# opencv/opencv_zoo

Model Zoo For OpenCV DNN and Benchmarks.

Repository: https://github.com/opencv/opencv_zoo
Canonical: https://ross.abutalabs.com/products/opencv_zoo
Language: Python
License: Apache-2.0
License Family: permissive
Topics: opencv, deep-learning, model-zoo, benchmark
Last push: 2026-05-28T14:46:51+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 84, release rhythm 8, longevity 100
- inputs: {"age_days": 1861, "days_push": 97, "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 1034, forks 299 (observed 2026-08-28T04:03:18.484955+00:00)

## What it is
A collection of pre-trained computer vision models tuned for OpenCV's DNN inference module, accompanied by benchmarking tools for various hardware platforms. It provides demo scripts and performance measurements across x86 CPUs, ARM boards, NPUs, and GPUs.

## Use cases
- run face detection with opencv dnn
- benchmark deep learning models on raspberry pi
- find pretrained models for opencv inference
- run object detection on embedded arm boards
- compare model inference speed across npu hardware
- deploy computer vision models without pytorch or tensorflow

## When to choose
- you want lightweight inference using only OpenCV without heavy ML frameworks
- you need benchmark data for vision models on edge devices like Jetson or Raspberry Pi
- you want ready-to-use pretrained models with demo scripts for common vision tasks

## When to avoid
- you need to train or fine-tune models rather than run inference
- you require models beyond the curated vision tasks included in the zoo
- you need production model serving with REST APIs rather than library-style inference

## Facets
- artifact type: dataset
- maturity: active
- function: machine-learning, deep-learning, computer-vision, image-processing, benchmarking, llm-inference
- domain: computer-vision, machine-learning, deep-learning, developer-tools, performance
- platform: python, cross-platform, windows, embedded
- tags: opencv-dnn, model-zoo, pretrained-models, inference, edge-devices, npu, face-detection, object-detection, quantization, linux, macos, gpu

## Member repositories
- opencv/opencv_zoo (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:18.484955+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 2026-08-30T07:06:34.980612+00:00, confidence not recorded.
  - readme: https://github.com/opencv/opencv_zoo (fetched 2026-08-28T04:03:18.484955+00:00, sha 4f7e6adb2ff0)
- Data as of 2026-08-30T08:39:29.467469+00:00.