# iscyy/ultralyticsPro

🔥🔥🔥 专注于YOLO11，YOLOv8、TYOLOv12、YOLOv10、RT-DETR、YOLOv7、YOLOv5改进模型，Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀

Repository: https://github.com/iscyy/ultralyticsPro
Canonical: https://ross.abutalabs.com/products/ultralyticspro
Homepage: https://github.com/iscyy/ultralyticsPro
Language: Python
License Family: other
Topics: yolov5, backbone, pytorch, transformer, yolov3, yolov4, yolov7, deep-learning, yoloair, yolov6, yolo, rt-detr, yolo11, yolov10, yolov8
Last push: 2025-12-15T02:11:00+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 57, release rhythm 8, longevity 100
- inputs: {"age_days": 1489, "days_push": 262, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2954, forks 459 (observed 2026-08-28T04:07:32.119628+00:00)

## What it is
A PyTorch-based collection of improved YOLO-family object detection models (YOLOv5 through YOLOv13, RT-DETR) with pluggable modules for backbones, necks, heads, losses, IoU, and NMS. It provides training and prediction scripts for detection, segmentation, pose, OBB, and classification tasks.

## Use cases
- improve yolo model accuracy with custom backbone
- swap attention modules into yolov8 neck
- train rt-detr on custom dataset
- experiment with different iou loss functions
- try new nms variants in yolo detection
- fine-tune yolo11 for object detection
- compare yolov8 vs yolov10 improvements

## When to choose
- you want to experiment with modular improvements to YOLO-family detectors
- you need a research playground for backbones, necks, heads, and loss functions
- you want ready-made training scripts for detection, segmentation, pose, or OBB tasks

## When to avoid
- you need a production-supported detector with a permissive license and long-term maintenance
- you want a stable, well-documented framework rather than a research collection
- you need guaranteed updates or official support, since the repo has no license and limited commit history

## Facets
- artifact type: library
- maturity: active
- function: deep-learning, machine-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python, cross-platform
- tags: yolo, object-detection, pytorch, model-improvement, rt-detr, backbone, neck, head, loss-functions, iou, nms, research, gpu

## Member repositories
- iscyy/ultralyticsPro (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:32.119628+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 2026-08-30T07:32:36.680574+00:00, confidence not recorded.
  - readme: https://github.com/iscyy/ultralyticsPro (fetched 2026-08-28T04:07:32.119628+00:00, sha ce47f33a7565)
  - homepage: https://github.com/iscyy/ultralyticsPro (fetched 2026-08-29T09:47:39.749164+00:00, sha 6c761aaa727e)
- Data as of 2026-08-30T08:39:29.467469+00:00.