# WongKinYiu/PyTorch_YOLOv4

PyTorch implementation of YOLOv4

Repository: https://github.com/WongKinYiu/PyTorch_YOLOv4
Canonical: https://ross.abutalabs.com/products/pytorch_yolov4
Language: Python
License Family: other
Last push: 2024-11-03T00:53:06+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": 2272, "days_push": 669, "days_rel": 669, "gap_med": null, "n_releases_24m": 1}
- flags: prerelease_only, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1908, forks 581 (observed 2026-08-28T04:05:52.842229+00:00)

## What it is
A PyTorch implementation of the YOLOv4 real-time object detection model, based on ultralytics/yolov3. It includes research extensions such as instance segmentation, transformer backbones, and various loss functions.

## Use cases
- train a custom object detection model in pytorch
- run real-time object detection on images and video
- implement yolov4 without darknet
- add instance segmentation to yolo detection
- experiment with transformer backbones for detection

## When to choose
- you want a PyTorch-native YOLOv4 with research extensions like segmentation and attention modules
- you need to train or fine-tune YOLO models on custom datasets

## When to avoid
- you need a maintained production detector with active support and a clear license
- you want the latest YOLO versions or simple out-of-the-box inference APIs

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

## Member repositories
- WongKinYiu/PyTorch_YOLOv4 (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:52.842229+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 2026-08-30T03:11:11.653832+00:00, confidence not recorded.
  - readme: https://github.com/WongKinYiu/PyTorch_YOLOv4 (fetched 2026-08-28T04:05:52.842229+00:00, sha 81c8f78d29a8)
- Data as of 2026-08-30T08:39:29.467469+00:00.