08-30T02:51:12.170046+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/SparseConvNet (fetched 2026-08-28T04:06:18.709923+00:00, sha 78e99246a0b3)
  - homepage: https://github.com/facebookresearch/SparseConvNet (fetched 2026-08-29T10:31:08.993049+00:00, sha 43b522ac5479)
- Data as of 2026-08-30T08:39:29.467469+00:00.