# bubbliiiing/yolov4-pytorch

这是一个YoloV4-pytorch的源码，可以用于训练自己的模型。

Repository: https://github.com/bubbliiiing/yolov4-pytorch
Canonical: https://ross.abutalabs.com/products/yolov4-pytorch
Language: Python
License: MIT
License Family: permissive
Last push: 2023-10-03T22:49:16+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": 2292, "days_push": 1065, "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 2160, forks 595 (observed 2026-08-28T04:06:20.934886+00:00)

## What it is
A PyTorch implementation of the YOLOv4 object detection model with full training, prediction, and evaluation scripts. It supports training custom datasets in VOC format, multi-GPU training, and pretrained COCO/VOC weights.

## Use cases
- train a custom object detection model on my own dataset
- run YOLOv4 object detection in PyTorch
- detect objects in images and videos with YOLOv4
- fine-tune YOLOv4 on a VOC-format dataset
- evaluate object detection mAP on a test set
- learn how YOLOv4 works from annotated source code

## When to choose
- you want a readable, well-commented YOLOv4 implementation for training custom detectors
- you need pretrained COCO or VOC weights with simple predict/train scripts
- you are learning object detection internals like Mosaic augmentation, CIOU loss, and PAN/SPP

## When to avoid
- you need the latest YOLO versions or state-of-the-art accuracy (consider YOLOv7/v8 or Ultralytics)
- you need production-grade packaging, APIs, or long-term maintenance
- you cannot use older PyTorch versions the codebase was built around

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, image-processing, deep-learning
- domain: computer-vision, deep-learning, machine-learning, image-processing
- platform: python, cross-platform
- tags: yolov4, object-detection, pytorch, darknet53, training, inference, custom-dataset, tutorial, gpu

## Member repositories
- bubbliiiing/yolov4-pytorch (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:20.934886+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 2026-08-30T02:50:17.810471+00:00, confidence not recorded.
  - readme: https://github.com/bubbliiiing/yolov4-pytorch (fetched 2026-08-28T04:06:20.934886+00:00, sha 4642dbfc698d)
- Data as of 2026-08-30T08:39:29.467469+00:00.