Erste Schritte

Ultralytics YOLO26 auf NVIDIA Jetson mit DeepStream SDK und TensorRT



Ansehen: So verwendest du Ultralytics YOLO26-Modelle mit NVIDIA DeepStream auf Jetson Orin NX 🚀

Diese Anleitung führt dich durch die Bereitstellung von Ultralytics YOLO26 auf NVIDIA Jetson-Geräten mit DeepStream SDK und TensorRT. Wir verwenden TensorRT, um die Inferenzleistung auf der Jetson-Plattform zu maximieren.

Diese Anleitung führt dich durch die DeepStream-Konfiguration für YOLO26, die INT8-Kalibrierung, die Einrichtung mehrerer Streams und die Benchmark-Ergebnisse.

NVIDIA DeepStream SDK on Jetson platform
Hinweis

Diese Anleitung wurde mit dem NVIDIA Jetson Orin Nano Super Developer Kit getestet, auf dem die JetPack-Version JP6.1 läuft, mit dem Seeed Studio reComputer J4012, das auf NVIDIA Jetson Orin NX 16GB basiert und mit der JetPack-Version JP5.1.3 läuft, sowie mit dem Seeed Studio reComputer J1020 v2, das auf NVIDIA Jetson Nano 4GB basiert und mit der JetPack-Version JP4.6.4 läuft. Die Anleitung sollte mit der gesamten NVIDIA-Jetson-Hardwarepalette funktionieren, einschließlich der neuesten und älteren Modelle.

Was ist NVIDIA DeepStream?#

Das DeepStream SDK von NVIDIA ist ein umfassendes Toolkit zur Streaming-Analyse auf Basis von GStreamer für KI-gestützte Verarbeitung mehrerer Sensoren sowie für die Analyse von Video, Audio und Bildern. Es eignet sich ideal für Entwickler im Bereich Vision-KI, Softwarepartner, Start-ups und OEMs, die IVA-Anwendungen (intelligente Videoanalyse) und -Dienste entwickeln. Du kannst Pipelines zur Stream-Verarbeitung erstellen, die neuronale Netze und weitere komplexe Aufgaben wie Tracking, Video-Encoding und -Decoding sowie Videodarstellung umfassen. Diese Pipelines ermöglichen Echtzeitanalysen von Video-, Bild- und Sensordaten. Dank der Unterstützung mehrerer Plattformen kannst du mit DeepStream Vision-KI-Anwendungen und -Dienste schneller und einfacher lokal, am Rand des Netzwerks und in der Cloud entwickeln.

Voraussetzungen#

Bevor du mit dieser Anleitung beginnst:

Tipp

In dieser Anleitung verwenden wir die Debian-Paketmethode, um DeepStream SDK auf dem Jetson-Gerät zu installieren. Unter DeepStream SDK auf Jetson (archiviert) findest du auch ältere DeepStream-Versionen.

DeepStream-Konfiguration für YOLO26#

Wir verwenden hier das GitHub-Repository marcoslucianops/DeepStream-Yolo, das NVIDIA-DeepStream-SDK-Unterstützung für YOLO-Modelle enthält. Wir bedanken uns bei marcoslucianops für die Beiträge.

  1. Installiere Ultralytics mit den erforderlichen Abhängigkeiten

    pip install ultralytics onnx onnxslim
  2. Klone das DeepStream-Yolo-Repository

    cd ~
    git clone https://github.com/marcoslucianops/DeepStream-Yolo
  3. Lade ein Ultralytics-YOLO26-Erkennungsmodell (.pt) deiner Wahl aus dem YOLO26-Projekt herunter. Hier verwenden wir yolo26s.pt.

    wget https://github.com/ultralytics/assets/releases/download/v8.4.0/yolo26s.pt
Hinweis

Du kannst auch ein benutzerdefiniert trainiertes YOLO26-Modell verwenden.

  1. Konvertiere das Modell in ONNX und schreibe die Datei labels.txt, aus der DeepStream die Klassennamen liest.

    from ultralytics import YOLO
    
    model = YOLO("yolo26s.pt")
    model.export(format="onnx", nms=False, agnostic_nms=True)  # erstellt 'yolo26s.onnx'
    with open("labels.txt", "w") as f:
        f.write("\n".join(model.names.values()))
Exportargumente

nms=False exportiert den NMS-freien Kopf, und agnostic_nms=True behält eine einzelne Klasse pro Erkennung bei, damit cluster-mode=4 (kein Clustering) in der DeepStream-Konfiguration keine Box doppelt zeichnet. Füge imgsz=1280 hinzu, um die Inferenzgröße zu ändern (Standard: 640), batch=4 für eine Batchgröße von 4 (der exportierte Batch ist statisch und muss daher mit batch-size in der DeepStream-Konfiguration übereinstimmen) und opset=12 für TensorRT 8.2 oder älter (DeepStream 6.0.1 und früher). Die vollständige Liste findest du unter Exportargumente.

  1. Kopiere die generierte Modelldatei .onnx und die Datei labels.txt in den Ordner DeepStream-Yolo.

    cp yolo26s.onnx labels.txt ~/DeepStream-Yolo
    cd ~/DeepStream-Yolo
  2. Lege die CUDA-Version entsprechend der installierten JetPack-Version fest.

    Für JetPack 4.6.4:

    export CUDA_VER=10.2

    Für JetPack 5.1.3:

    export CUDA_VER=11.4

    Für JetPack 6.1:

    export CUDA_VER=12.6

    Für JetPack 7.1:

    export CUDA_VER=13.0
  3. Kompiliere die Bibliothek.

    make -C nvdsinfer_custom_impl_Yolo clean && make -C nvdsinfer_custom_impl_Yolo
  4. Bearbeite die Datei config_infer_primary_yolo26.txt passend zu deinem Modell (für YOLO26s mit 80 Klassen).

    [property]
    ...
    onnx-file=yolo26s.onnx
    ...
    num-detected-classes=80
    ...
    parse-bbox-func-name=NvDsInferParseYolo
    ...
YOLO26-Einstellungen für die Genauigkeit

YOLO26 passt die Eingabegröße durch zentriertes Padding an und läuft ohne NMS. Für die beste Genauigkeit füge Folgendes im Abschnitt [property] der Datei config_infer_primary_yolo26.txt hinzu:

[property]
...
maintain-aspect-ratio=1
symmetric-padding=1
cluster-mode=4
...
  1. Bearbeite die Datei deepstream_app_config.

    ...
    [primary-gie]
    ...
    config-file=config_infer_primary_yolo26.txt
  2. Du kannst auch die Videoquelle in der Datei deepstream_app_config ändern. Hier wird eine Standardvideodatei geladen.

    ...
    [source0]
    ...
    uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4

Inferenz ausführen#

deepstream-app -c deepstream_app_config.txt
Hinweis

Das Erstellen der TensorRT-Engine-Datei kann lange dauern, bevor die Inferenz startet.

