AI Rank
EN
← 开源
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

InfrastructureDeploy & ServePython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
2.07k
Star
464
Fork
+-2
本周
8
贡献者
创建于 2020-03-31 · 更新于 2026-10-15 · 今日第 9025 名
主要开发者
marcoslucianopspieris98AnvarNazar

marcoslucianops/DeepStream-Yolo 排名第 9,025，有 2,071 个星标。

同类别比较

marcoslucianops/DeepStream-Yolo 排名第 9,025，此处有 8 个同类条目；schibsted/WAAS 排名第 9,023。

同类别比较
名称排名指标
deepspeedai/DeepSpeed-MII8,964
语言:
Python
星标数:
2,115
分叉数:
192
简介:
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
vitoplantamura/OnnxStream9,008
语言:
C++
星标数:
2,088
分叉数:
99
简介:
Lightweight inference library for ONNX files, written in C++. It can run Stable Diffusion XL 1.0 on a RPI Zero 2 (or in 298MB of RAM) but also Mistral 7B on desktops and servers. ARM, x86, WASM, RISC-V supported. Accelerated by XNNPACK. Python, C# and JS(WASM) bindings available.
guinmoon/LLMFarm9,013
语言:
C
星标数:
2,080
分叉数:
186
简介:
llama and other large language models on iOS and MacOS offline using GGML library.
schibsted/WAAS9,023
语言:
JavaScript
星标数:
2,074
分叉数:
115
简介:
Whisper as a Service (GUI and API with queuing for OpenAI Whisper)
BoCloud/folib9,033
语言:
Java
星标数:
2,064
分叉数:
137
简介:
全语言制品仓库，涵盖npm、Maven、PyPi、Docker、Gradle、SBT、Cocoapods、Swift、RPM、Debian、PHP、Go、Pub、Ivy、NuGet、Conda、Cargo、Conan、Yarn、GitLFS、Helm、OHPM等主流工具,涵盖Huggingface 等主流AI模型仓库的代理与同步
xmanrui/OpenClaw-bot-review9,087
语言:
TypeScript
星标数:
2,023
分叉数:
383
简介:
A lightweight web dashboard for viewing all your OpenClaw Bots/Agents/Models/Sessions status at a glance.
intel/intel-extension-for-pytorch9,100
语言:
Python
星标数:
2,012
分叉数:
323
简介:
A Python package for extending the official PyTorch that can easily obtain performance on Intel platform
AgentOps-AI/tokencost9,109
语言:
Python
星标数:
2,005
分叉数:
107
简介:
Easy token price estimates for 400+ LLMs. TokenOps.
关键参数与规格
关键参数与规格
参数值
语言Python
类别Infrastructure
子类别Deploy & Serve
星标数2,071
分叉数464
贡献者8
创建日期2020-03-31
更新日期2026-10-15
1 天星标数0
7 天星标数-2
排名9,025
上次排名19,235
排名变化10,210
7 天星标排名18,245
上次 7 天星标排名16,958
7 天星标排名变化-1,287
总星标排名6,165
上次总星标排名6,160
总星标排名变化-5
国家Brazil
README 摘录

DeepStream-Yolo NVIDIA DeepStream SDK 8. 20 (TITAN, GeForce RTX / GTX series and RTX / Quadro series) NVIDIA DeepStream SDK 8. 03 (TITAN, GeForce RTX / GTX series and RTX / Quadro series) NVIDIA DeepStream SDK 7. 1 DeepStream-Yolo Supported models Darknet MobileNet-YOLO YOLO-Fastest YOLOv5 YOLOv5u YOLOv6 YOLOv7 YOLOv8 YOLOv9 YOLOv10 YOLO11 YOLOv12 YOLOv13 YOLOR YOLOX RTMDet (MMYOLO) Gold-YOLO DAMO-YOLO PP-YOLOE / PP-YOLOE+ YOLO-NAS CO-DETR (MMDetection) RT-DETR D-FINE RF-DETR YOLO26 YOLO-Master

