# zju3dv/snake

Code for "Deep Snake for Real-Time Instance Segmentation" CVPR 2020 oral

Repository: https://github.com/zju3dv/snake
Canonical: https://ross.abutalabs.com/products/zju3dv-snake
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Last push: 2024-05-03T19:42:35+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2438, "days_push": 852, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1185, forks 228 (observed 2026-08-28T04:03:54.825989+00:00)

## What it is
Official research code for 'Deep Snake for Real-Time Instance Segmentation' (CVPR 2020 oral), implementing a deep contour-based instance segmentation model. It includes pretrained models, evaluation, and visualization scripts for Cityscapes, KINS (Kitti), and SBD datasets.

## Use cases
- run real-time instance segmentation on images
- segment object contours with deep snake algorithm
- evaluate instance segmentation on Cityscapes
- test pretrained models on Kitti instances dataset
- visualize segmentation results on street scenes
- reproduce CVPR 2020 paper results

## When to choose
- you need contour-based real-time instance segmentation
- you want to reproduce or build on the Deep Snake paper
- you work with Cityscapes or Kitti-style autonomous driving imagery

## When to avoid
- you need a production-ready segmentation pipeline with support
- you want a maintained general-purpose segmentation library
- you need a non-research license for commercial use

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, deep-learning
- platform: python
- tags: instance-segmentation, contour-model, cvpr-2020, research-code, object-detection, pytorch, linux, gpu

## Member repositories
- zju3dv/snake (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:54.825989+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 2026-08-30T06:24:13.484758+00:00, confidence not recorded.
  - readme: https://github.com/zju3dv/snake (fetched 2026-08-28T04:03:54.825989+00:00, sha b631f74c52fd)
- Data as of 2026-08-30T08:39:29.467469+00:00.