# eriklindernoren/PyTorch-YOLOv3

Minimal PyTorch implementation of YOLOv3

Repository: https://github.com/eriklindernoren/PyTorch-YOLOv3
Canonical: https://ross.abutalabs.com/products/pytorch-yolov3
Language: Python
License: GPL-3.0
License Family: copyleft
Last push: 2024-11-17T15:24:57+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": 3026, "days_push": 654, "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 7440, forks 2589 (observed 2026-08-28T04:09:59.909971+00:00)

## What it is
A minimal PyTorch implementation of YOLOv3 supporting training, inference, and evaluation, with compatibility for YOLOv4 and YOLOv7 weights. It is installable via pip as a library and provides CLI tools for detection, training, and testing.

## Use cases
- run object detection on images with yolo
- train a custom yolo object detection model in pytorch
- evaluate yolo model mAP on COCO
- load yolov3 or yolov4 weights in pytorch
- integrate yolo detection into a python project

## When to choose
- you want a lightweight, readable YOLOv3 implementation in PyTorch
- you need to train or fine-tune YOLO on custom datasets
- you want pip-installable YOLO with CLI tools

## When to avoid
- you need the latest YOLO architectures or best performance
- you want a production-grade maintained detection framework
- you need non-GPL licensing

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, image-processing, machine-learning, deep-learning, cli
- domain: computer-vision, machine-learning, deep-learning, image-processing
- platform: python, cli, cross-platform
- tags: yolo, object-detection, pytorch, darknet, yolov3, yolov4, yolov7, gpu

## Member repositories
- eriklindernoren/PyTorch-YOLOv3 (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:59.909971+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 2026-08-29T17:37:41.811179+00:00, confidence not recorded.
  - readme: https://github.com/eriklindernoren/PyTorch-YOLOv3 (fetched 2026-08-28T04:09:59.909971+00:00, sha a32fa953665c)
- Data as of 2026-08-30T08:39:29.467469+00:00.