# marcoslucianops/DeepStream-Yolo

NVIDIA DeepStream SDK 8.0 / 7.1 / 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models

Repository: https://github.com/marcoslucianops/DeepStream-Yolo
Canonical: https://ross.abutalabs.com/products/deepstream-yolo
Language: Python
License: MIT
License Family: permissive
Topics: nvidia-deepstream-sdk, deepstream, object-detection, yolo, darknet, tensorrt, pytorch, nvidia, ultralytics, ppyoloe, paddle, mmyolo, rtdetr, rtmdet, cuda
Last push: 2026-01-25T15:24:40+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 64, release rhythm 35, longevity 100
- inputs: {"age_days": 2346, "days_push": 220, "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 2054, forks 462 (observed 2026-08-28T04:06:09.743086+00:00)

## What it is
A collection of configuration files, parsers, and conversion utilities for running YOLO-family object detection models on NVIDIA DeepStream SDK. It supports many model variants (YOLOv5 through YOLO26, RT-DETR, PPYOLOE, etc.) via ONNX or Darknet conversion with TensorRT engines and GPU post-processing.

## Use cases
- deploy yolo models with nvidia deepstream
- convert yolov8 onnx to tensorrt engine
- run object detection on jetson with deepstream
- int8 calibration for yolo tensorrt
- use custom yolo weights in deepstream pipeline
- real-time object detection on gpu video streams

## When to choose
- you need to run YOLO-family detectors inside NVIDIA DeepStream pipelines
- you want TensorRT optimization with INT8 calibration for detection models
- you target Jetson or dGPU hardware for real-time video analytics

## When to avoid
- you need a framework-agnostic inference solution without DeepStream
- you run on non-NVIDIA hardware
- you need segmentation or pose models (use the companion DeepStream-Yolo-Seg/Pose repos)

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, computer-vision, image-processing, gpu-computing, sdk
- domain: computer-vision, deep-learning, machine-learning, gpu-computing
- platform: python, cpp
- tags: nvidia-deepstream, yolo, tensorrt, object-detection, onnx, int8-calibration, darknet, ultralytics, video-analytics, video, linux, gpu, docker

## Member repositories
- marcoslucianops/DeepStream-Yolo (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:09.743086+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 2026-08-30T02:57:18.310422+00:00, confidence not recorded.
  - readme: https://github.com/marcoslucianops/DeepStream-Yolo (fetched 2026-08-28T04:06:09.743086+00:00, sha 4581fa96528b)
- Data as of 2026-08-30T08:39:29.467469+00:00.