YOLO26 object detection running in NVIDIA DeepStream on Jetson
Tipp

Um das Modell mit FP16-Präzision umzuwandeln, setze model-engine-file=model_b1_gpu0_fp16.engine und network-mode=2 in config_infer_primary_yolo26.txt.

INT8-Kalibrierung#

Führe die folgenden Schritte aus, um bei der Inferenz INT8-Präzision zu verwenden:

Hinweis

INT8 funktioniert derzeit nicht mit TensorRT 10.x. Dieser Abschnitt der Anleitung wurde mit TensorRT 8.x getestet, womit es voraussichtlich funktioniert.

  1. Lege die Umgebungsvariable OPENCV fest.

    export OPENCV=1
  2. Kompiliere die Bibliothek.

    make -C nvdsinfer_custom_impl_Yolo clean && make -C nvdsinfer_custom_impl_Yolo
  3. Lade für den COCO-Datensatz val2017 herunter, entpacke die Datei und verschiebe sie in den Ordner DeepStream-Yolo.

  4. Erstelle ein neues Verzeichnis für die Kalibrierungsbilder.

    mkdir calibration
  5. Führe Folgendes aus, um 1000 zufällige Bilder aus dem COCO-Datensatz für die Kalibrierung auszuwählen.

    for jpg in $(ls -1 val2017/*.jpg | sort -R | head -1000); do
      cp ${jpg} calibration/
    done
Hinweis

NVIDIA empfiehlt mindestens 500 Bilder, um eine gute Genauigkeit zu erreichen. In diesem Beispiel werden für eine noch bessere Genauigkeit 1000 Bilder verwendet (mehr Bilder führen in der Regel zu höherer Genauigkeit). Du kannst die Anzahl mit head -1000 festlegen. Für 2000 Bilder verwendest du beispielsweise head -2000. Dieser Vorgang kann lange dauern.

  1. Erstelle die Datei calibration.txt mit allen ausgewählten Bildern.

    realpath calibration/*jpg > calibration.txt
  2. Lege die Umgebungsvariablen fest.

    export INT8_CALIB_IMG_PATH=calibration.txt
    export INT8_CALIB_BATCH_SIZE=1
Hinweis

Höhere Werte für INT8_CALIB_BATCH_SIZE ermöglichen eine genauere und schnellere Kalibrierung. Wähle den Wert passend zum GPU-Speicher.

  1. Aktualisiere die Datei config_infer_primary_yolo26.txt.

    Von

    ...
    model-engine-file=model_b1_gpu0_fp32.engine
    #int8-calib-file=calib.table
    ...
    network-mode=0
    ...

    Zu

    ...
    model-engine-file=model_b1_gpu0_int8.engine
    int8-calib-file=calib.table
    ...
    network-mode=1
    ...

INT8-Inferenz ausführen#

Führe denselben Befehl aus, um die INT8-Engine zu erstellen und die Inferenz zu starten:

deepstream-app -c deepstream_app_config.txt

Einrichtung mehrerer Streams#



Ansehen: So führst du Inferenz mit mehreren Streams mithilfe von Ultralytics YOLO26 und NVIDIA DeepStream auf Jetson Orin aus 🚀

Um mehrere Streams in einer einzelnen DeepStream-Anwendung einzurichten, nimm die folgenden Änderungen an der Datei deepstream_app_config.txt vor:

  1. Ändere die Zeilen und Spalten, um ein Raster entsprechend der gewünschten Anzahl von Streams zu erstellen. Für 4 Streams kannst du zum Beispiel 2 Zeilen und 2 Spalten hinzufügen.

    [tiled-display]
    rows=2
    columns=2
  2. Füge für jeden Stream eine eigene Gruppe [sourceN] hinzu, jeweils mit eigenen uri und num-sources=1.

    [source0]
    enable=1
    type=3
    uri=file:///path/to/video1.mp4
    num-sources=1
    
    [source1]
    enable=1
    type=3
    uri=file:///path/to/video2.mp4
    num-sources=1
    
    [source2]
    enable=1
    type=3
    uri=file:///path/to/video3.mp4
    num-sources=1
    
    [source3]
    enable=1
    type=3
    uri=file:///path/to/video4.mp4
    num-sources=1

Inferenz mit mehreren Streams ausführen#

Führe denselben Befehl aus, um alle Streams in der gekachelten Anzeige zu starten:

deepstream-app -c deepstream_app_config.txt
DeepStream multi-camera streaming configuration

Benchmark-Ergebnisse#

Die folgenden Benchmarks zeigen die Leistung von YOLO11-Modellen mit verschiedenen TensorRT-Präzisionsstufen und einer Eingabegröße von 640x640 auf NVIDIA Jetson Orin NX 16GB. YOLO26 verwendet denselben oben beschriebenen DeepStream-Export- und Inferenzablauf.

Vergleichsdiagramm#

NVIDIA Jetson DeepStream performance benchmarks

Detaillierte Vergleichstabelle#

Leistung
FormatStatusInferenzzeit (ms/Bild)
TensorRT (FP32)✅8.64
TensorRT (FP16)✅5.27
TensorRT (INT8)✅4.54

Danksagungen#

Diese Anleitung wurde ursprünglich von unseren Freunden Lakshantha und Elaine bei Seeed Studio erstellt.

Häufig gestellte Fragen#

  • Um Ultralytics YOLO26 auf einem NVIDIA Jetson-Gerät einzurichten, musst du zuerst das mit deiner JetPack-Version kompatible DeepStream SDK installieren. Folge der Schritt-für-Schritt-Anleitung in unserer Kurzanleitung, um dein NVIDIA Jetson für die Bereitstellung von YOLO26 zu konfigurieren.

  • Die Verwendung von TensorRT mit YOLO26 optimiert das Modell für die Inferenz, reduziert die Latenz erheblich und verbessert den Durchsatz auf NVIDIA-Jetson-Geräten. TensorRT ermöglicht eine leistungsstarke Inferenz mit geringer Latenz für Deep Learning durch Layer-Fusion, Präzisionskalibrierung und automatische Kernel-Abstimmung. Das sorgt für eine schnellere und effizientere Ausführung und ist besonders nützlich für Echtzeitanwendungen wie Videoanalyse und autonome Maschinen.

  • Ja, die Anleitung zur Bereitstellung von Ultralytics YOLO26 mit DeepStream SDK und TensorRT ist mit der gesamten NVIDIA-Jetson-Produktpalette kompatibel. Dazu gehören Geräte wie Jetson Orin NX 16GB mit JetPack 5.1.3 und Jetson Nano 4GB mit JetPack 4.6.4. Eine ausführliche Anleitung findest du im Abschnitt DeepStream-Konfiguration für YOLO26.

  • Exportiere das Modell mit dem NMS-freien Kopf mithilfe des Ultralytics-Exporters und schreibe die Datei labels.txt, aus der DeepStream die Klassennamen liest:

    from ultralytics import YOLO
    
    model = YOLO("yolo26s.pt")
    model.export(format="onnx", nms=False, agnostic_nms=True)  # erstellt 'yolo26s.onnx'
    with open("labels.txt", "w") as f:
        f.write("\n".join(model.names.values()))

    Füge opset=12 für TensorRT 8.2 oder älter (DeepStream 6.0.1 und früher) hinzu. Weitere Informationen zur Modellkonvertierung findest du in unserem Abschnitt Modellexport.

  • Um INT8-Inferenz auszuführen, kalibriere das Modell mit einer repräsentativen Bildauswahl und stelle die DeepStream-Konfiguration auf den INT8-Modus um. Lade die COCO-val2017-Bilder herunter, wähle etwa 1000 Kalibrierungsbilder aus, lege die Umgebungsvariablen INT8_CALIB_IMG_PATH und INT8_CALIB_BATCH_SIZE fest und aktualisiere anschließend config_infer_primary_yolo26.txt mit model-engine-file=model_b1_gpu0_int8.engine, int8-calib-file=calib.table und network-mode=1. Alle Schritte findest du im Abschnitt INT8-Kalibrierung. INT8 erfordert derzeit TensorRT 8.x.

  • Um mehrere Streams in einer einzelnen DeepStream-Anwendung zu verarbeiten, bearbeite die Datei deepstream_app_config.txt, um ein Raster für die gekachelte Anzeige hinzuzufügen und jede Quell-URI aufzulisten. Lege rows und columns unter [tiled-display] fest, um das Raster zu erstellen, füge pro Stream eine eigene Gruppe [sourceN] mit eigenen uri und num-sources=1 hinzu und passe das Raster an die Anzahl der Streams an. Ein vollständiges Beispiel findest du im Abschnitt Einrichtung mehrerer Streams.

  • Die Leistung von YOLO11-Modellen auf NVIDIA Jetson Orin NX 16GB variiert je nach TensorRT-Präzisionsstufe. YOLO11s-Modelle erreichen zum Beispiel:

    • FP32-Präzision: 14.53 ms/im, 68.8 FPS
    • FP16-Präzision: 7.91 ms/im, 126 FPS
    • INT8-Präzision: 6.05 ms/im, 165 FPS

    Diese Ergebnisse zeigen, wie stark FP16- und INT8-TensorRT-Engines YOLO11-Modelle auf NVIDIA-Jetson-Hardware beschleunigen.

Kommentare145

Stell eine Frage, teile deine Ergebnisse oder hilf jemand anderem.

  1. Llinz24GitHub

    hi!I encountered the following issue when using NVIDIA's official DeepStream 8.0 gc-triton-devel image to implement deepstream-yolo: I cannot compile the library, and it prompts that my Tensor version is too new. Is there any solution? Could it be that the current code hasn't fully adapted to DeepStream 8.0? ( root@LGDX:/workspace/DeepStream-Yolo# export CUDA_VER=12.8 root@LGDX:/workspace/DeepStream-Yolo# make -C nvdsinfer_custom_impl_Yolo clean && make -C nvdsinfer_custom_impl_Yolo make: Entering directory '/workspace/DeepStream-Yolo/nvdsinfer_custom_impl_Yolo' rm -rf libnvdsinfer_custom_impl_Yolo.so rm -rf nvdsinfer_yolo_engine.o nvdsparsebbox_Yolo.o utils.o yolo.o yoloPlugins.o layers/activation_layer.o layers/batchnorm_layer.o layers/channels_layer.o layers/convolutional_layer.o layers/deconvolutional_layer.o layers/implicit_layer.o layers/pooling_layer.o layers/reorg_layer.o layers/route_layer.o layers/sam_layer.o layers/shortcut_layer.o layers/slice_layer.o layers/upsample_layer.o nvdsparsebbox_Yolo_cuda.o yoloForward.o yoloForward_nc.o yoloForward_v2.o make: Leaving directory '/workspace/DeepStream-Yolo/nvdsinfer_custom_impl_Yolo' make: Entering directory '/workspace/DeepStream-Yolo/nvdsinfer_custom_impl_Yolo' g++ -c -o nvdsinfer_yolo_engine.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-12.8/include nvdsinfer_yolo_engine.cpp g++ -c -o nvdsparsebbox_Yolo.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-12.8/include nvdsparsebbox_Yolo.cpp In file included from nvdsparsebbox_Yolo.cpp:26: nvdsparsebbox_Yolo.cpp: In function 'void checkFunc_NvDsInferParseYolo(NvDsInferParseCustomFunc)': /opt/nvidia/deepstream/deepstream/sources/includes/nvdsinfer_custom_impl.h:221:17: warning: infinite recursion detected [-Winfinite-recursion] 221 | static void checkFunc_ ## customParseFunc (NvDsInferParseCustomFunc func = customParseFunc)
    | ^~~~~~~~~~ nvdsparsebbox_Yolo.cpp:129:1: note: in expansion of macro 'CHECK_CUSTOM_PARSE_FUNC_PROTOTYPE' 129 | CHECK_CUSTOM_PARSE_FUNC_PROTOTYPE(NvDsInferParseYolo); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ /opt/nvidia/deepstream/deepstream/sources/includes/nvdsinfer_custom_impl.h:222:41: note: recursive call 222 | { checkFunc_ ## customParseFunc (); };
    | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~ nvdsparsebbox_Yolo.cpp:129:1: note: in expansion of macro 'CHECK_CUSTOM_PARSE_FUNC_PROTOTYPE' 129 | CHECK_CUSTOM_PARSE_FUNC_PROTOTYPE(NvDsInferParseYolo); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ g++ -c -o utils.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-12.8/include utils.cpp g++ -c -o yolo.o -Wall -std=c++11 -shared -fPIC -Wno-error=deprecated-declarations -I/opt/nvidia/deepstream/deepstream/sources/includes -I/usr/local/cuda-12.8/include yolo.cpp In file included from yolo.cpp:29: yoloPlugins.h:53:59: warning: 'IPluginV2DynamicExt' is deprecated [-Wdeprecated-declarations] 53 | nvinfer1::IPluginV2DynamicExt* clone() const noexcept override; | ^~~~~~~~ In file included from /usr/include/x86_64-linux-gnu/NvInfer.h:22, from /usr/include/x86_64-linux-gnu/NvOnnxParser.h:21, from yolo.cpp:26: /usr/include/x86_64-linux-gnu/NvInferRuntime.h:406:22: note: declared here 406 | class TRT_DEPRECATED IPluginV2DynamicExt : public nvinfer1::IPluginV2Ext | ^~~~~~~~~~~~~~~~~~~ yoloPlugins.h:124:9: warning: 'IPluginV2DynamicExt' is deprecated [-Wdeprecated-declarations] 124 | override { | ^~~~~~~~ /usr/include/x86_64-linux-gnu/NvInferRuntime.h:406:22: note: declared here 406 | class TRT_DEPRECATED IPluginV2DynamicExt : public nvinfer1::IPluginV2Ext | ^~~~~~~~~~~~~~~~~~~ yoloPlugins.h:130:18: warning: 'IPluginV2DynamicExt' is deprecated [-Wdeprecated-declarations] 130 | noexcept override { | ^~~~~~~~ /usr/include/x86_64-linux-gnu/NvInferRuntime.h:406:22: note: declared here 406 | class TRT_DEPRECATED IPluginV2DynamicExt : public nvinfer1::IPluginV2Ext | ^~~~~~~~~~~~~~~~~~~ yolo.cpp: In member function 'nvinfer1::ICudaEngine* Yolo::createEngine(nvinfer1::IBuilder*, nvinfer1::IBuilderConfig*)': yolo.cpp:71:76: error: 'kEXPLICIT_BATCH' is not a member of 'nvinfer1::NetworkDefinitionCreationFlag' 71 | tic_cast<uint32_t>(nvinfer1::NetworkDefinitionCreationFlag::kEXPLICIT_BATCH); | ^~~~~~~~~~~~~~~

    In file included from /usr/include/c++/13/cassert:44, from layers/../utils.h:32, from layers/route_layer.h:9, from yolo.h:39, from yolo.cpp:28: yolo.cpp:155:21: error: 'class nvinfer1::IBuilder' has no member named 'platformHasFastFp16' 155 | assert(builder->platformHasFastFp16()); | ^~~~~~~~~~~~~~~~~~~ yolo.cpp:156:44: error: 'kFP16' is not a member of 'nvinfer1::BuilderFlag' 156 | config->setFlag(nvinfer1::BuilderFlag::kFP16); | ^~~~~ yolo.cpp:159:21: error: 'class nvinfer1::IBuilder' has no member named 'platformHasFastInt8' 159 | assert(builder->platformHasFastInt8()); | ^~~~~~~~~~~~~~~~~~~ yolo.cpp:160:44: error: 'kINT8' is not a member of 'nvinfer1::BuilderFlag' 160 | config->setFlag(nvinfer1::BuilderFlag::kINT8); | ^~~~~ yolo.cpp: In member function 'NvDsInferStatus Yolo::buildYoloNetwork(std::vector&, nvinfer1::INetworkDefinition&)': yolo.cpp:481:36: warning: 'IPluginV2DynamicExt' is deprecated [-Wdeprecated-declarations] 481 | nvinfer1::IPluginV2DynamicExt* yoloPlugin = new YoloLayer(m_InputW, m_InputH, m_NumClasses, m_NewCoords, | ^~~~~~~~~~ /usr/include/x86_64-linux-gnu/NvInferRuntime.h:406:22: note: declared here 406 | class TRT_DEPRECATED IPluginV2DynamicExt : public nvinfer1::IPluginV2Ext | ^~~~~~~~~~~~~~~~~~~ yolo.cpp:484:31: warning: 'IPluginV2Layer' is deprecated [-Wdeprecated-declarations] 484 | nvinfer1::IPluginV2Layer* yolo = network.addPluginV2(yoloTensorInputs, m_YoloCount, yoloPlugin); | ^~~~ /usr/include/x86_64-linux-gnu/NvInfer.h:2542:22: note: declared here 2542 | class TRT_DEPRECATED IPluginV2Layer : public ILayer | ^~~~~~~~~~~~~~ yolo.cpp:484:57: warning: 'nvinfer1::IPluginV2Layer nvinfer1::INetworkDefinition::addPluginV2(nvinfer1::ITensor* const*, int32_t, nvinfer1::IPluginV2&)' is deprecated [-Wdeprecated-declarations] 484 | nvinfer1::IPluginV2Layer* yolo = network.addPluginV2(yoloTensorInputs, m_YoloCount, yoloPlugin); | ~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ /usr/include/x86_64-linux-gnu/NvInfer.h:8859:36: note: declared here 8859 | TRT_DEPRECATED IPluginV2Layer addPluginV2(ITensor* const* inputs, int32_t nbInputs, IPluginV2& plugin) noexcept | ^~~~~~~~~~~ make: *** [Makefile:86: yolo.o] Error 1 make: Leaving directory '/workspace/DeepStream-Yolo/nvdsinfer_custom_impl_Yolo' root@LGDX:/workspace/DeepStream-Yolo#)

    1. Glenn JocherUltralytics

      Yes, those build errors are from a TensorRT API mismatch, not your commands: the DeepStream-Yolo path used in this doc was tested with the DeepStream/JetPack combinations listed in the Jetson + DeepStream guide, and DeepStream 8.0 gc-triton-devel is using newer TensorRT APIs where symbols like kEXPLICIT_BATCH, kFP16, and platformHasFastFp16() are gone, so it will not compile unchanged; for now please use a supported version combo from the guide or a direct TensorRT export workflow, and if you want to stay on DS 8.0 please share the exact DeepStream-Yolo commit plus your TensorRT version here so we can point out the required upstream patch areas.

    2. Llinz24GitHub

      root@LGDX:/workspace/DeepStream-Yolo# dpkg -l | grep tensorrt ii tensorrt-dev 11.0.0.114-1+cuda13.2 amd64 Meta package for TensorRT development libraries

      If I plan to use yolo11-pose and yolo26, what kind of adjustments do I need?

    3. Glenn JocherUltralytics(bearbeitet)

      For YOLO11-pose, use DeepStream-Yolo-Pose with config_infer_primary_yolo11_pose.txt; for YOLO26 detection, use the main DeepStream-Yolo repo and export through its updated export_yolo26.py path or export with the nms argument described in the End-to-End Detection guide for the classic DeepStream parser flow. The bigger blocker is your environment: DeepStream 8.0 on x86 is validated with TensorRT 10.9.0.34, while your container has TensorRT 11.0.0, and TRT 11 removed the older builder-flag/calibrator APIs, so those external DeepStream custom libs need a TRT11 migration before they will compile; the quickest path is a TRT 10.9 DeepStream 8.0 stack plus the latest repo files, and the relevant Ultralytics export compatibility notes are in Export Settings.

  2. User

    Why can't I see my class name in the block boxes with multiple RTSP video streams (like in the single-stream example)?

    Is there a way to fix this?

    1. Glenn JocherUltralytics

      Yes—if you’re using deepstream-app in tiled multistream mode, bbox labels are often hidden unless you start it with -t, so try deepstream-app -c deepstream_app_config.txt -t, then confirm [osd] has display-text=1 and increase text-size if the tiles are small; please keep Jetson/DeepStream questions here in Discussions so the team can track them, and the Jetson + DeepStream guide is the right reference alongside NVIDIA’s DeepStream reference app docs. (forums.developer.nvidia.com)

  3. Llinz24GitHub

    Is YOLO26-seg currently supported for direct deployment and execution in DeepStream? Are there any available tutorials or reference solutions?

    1. Glenn JocherUltralytics

      Not in the published direct DeepStream flow yet—the current Jetson + DeepStream guide is detection-focused and uses DeepStream-Yolo, while the available segmentation reference is DeepStream-Yolo-Seg, which currently lists YOLO11-Seg and YOLOv8-Seg support rather than YOLO26-seg, so there isn’t an official YOLO26-seg DeepStream tutorial at the moment; feel free to keep the details here in Discussions and we can help with the closest path forward. (docs.ultralytics.com)

    2. Llinz24GitHub

      I'm running into an issue with YOLO11-seg + DeepStream and could use some help 🙏 So I exported my YOLO11-seg model to ONNX and then to a TensorRT engine. When I run deepstream-app, it does find and load the engine just fine — but the segmentation part just doesn't work. I'm not seeing any masks or even bounding boxes on the video output. Any idea what might be going wrong here? Also, when I use the deepstream-yolo export script to get the ONNX file, the output only shows one node: 1 OUTPUT kFLOAT output 100x102406 But from what I've seen with official YOLO-seg exports (like from Ultralytics), there should usually be two outputs — one for boxes/classes and another for the masks. That mismatch feels like it might be part of the problem? Has anyone run into this before? Any tips on: How to export the ONNX correctly for YOLO-seg (maybe a flag I'm missing?) What to tweak in the DeepStream config (config_infer_primary.txt, parser settings, etc.) to make it actually show the segmentation results? Thanks in advance!

    3. Glenn JocherUltralytics

      Yes, a single-output ONNX is very likely the blocker here: for YOLO11-seg, DeepStream needs the segmentation export with both detection and mask-proto outputs, so a detection-style ONNX/parser will often load the engine but show neither boxes nor masks; please re-export from the Ultralytics side using the workflow in the TensorRT export docs, make sure you are using the segmentation-specific DeepStream parser/config rather than the detection one, and if it still fails please paste the full deepstream-app log plus yolo checks output here so we can verify the tensor names, parser, and engine match.

  4. aneesaromGitHub

    Below is the result from deepstream

    **PERF: FPS 0 (Avg) **PERF: 53.80 (58.72) **PERF: 60.00 (59.38) **PERF: 60.00 (59.59) **PERF: 60.00 (59.69)

    But i can get around 85 fps using ultralytics inference. why is that so. what is the need of using deepstream then. or i am doing anything wrong?

    1. Glenn JocherUltralytics

      Those PERF numbers from deepstream-app are end-to-end pipeline FPS and are often capped by your input stream rate and/or display sync (so a steady ~60 usually means you’re running “real-time/render-limited,” not model-limited), while your Ultralytics run is likely closer to “pure inference throughput”; DeepStream’s value is when you need a full GStreamer pipeline (decode/scale/batching/multi-stream/OSD/encode/RTSP), so for a fair comparison try a headless config (disable OSD/tiler and use fakesink with sync=0) as described in the Ultralytics YOLO26 DeepStream on Jetson guide and make sure you’re matching TensorRT precision/imgsz like in the TensorRT export docs:

      [osd]
      enable=0
      
      [tiled-display]
      enable=0
      
      [sink0]
      type=1
      sync=0

      If you paste your deepstream_app_config.txt [source0] + [sink0] + [primary-gie] sections (and JetPack/DeepStream versions) here, we can point out what’s throttling it.

      1
    2. aneesaromGitHub

      @glenn-jocher Thank you so much for your reply. Now i understood and can see 120 Fps with this setting. But i have a doubt when do we need deepstream over normal ultralytics inferencing. Can you explain it

    3. Glenn JocherUltralytics

      DeepStream is worth using when you need a production GStreamer pipeline around the model—hardware-accelerated decode/encode, zero-copy GPU memory, batching across multiple cameras/streams, RTSP ingest/egress, OSD/tiling, tracking, and easy composition with other DeepStream plugins—whereas “plain” Ultralytics inference is often the simplest/fastest path for single-stream or custom Python loops that just need model outputs; the DeepStream on Jetson guide and the TensorRT export docs are the best references, and feel free to drop your specific target pipeline (sources/sinks/stream count/latency needs) here so we can sanity-check the recommended setup.

  5. SaarulogGitHub

    Hello,

    Thank you for all your help to my issues.

    I have a usb camera with the below format and fails to run. How do I get deepstream to accept or convert the format below to the needed format for display.

    Deepstream 7.1/Jetpack 6.2.1

    deepstream app text file:

    [soruce0] camera- camera-fps-n=9 camera-fps-d=1

    v4l2-ctl -d /dev/video0 --list-formats-ext

    ioctl: VIDIOC_ENUM_FMT Type: Video Capture

    [0]: 'UYVY' (UYVY 4:2:2)
    	Size: Discrete 80x60
    		Interval: Discrete 0.111s (9.000 fps)
    [1]: 'Y16 ' (16-bit Greyscale)
    	Size: Discrete 80x60
    		Interval: Discrete 0.111s (9.000 fps)
    	Size: Discrete 80x63
    		Interval: Discrete 0.111s (9.000 fps)
    [2]: 'GREY' (8-bit Greyscale)
    	Size: Discrete 80x60
    		Interval: Discrete 0.111s (9.000 fps)
    [3]: 'RGBP' (16-bit RGB 5-6-5)
    	Size: Discrete 80x60
    		Interval: Discrete 0.111s (9.000 fps)
    [4]: 'BGR3' (24-bit BGR 8-8-8)
    	Size: Discrete 80x60
    		Interval: Discrete 0.111s (9.000 fps)

    GST_DEBUG=3 deepstream-app -c deepstream_app_config_yolo26_1usbcam.txt

    Setting min object dimensions as 16x16 instead of 1x1 to support VIC compute mode. WARNING: [TRT]: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors. 0:00:00.401328266 6238 0xaaaad1ab46c0 INFO nvinfer gstnvinfer.cpp:684:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2092> [UID = 1]: deserialized trt engine from :/home/shamsee/DeepStream-Yolo/model_b1_gpu0_fp32.engine Implicit layer support has been deprecated INFO: [Implicit Engine Info]: layers num: 0

    0:00:00.401518311 6238 0xaaaad1ab46c0 INFO nvinfer gstnvinfer.cpp:684:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2195> [UID = 1]: Use deserialized engine model: /home/shamsee/DeepStream-Yolo/model_b1_gpu0_fp32.engine 0:00:00.412604525 6238 0xaaaad1ab46c0 INFO nvinfer gstnvinfer_impl.cpp:343:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/home/shamsee/DeepStream-Yolo/config_infer_primary_yolo26_1usbcam_flir.txt sucessfully 0:00:00.414435142 6238 0xaaaad1cb8920 WARN basesrc gstbasesrc.c:3127:gst_base_src_loop:<src_elem> error: Internal data stream error. 0:00:00.414475340 6238 0xaaaad1cb8920 WARN basesrc gstbasesrc.c:3127:gst_base_src_loop:<src_elem> error: streaming stopped, reason not-negotiated (-4) 0:00:00.414521843 6238 0xaaaad1ab46c0 WARN v4l2src gstv4l2src.c:794:gst_v4l2src_query:<src_elem> Can't give latency since framerate isn't fixated ! nvstreammux: Successfully handled EOS for source_id=0

    Runtime commands: h: Print this help q: Quit

    p: Pause
    r: Resume

    NOTE: To expand a source in the 2D tiled display and view object details, left-click on the source. To go back to the tiled display, right-click anywhere on the window.

    ** INFO: <bus_callback:291>: Pipeline ready

    ERROR from src_elem: Internal data stream error. Debug info: ../libs/gst/base/gstbasesrc.c(3127): gst_base_src_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin0/GstV4l2Src:src_elem: streaming stopped, reason not-negotiated (-4) ** INFO: <bus_callback:256>: incorrect camera parameters provided, please provide supported resolution and frame rate

    ** INFO: <bus_callback:277>: Pipeline running

    ** INFO: <bus_callback:334>: Received EOS. Exiting ...

    Quitting 0:00:01.483704521 6238 0xaaaad1ab46c0 ERROR GST_BUS gstbus.c:1075:gst_bus_remove_watch: no bus watch was present App run failed

    1. Glenn JocherUltralytics

      That not-negotiated (-4) is coming from v4l2src not being able to match the caps DeepStream requested (your snippet also has a typo: it must be [source0], and you need type, camera-width, and camera-height set explicitly); please try a minimal V4L2 source config like this (and set [streammux] live-source=1 for a USB cam), per the DeepStream deepstream-app source-group keys in the NVIDIA reference app docs and our YOLO26 DeepStream Jetson guide:

      [source0]
      enable=1
      type=1
      camera-v4l2-dev-node=0
      camera-width=80
      camera-height=60
      camera-fps-n=9
      camera-fps-d=1
      video-format=NV12

      If it still fails, first confirm GStreamer can negotiate your camera at 80x60@9 in UYVY (then we can mirror that into DeepStream), and paste your full [source0] + [streammux] blocks here in this discussion along with the complete text log (not a screenshot).

  6. SaarulogGitHub(bearbeitet)

    Hello I finally got everything else working but stuck in terms of wanting to extract deepstream metadata(inference results-frame, trackerID, detection class, bounding box and etc) and to allow my crewai agents to access for further processing/instructions.  I Don't know where to start or what to create(config files or edit files), properties needed or mapping it within the deepstream_app_config.txt/config_infer_primary_yolo26 besides the custom crewai tool(python) to retrieve the needed metadata. I don't want to use cloud storage but locally to jetson orin nano. Any suggestion, direction PLEASE would be GREATLY appreciated. Thanks again for your help and time. SA

    1. Glenn JocherUltralytics

      DeepStream already attaches detections/tracks as NvDsBatchMeta (frame + NvDsObjectMeta with class_id, bbox, and object_id once nvtracker is enabled), but deepstream-app isn’t really meant to be “extended” from Python—if you want to feed results into CrewAI locally on the Orin, the usual path is to build a small custom DeepStream app using the NVIDIA DeepStream Python sample apps and add a pad-probe on the nvinfer/nvtracker src pad to serialize metadata (e.g., JSON) and hand it directly to your agents.

      # inside a pad-probe callback
      import pyds
      
      batch_meta = pyds.gst_buffer_get_nvds_batch_meta(hash(gst_buffer))
      l_frame = batch_meta.frame_meta_list
      while l_frame:
          frame_meta = pyds.NvDsFrameMeta.cast(l_frame.data)
          l_obj = frame_meta.obj_meta_list
          while l_obj:
              obj = pyds.NvDsObjectMeta.cast(l_obj.data)
              tid = int(obj.object_id)          # tracker ID (requires nvtracker)
              cid = int(obj.class_id)           # class
              r = obj.rect_params               # bbox (left, top, width, height)
              conf = float(obj.confidence)
              # -> push to your local queue / file / socket for CrewAI
              l_obj = l_obj.next
          l_frame = l_frame.next

      If you reply with your JetPack/DeepStream versions and whether you’re currently running the stock deepstream-app config or a custom GStreamer pipeline, I can point you to the closest matching sample to start from.

    2. SaarulogGitHub(bearbeitet)

      Thanks Glen. I am using Jetpack 6.2.1 and DeepStream 7.1. Deepstream-Yolo(deepstream_app_config.txt). How would the "deepstream_app_config.txt/config_infer_primary_yolo26" be mapped or linked to the deepstream python example you provided above?

    3. Glenn JocherUltralytics

      deepstream_app_config.txt is parsed only by deepstream-app; the Python samples don’t “map” it automatically, so in Python you recreate the pipeline in code and simply reuse the same nvinfer config by pointing nvinfer at your existing config_infer_primary_yolo26.txt (which can keep all your DeepStream-Yolo settings like custom parser lib paths) as shown in the DeepStream on Jetson guide and the upstream DeepStream-Yolo project.

      # after you create the elements in your Python pipeline
      pgie = Gst.ElementFactory.make("nvinfer", "primary-gie")
      pgie.set_property("config-file-path", "config_infer_primary_yolo26.txt")
      
      tracker = Gst.ElementFactory.make("nvtracker", "tracker")
      # set tracker properties from your tracker config the same way (or load them via configparser)
  7. AfaqKarimGitHub(bearbeitet)

    Title: Guidance Needed: Where to Modify Code to Add Custom Violation Logic and Modbus Output in DeepStream-YOLO Pipeline

    Hello DeepStream-YOLO Team,

    First of all, thank you for the excellent DeepStream-YOLO integration repository. I was able to successfully deploy a YOLO26 model using DeepStream on a Jetson Orin Nano (JetPack 6.1), and inference is working correctly using deepstream-app with config_infer_primary_yolo26.txt.


    My Use Case

    I am building an industrial safety system. After YOLO detection, if there is violation i have to send 0 or 1 through modbus to the plc: .

    So I need to integrate custom logic after detection results.


    My Question

    In this DeepStream-YOLO setup, in which file or location should I add my custom logic?

    Specifically, I want to know:

    • Should I modify:

      • nvdsparsebbox_Yolo.cpp inside nvdsinfer_custom_impl_Yolo?
      • Or write a custom DeepStream app (like deepstream-test1 / deepstream-test3)?
      • Or add a probe function after nvinfer in the pipeline?

    Because I understand that:

    • Parsing .so is only for decoding bounding boxes,
    • But my requirement is to process detections and send a Modbus signal continuously.

    So I want guidance on the recommended DeepStream architecture for this.


    My Current Setup
    • Jetson Orin Nano – JetPack 6.1
    • DeepStream-YOLO repo working
    • YOLO26 model inference OK
    • Using deepstream-app -c deepstream_app_config.txt

    Goal

    After detection → evaluate violation → send Modbus 0/1 signal in real-time.

    I would really appreciate guidance on:

    • Best file/place to implement this logic,
    • Any example for accessing detection metadata in DeepStream-YOLO.

    Thank you again for your great work 🙏

    1. Glenn JocherUltralytics

      You generally shouldn’t put violation/Modbus logic inside nvdsparsebbox_Yolo.cpp (keep the custom parser .so focused on decoding tensors → boxes); the recommended DeepStream architecture is to write a small custom DeepStream app (C/C++ or Python) and attach a pad-probe after nvinfer (or after nvtracker if you want stable IDs) to read NvDsObjectMeta and then publish your Modbus 0/1 in a non-blocking way (e.g., queue + worker thread), while still following the config/export flow in our Jetson DeepStream + TensorRT guide and the marcoslucianops/DeepStream-Yolo repository.

      // Probe callback (attach to a pad after nvinfer/nvtracker, e.g. OSD sink pad)
      static GstPadProbeReturn probe_cb(GstPad* pad, GstPadProbeInfo* info, gpointer user_data) {
        GstBuffer* buf = (GstBuffer*)info->data;
        NvDsBatchMeta* batch = gst_buffer_get_nvds_batch_meta(buf);
        for (NvDsMetaList* lf = batch->frame_meta_list; lf; lf = lf->next) {
          NvDsFrameMeta* f = (NvDsFrameMeta*)lf->data;
          for (NvDsMetaList* lo = f->obj_meta_list; lo; lo = lo->next) {
            NvDsObjectMeta* o = (NvDsObjectMeta*)lo->data;
            // o->class_id, o->confidence, o->rect_params; compute “violation” then enqueue Modbus 0/1
          }
        }
        return GST_PAD_PROBE_OK;
      }

      If you share whether you need “violation” per-frame or latched with hysteresis (and whether you’re using nvtracker), reply here and we can suggest the cleanest probe point and metadata fields to use.

    2. AfaqKarimGitHub

      Hi @glenn-jocher — thanks, that makes sense.

      My requirements:

      Input: RTSP (H.264) on Jetson Orin Nano (JP 6.1 / DS 7.1)

      Throughput: ~25 FPS

      Tracking: Not using nvtracker (I only need a global safety signal, not per-person IDs)

      Decision: Per-frame violation, but I’m open to latching / hysteresis if that’s the recommended way to avoid flicker.

      Output: Modbus TCP to PLC; I need to continuously send 0/1 (currently planning to write a coil bit), e.g. modbus_write_bit(coil_addr, value) at ~25Hz (or “send on change” if better).

      Violation rule (current):

      I define a polygon zone (danger/no-go area).

      Violation = 1 if a detected person bbox is fully inside the polygon (all 4 corners inside).

      Violation = 0 otherwise.

      Questions to confirm best architecture:

      Probe location: since I’m not using tracker, is the best place a pad-probe on nvinfer src pad (or OSD sink pad)?

      Metadata fields: I’m reading from NvDsObjectMeta → class_id, confidence, rect_params (left/top/width/height). Is that the correct/standard way?

      Best practice for Modbus: should I publish every frame (25Hz), or only on state change with a small debounce/hysteresis window (e.g., require N consecutive frames to assert violation)?

      If you can point to the cleanest DeepStream sample to start from (e.g., deepstream-test3 or deepstream-app custom plugin approach) and the recommended probe pad in that pipeline, I’ll follow that pattern.

      Thanks again 🙏

  8. SaarulogGitHub

    Hello, Deepstream Clarity question please.

    I notice the Nvidia Deepstream_python_app sample application use python file and one or more configuration text files. While Ultralytics Deepstream_Yolo uses two configuration text files.

    1. Could you please explain why Deepstream_Yolo is different?

    2. This command for Yolo26 "python3 export_yolo26.py -w yolo26s.pt" does not seem to generate a working .onnx model file but works with previous Yolo models(Ex. Yolo11). What are my options to get this to work?

    Thank you for your help and time.

    1. Glenn JocherUltralytics(bearbeitet)

      DeepStream-Yolo isn’t fundamentally “different” from deepstream_python_apps—it just splits configuration the way deepstream-app expects: deepstream_app_config.txt describes the full pipeline/sources/sinks, while config_infer_primary_yolo26.txt is the nvinfer (GIE) config that points to the ONNX/engine and the custom YOLO parser library; the Python sample builds more of the pipeline in code so you’ll see fewer/different config files even though the same DeepStream components are in play (see the DeepStream on Jetson + Ultralytics YOLO26 guide).

      For the YOLO26 ONNX export, it almost always comes down to a JetPack/DeepStream compatibility mismatch with --dynamic/--opset (DeepStream 6.0.1 and earlier need opset=12, while newer DeepStream uses the exports shown in the guide), so please paste the full terminal output from the export command (text, not a screenshot) and your yolo checks output so we can see your exact JetPack/DeepStream/Python/Ultralytics versions (also double-check you followed the Jetson setup in the Jetson quickstart).

    2. SaarulogGitHub

      Hello. Thank you for the quick response. below is the terminal output.

      Starting: yolo26s.pt Opening YOLO26 model YOLO26s summary (fused): 122 layers, 9,496,140 parameters, 0 gradients, 20.7 GFLOPs Creating labels.txt file Exporting the model to ONNX W0205 20:50:46.390000 684277 torch/onnx/_internal/exporter/_compat.py:125] Setting ONNX exporter to use operator set version 18 because the requested opset_version 17 is a lower version than we have implementations for. Automatic version conversion will be performed, which may not be successful at converting to the requested version. If version conversion is unsuccessful, the opset version of the exported model will be kept at 18. Please consider setting opset_version >=18 to leverage latest ONNX features W0205 20:50:48.526000 684277 torch/onnx/_internal/exporter/_schemas.py:455] Missing annotation for parameter 'input' from (input, boxes, output_size: 'Sequence[int]', spatial_scale: 'float' = 1.0, sampling_ratio: 'int' = -1, aligned: 'bool' = False). Treating as an Input. W0205 20:50:48.527000 684277 torch/onnx/_internal/exporter/_schemas.py:455] Missing annotation for parameter 'boxes' from (input, boxes, output_size: 'Sequence[int]', spatial_scale: 'float' = 1.0, sampling_ratio: 'int' = -1, aligned: 'bool' = False). Treating as an Input. W0205 20:50:48.528000 684277 torch/onnx/_internal/exporter/_schemas.py:455] Missing annotation for parameter 'input' from (input, boxes, output_size: 'Sequence[int]', spatial_scale: 'float' = 1.0). Treating as an Input. W0205 20:50:48.528000 684277 torch/onnx/_internal/exporter/_schemas.py:455] Missing annotation for parameter 'boxes' from (input, boxes, output_size: 'Sequence[int]', spatial_scale: 'float' = 1.0). Treating as an Input. The model version conversion is not supported by the onnxscript version converter and fallback is enabled. The model will be converted using the onnx C API (target version: 17). Failed to convert the model to the target version 17 using the ONNX C API. The model was not modified Traceback (most recent call last): File "/home/shamsee/Shamsee/lib/python3.10/site-packages/onnxscript/version_converter/init.py", line 127, in call converted_proto = _c_api_utils.call_onnx_api( File "/home/shamsee/Shamsee/lib/python3.10/site-packages/onnxscript/version_converter/_c_api_utils.py", line 65, in call_onnx_api result = func(proto) File "/home/shamsee/Shamsee/lib/python3.10/site-packages/onnxscript/version_converter/init.py", line 122, in _partial_convert_version return onnx.version_converter.convert_version( File "/home/shamsee/Shamsee/lib/python3.10/site-packages/onnx/version_converter.py", line 39, in convert_version converted_model_str = C.convert_version(model_str, target_version) RuntimeError: /github/workspace/onnx/version_converter/BaseConverter.h:65: adapter_lookup: Assertion false failed: No Adapter To Version $17 for Resize Done: yolo26s.onnx

    3. Glenn JocherUltralytics(bearbeitet)

      That log shows PyTorch is actually exporting at opset 18 and then failing to down-convert to opset 17 (No Adapter To Version 17 for Resize), so the fix is to export with an opset that matches what the exporter is using (>=18) instead of forcing 17:

      python3 export_yolo26.py -w yolo26s.pt --opset 18

      If you’re on an older DeepStream/TensorRT stack that truly requires lower opset (e.g. DeepStream 6.0.1), you’ll need the DeepStream 6.0.1 and earlier setting from the guide (opset=12) and typically an older PyTorch ONNX exporter that can produce opset 12 cleanly; please paste your yolo checks output and the exact DeepStream nvinfer ONNX parsing error so we can align this to your JetPack/DeepStream version (see the DeepStream on Jetson + Ultralytics YOLO26 guide and the Jetson quickstart).

    4. SaarulogGitHub(bearbeitet)

      smh, User Error. :-) I forgot about the steps at https://docs.ultralytics.com/guides/nvidia-jetson/ . It works after following steps!!!

      One last issue for Segmentation ONNX conversion. Hopefully this is another user error. python3 export_yolo26.py -w yolo26s-seg.pt

      I got these error:

      Starting: yolo26s-seg.pt Opening YOLO26 model YOLO26s-seg summary (fused): 139 layers, 10,396,300 parameters, 0 gradients, 34.2 GFLOPs Creating labels.txt file Exporting the model to ONNX Traceback (most recent call last): File "/home/shamsee/ultralytics/export_yolo26.py", line 157, in main(args) File "/home/shamsee/ultralytics/export_yolo26.py", line 116, in main torch.onnx.export( File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/onnx/utils.py", line 549, in export _export( File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/onnx/utils.py", line 1641, in _export graph, params_dict, torch_out = _model_to_graph( File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/onnx/utils.py", line 1184, in _model_to_graph graph, params, torch_out, module = _create_jit_graph(model, args) File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/onnx/utils.py", line 1060, in _create_jit_graph graph, torch_out = _trace_and_get_graph_from_model(model, args) File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/onnx/utils.py", line 964, in _trace_and_get_graph_from_model trace_graph, torch_out, inputs_states = torch.jit._get_trace_graph( File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/jit/_trace.py", line 1502, in _get_trace_graph outs = ONNXTracedModule( File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1714, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1725, in _call_impl return forward_call(*args, **kwargs) File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/jit/_trace.py", line 141, in forward graph, out = torch._C._create_graph_by_tracing( File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/jit/_trace.py", line 132, in wrapper outs.append(self.inner(*trace_inputs)) File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1714, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1725, in _call_impl return forward_call(*args, **kwargs) File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1704, in _slow_forward result = self.forward(*input, **kwargs) File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/nn/modules/container.py", line 249, in forward input = module(input) File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1714, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1725, in _call_impl return forward_call(*args, **kwargs) File "/home/shamsee/Sentinel_yolo26/Sentinel_proj/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1704, in _slow_forward result = self.forward(*input, **kwargs) File "/home/shamsee/ultralytics/export_yolo26.py", line 34, in forward x = x.transpose(1, 2) AttributeError: 'tuple' object has no attribute 'transpose'

      Thanks for your help and time.

    5. Glenn JocherUltralytics

      That traceback is expected with yolo26*-seg: the export_yolo26.py you’re using (from DeepStream-Yolo) is built around detection-only outputs, while segmentation models return multiple outputs (so you end up with a tuple and hit the transpose failure); for DeepStream segmentation please use the dedicated DeepStream-Yolo-Seg project (its supported-model list currently covers YOLO11/YOLOv8 seg), and if you specifically need YOLO26-Seg in DeepStream please open a report in DeepStream-Yolo-Seg Issues with your JetPack/DeepStream versions plus yolo checks so it’s trackable.

  9. lovechang1986GitHub

    I'm working on integrating SAHI with YOLOv11 and deploying it on a Jetson device using DeepStream. The original image size is 14401080, and I plan to split it into 640640 sub-images with overlaps between different sub-images. Are there any good methods for this?

    Additionally, I still hope to use DeepSort for inference and tracking after obtaining the final image.

    1. Glenn JocherUltralytics

      SAHI-style slicing isn’t something DeepStream handles automatically, so you’ll either need to slice frames before they enter the DeepStream pipeline (then offset + merge all tile detections back into full-frame coordinates before tracking), or implement ROI/tiling as a DeepStream preprocess step (e.g., via nvdspreprocess or a small custom plugin) so the primary GIE sees a batched set of crops; on Jetson it’s often simpler/faster to avoid slicing and instead run a single-pass TensorRT engine at a larger imgsz if latency allows (and YOLO26 is the recommended starting point for new deployments). If you plan to track inside DeepStream, put the tracker after you’ve merged detections to full-frame coordinates; DeepStream’s built-in nvtracker works out of the box, while DeepSORT specifically typically requires custom integration rather than a drop-in switch. If you paste your JetPack/DeepStream versions and your current deepstream_app_config.txt into this discussion, we can suggest the cleanest path based on the exact pipeline; the baseline export + DeepStream wiring is in the Jetson DeepStream guide and Jetson quickstart.