Basic usage 1. Download the and files from Darknet repo to the DeepStream-Yolo folder 3. Set the according to your DeepStream version x86 platform Jetson platform 3. Edit the file according to your model (example for YOLOv4) **NOTE**: For **Darknet** models, by default, the dynamic batch-size is set. To use static batch-size, uncomment the line 5. Run **NOTE**: The TensorRT engine file may take a very long time to generate (sometimes more than 10 minutes). **NOTE**: If

you want to use YOLOv2 or YOLOv2-Tiny models, change the file before run it Docker usage x86 platform Jetson platform **NOTE**: To compile the , you need to install the g++ inside the container **NOTE**: With DeepStream 8. 0, the docker containers do not package libraries necessary for certain multimedia operations like audio data parsing, CPU decode, and CPU encode. This change could affect processing certain video streams/files like mp4 that include audio track. Please run the below script

inside the docker images to install additional packages that might be necessary to use all of the DeepStreamSDK features: NMS Configuration To change the , and values, modify the config_infer file **NOTE**: Make sure to set in the config_infer file. Sometimes while running gstreamer pipeline or sample apps, user can encounter error: . The issue is caused because of a bug in version which comes with Ubuntu 22. The issue is addressed in and its installation is required to fix

the issue ( 2. Sometimes with RTSP streams the application gets stuck on reaching EOS. This is because of an issue in rtpjitterbuffer component. To fix this issue, a script has been provided with required details to update gstrtpmanager library. Extract metadata You can get metadata from DeepStream using Python and C/C++. For Python, your can install and edit deepstream_python_apps. Basically, you need manipulate the (Python / C/C++) (Python / C/C++) to get the label, position, etc.

常见问题

记录了多少星标和分叉？

marcoslucianops/DeepStream-Yolo 有 2,071 个星标和 464 个分叉。

仓库排名是多少？

marcoslucianops/DeepStream-Yolo 排名第 9,025。

记录的语言和类别是什么？

marcoslucianops/DeepStream-Yolo 有 2,071 个星标，语言为 Python，类别为 Infrastructure。

哪个仓库排名最接近？

marcoslucianops/DeepStream-Yolo 与 schibsted/WAAS 比较，后者排名第 9,023，有 2,074 个星标。

README

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 configuration for YOLO models

For now, I am limited for some updates. Thank you for understanding.

YOLO-Pose: https://github.com/marcoslucianops/DeepStream-Yolo-Pose

YOLO-Seg: https://github.com/marcoslucianops/DeepStream-Yolo-Seg

YOLO-Face: https://github.com/marcoslucianops/DeepStream-Yolo-Face

Important: please export the ONNX model with the new export file, generate the TensorRT engine again with the updated files, and use the new config_infer_primary file according to your model

Improvements on this repository

  • Support for INT8 calibration
  • Support for non square models
  • Models benchmarks
  • Support for Darknet models (YOLOv4, etc) using cfg and weights conversion with GPU post-processing
  • Support for YOLO-Master, YOLO26, RF-DETR, D-FINE, RT-DETR, CO-DETR (MMDetection), YOLO-NAS, PPYOLOE+, PPYOLOE, DAMO-YOLO, Gold-YOLO, RTMDet (MMYOLO), YOLOX, YOLOR, YOLOv13, YOLOv12, YOLO11, YOLOv10, YOLOv9, YOLOv8, YOLOv7, YOLOv6, YOLOv5u and YOLOv5 using ONNX conversion with GPU post-processing
  • GPU bbox parser
  • Custom ONNX model parser
  • Dynamic batch-size
  • INT8 calibration (PTQ) for Darknet and ONNX exported models

Getting started

Requirements

DeepStream 8.0 on x86 platform

DeepStream 7.1 on x86 platform

DeepStream 7.0 on x86 platform

DeepStream 6.4 on x86 platform

DeepStream 6.3 on x86 platform

DeepStream 6.2 on x86 platform

DeepStream 6.1.1 on x86 platform

DeepStream 6.1 on x86 platform

DeepStream 6.0.1 / 6.0 on x86 platform

DeepStream 5.1 on x86 platform

DeepStream 8.0 on Jetson platform

DeepStream 7.1 on Jetson platform

DeepStream 7.0 on Jetson platform

DeepStream 6.4 on Jetson platform

DeepStream 6.3 on Jetson platform

DeepStream 6.2 on Jetson platform

DeepStream 6.1.1 on Jetson platform

DeepStream 6.1 on Jetson platform

DeepStream 6.0.1 / 6.0 on Jetson platform

DeepStream 5.1 on Jetson platform

Supported models

Basic usage

1. Download the repo

git clone https://github.com/marcoslucianops/DeepStream-Yolo.git
cd DeepStream-Yolo

2. Download the cfg and weights files from Darknet repo to the DeepStream-Yolo folder

3. Compile the lib

3.1. Set the CUDA_VER according to your DeepStream version

export CUDA_VER=XY.Z

  • x86 platform

    DeepStream 8.0 = 12.8
DeepStream 7.1 = 12.6
DeepStream 7.0 / 6.4 = 12.2
DeepStream 6.3 = 12.1
DeepStream 6.2 = 11.8
DeepStream 6.1.1 = 11.7
DeepStream 6.1 = 11.6
DeepStream 6.0.1 / 6.0 = 11.4
DeepStream 5.1 = 11.1

  • Jetson platform

    DeepStream 8.0 = 13.0
DeepStream 7.1 = 12.6
DeepStream 7.0 / 6.4 = 12.2
DeepStream 6.3 / 6.2 / 6.1.1 / 6.1 = 11.4
DeepStream 6.0.1 / 6.0 / 5.1 = 10.2

3.2. Make the lib

make -C nvdsinfer_custom_impl_Yolo clean && make -C nvdsinfer_custom_impl_Yolo

4. Edit the config_infer_primary.txt file according to your model (example for YOLOv4)

[property]
...
custom-network-config=yolov4.cfg
model-file=yolov4.weights
...

NOTE: For Darknet models, by default, the dynamic batch-size is set. To use static batch-size, uncomment the line

...
force-implicit-batch-dim=1
...

5. Run

deepstream-app -c deepstream_app_config.txt

NOTE: The TensorRT engine file may take a very long time to generate (sometimes more than 10 minutes).

NOTE: If you want to use YOLOv2 or YOLOv2-Tiny models, change the deepstream_app_config.txt file before run it

...
[primary-gie]
...
config-file=config_infer_primary_yoloV2.txt
...

Docker usage

  • x86 platform

    nvcr.io/nvidia/deepstream:8.0-gc-triton-devel
nvcr.io/nvidia/deepstream:8.0-triton-multiarch

  • Jetson platform

    nvcr.io/nvidia/deepstream:8.0-triton-multiarch

NOTE: To compile the nvdsinfer_custom_impl_Yolo, you need to install the g++ inside the container

apt-get install build-essential

NOTE: With DeepStream 8.0, the docker containers do not package libraries necessary for certain multimedia operations like audio data parsing, CPU decode, and CPU encode. This change could affect processing certain video streams/files like mp4 that include audio track. Please run the below script inside the docker images to install additional packages that might be necessary to use all of the DeepStreamSDK features:

/opt/nvidia/deepstream/deepstream/user_additional_install.sh

NMS Configuration

To change the nms-iou-threshold, pre-cluster-threshold and topk values, modify the config_infer file

[class-attrs-all]
nms-iou-threshold=0.45
pre-cluster-threshold=0.25
topk=300

NOTE: Make sure to set cluster-mode=2 in the config_infer file.

Notes

  1. Sometimes while running gstreamer pipeline or sample apps, user can encounter error: GLib (gthread-posix.c): Unexpected error from C library during 'pthread_setspecific': Invalid argument. Aborting.. The issue is caused because of a bug in glib 2.0-2.72 version which comes with Ubuntu 22.04 by default. The issue is addressed in glib 2.76 and its installation is required to fix the issue (https://github.com/GNOME/glib/tree/2.76.6).

    • Migrate glib to newer version

      pip3 install meson
pip3 install ninja

      NOTE: It is recommended to use Python virtualenv.

      git clone https://github.com/GNOME/glib.git
cd glib
git checkout 2.76.6
meson build --prefix=/usr
ninja -C build/
cd build/
ninja install

    • Check and confirm the newly installed glib version:

      pkg-config --modversion glib-2.0

  2. Sometimes with RTSP streams the application gets stuck on reaching EOS. This is because of an issue in rtpjitterbuffer component. To fix this issue, a script has been provided with required details to update gstrtpmanager library.

    /opt/nvidia/deepstream/deepstream/update_rtpmanager.sh

Extract metadata

You can get metadata from DeepStream using Python and C/C++. For C/C++, you can edit the deepstream-app or deepstream-test codes. For Python, your can install and edit deepstream_python_apps.

Basically, you need manipulate the NvDsObjectMeta (Python / C/C++) and NvDsFrameMeta (Python / C/C++) to get the label, position, etc. of bboxes.

My projects: https://www.youtube.com/MarcosLucianoTV

排名相邻
同类项目