# bubbliiiing/yolov8-pytorch

这是一个yolov8-pytorch的仓库，可以用于训练自己的数据集。

Repository: https://github.com/bubbliiiing/yolov8-pytorch
Canonical: https://ross.abutalabs.com/products/yolov8-pytorch
Language: Python
License: GPL-3.0
License Family: copyleft
Last push: 2023-08-27T13:11:15+00:00

## Health v2 (maintenance only)
Score: 21/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 92
- inputs: {"age_days": 1295, "days_push": 1102, "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 1005, forks 110 (observed 2026-09-03T02:15:09.719088+00:00)

## What it is
A PyTorch implementation of the YOLOv8 object detection model with training, prediction, and evaluation scripts. It supports training on custom VOC-format datasets and provides pretrained COCO weights.

## Use cases
- train yolov8 on my own dataset
- object detection in pytorch
- detect objects in images with pretrained weights
- fine-tune yolo on custom data
- evaluate object detection mAP on COCO
- convert annotations to VOC format for training

## When to choose
- you want a readable, educational PyTorch implementation of YOLOv8
- you need to train object detection on custom VOC-format datasets
- you want multi-GPU training, EMA, and mixed precision support in a simple codebase

## When to avoid
- you need the official Ultralytics tooling, ecosystem, and export formats
- you require production-grade maintenance and frequent updates
- you need a non-PyTorch framework or non-GPL license

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning, image-processing
- platform: python, cross-platform
- tags: yolov8, object-detection, pytorch, custom-dataset-training, model-training, gpu

## Member repositories
- bubbliiiing/yolov8-pytorch (main) score 21

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:09.719088+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 2026-08-30T07:12:45.379867+00:00, confidence not recorded.
  - readme: https://github.com/bubbliiiing/yolov8-pytorch (fetched 2026-09-03T02:15:09.719088+00:00, sha fbeb538d4d2e)
- Data as of 2026-08-30T08:39:29.467469+00:00.