bubbliiiing/yolov8-pytorch
这是一个yolov8-pytorch的仓库,可以用于训练自己的数据集。 observed · 2026-09-03
Health v2 · maintenance only
21/100
- Activity 0
- Release rhythm 8
- Longevity 92
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-02. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 1295
- days_rel: n/a
- days_push: 1102
- n_releases_24m: 0
Adoption not part of the score
1005 stars · 110 forks observed · 2026-09-03
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
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
library · maturity maintenance
machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning image-processing python cross-platform yolov8 object-detection pytorch custom-dataset-training model-training gpu
1 source
- readme: https://github.com/bubbliiiing/yolov8-pytorch · fetched 2026-09-03 · fbeb538d4d2e
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| bubbliiiing/yolov8-pytorch | main | 21 |
For agents
markdown · JSON · MCP: product_card(name="bubbliiiing/yolov8-pytorch")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem