# microsoft/computervision-recipes

Best Practices, code samples, and documentation for Computer Vision.

Repository: https://github.com/microsoft/computervision-recipes
Canonical: https://ross.abutalabs.com/products/computervision-recipes
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: machine-learning, computer-vision, deep-learning, python, jupyter-notebook, operationalization, kubernetes, azure, microsoft, data-science, tutorial, artificial-intelligence, image-classification, image-processing, similarity, object-detection, convolutional-neural-networks
Last push: 2024-02-16T23:55:05+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2760, "days_push": 929, "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 9879, forks 1210 (observed 2026-08-28T04:10:37.613201+00:00)

## What it is
A Microsoft repository of Jupyter notebook examples, utility functions, and best-practice guidelines for building computer vision systems with PyTorch. It covers scenarios like image classification, object detection, image similarity, and action recognition, including cloud training and deployment guidance.

## Use cases
- learn computer vision with pytorch notebooks
- train an image classification model
- build an object detection pipeline
- compute image similarity for search
- deploy computer vision models to the cloud
- best practices for operationalizing cv models
- action recognition from video

## When to choose
- you want curated, example-driven guidance for common CV tasks in PyTorch
- you are a data scientist or ML engineer starting a vision project and want accelerators
- you need reference notebooks for training, evaluating, and deploying vision models

## When to avoid
- you need a production-ready maintained library rather than example notebooks
- you work outside PyTorch or require non-Azure cloud deployment
- you need cutting-edge state-of-the-art model implementations

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, image-processing, computer-vision, deep-learning
- domain: computer-vision, machine-learning, deep-learning, data-science, tutorials
- platform: python, cloud
- tags: jupyter-notebooks, pytorch, image-classification, object-detection, image-similarity, action-recognition, best-practices, azure, microsoft, gpu, docker

## Member repositories
- microsoft/computervision-recipes (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:37.613201+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 2026-08-29T17:20:21.645596+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/computervision-recipes (fetched 2026-08-28T04:10:37.613201+00:00, sha e1bf5d2dba2b)
- Data as of 2026-08-30T08:39:29.467469+00:00.