# tinyvision/DAMO-YOLO

DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.

Repository: https://github.com/tinyvision/DAMO-YOLO
Canonical: https://ross.abutalabs.com/products/damo-yolo
Language: Python
License: Apache-2.0
License Family: permissive
Topics: deep-learning, nas, object-detection, onnx, pytorch, tensorrt, yolo, yolov5, imagenet, damo-yolo
Last push: 2024-05-25T16:21:06+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 98
- inputs: {"age_days": 1375, "days_push": 830, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3183, forks 406 (observed 2026-08-28T04:07:47.916299+00:00)

## What it is
DAMO-YOLO is a fast and accurate object detection framework built on PyTorch, featuring NAS-searched backbones, RepGFPN, a lightweight ZeroHead with AlignedOTA label assignment, and distillation enhancement. It provides pretrained models and end-to-end tools from training to ONNX/TensorRT deployment.

## Use cases
- train a custom yolo object detection model
- deploy object detection with tensorrt or onnx
- find a fast real-time object detector alternative to yolov5
- run object detection on edge devices with low flops
- use pretrained models to boost downstream detection tasks
- quantize a detection model to int8

## When to choose
- you need state-of-the-art speed/accuracy tradeoffs in the YOLO family
- you want a full train-to-deploy pipeline with TensorRT/ONNX export
- you need lightweight nano models for CPU or edge inference

## When to avoid
- you need a general-purpose vision toolkit beyond detection
- you require frequent updates or broad community support
- your stack is TensorFlow or JAX based

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: deep-learning, computer-vision, machine-learning, artificial-intelligence
- platform: python
- tags: object-detection, yolo, pytorch, onnx, tensorrt, nas, model-deployment, distillation, gpu, linux, docker

## Member repositories
- tinyvision/DAMO-YOLO (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:47.916299+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 2026-08-30T07:25:02.894052+00:00, confidence not recorded.
  - readme: https://github.com/tinyvision/DAMO-YOLO (fetched 2026-08-28T04:07:47.916299+00:00, sha 3af4ae4f1cdf)
- Data as of 2026-08-30T08:39:29.467469+00:00.