How to Use Export YOLO ONNX model to use the ZED Custom Object Detection

Introduction #

This page will show you how to export a YOLO model into an ONNX file to use with the ZED YOLO TensorRT inference example, or the CUSTOM_YOLOLIKE_BOX_OBJECTS mode in the native ZED SDK Object Detection module.

This allows you to train your custom model using Ultralytics YOLO (v5, v8, v10, v11, v12), YOLOv6, or YOLOv7.

It can also be used with the default model trained on the COCO dataset (80 classes) provided by the framework maintainers. A custom detector can be trained using the same architecture. These tutorials walk you through the workflow of training a custom detector:

It enables the use of ZED 3D cameras with YOLO object detection, adding 3D localization and tracking to the most recent YOLO models using your own classes.

YOLO Comparison in terms of latency-accuracy (left) and FLOPs-accuracy (right) trade-offs (from YOLOv12)

Workflow #

The process is as follows:

  1. Train your model or use an existing state-of-the-art (SOTA) model.
  2. Export it into an ONNX file.
  3. Load the ONNX file into the SDK or sample to generate an optimized model. This process uses the TensorRT framework to run inference and requires an initial step of inference engine generation.

ZED SDK samples are available on GitHub:

Ultralytics YOLO (v5, v8, v10, v11, v12) #

Installing ultralytics #

ultralytics can be installed directly from pip using the following command:

python -m pip install -U ultralytics

ONNX file export #

In this documentation, we’ll use the CLI for export https://docs.ultralytics.com/modes/export/

YOLOv12 #

yolo export model=yolo12n.pt format=onnx simplify=True dynamic=False imgsz=608

YOLOv11 #

yolo export model=yolo11n.pt format=onnx simplify=True dynamic=False imgsz=608

YOLOv10 #

yolo export model=yolov10n.pt format=onnx simplify=True dynamic=False imgsz=608

YOLOv8 #

yolo export model=yolov8n.pt format=onnx simplify=True dynamic=False imgsz=608

YOLOv5 #

yolo export model=yolov5n.pt format=onnx simplify=True dynamic=False imgsz=608

Variants #

For each model the variant (n, s, m, l, x) can be selected, like:

yolo export model=yolo12x.pt format=onnx simplify=True dynamic=False imgsz=608

Dynamic size #

The model can also used dynamic dimensions:

yolo export model=yolo12m.pt format=onnx simplify=True dynamic=True

Custom model #

For a custom model model the weight file can be changed:

yolo export model=yolov8l_custom_model.pt format=onnx simplify=True dynamic=False imgsz=512

Please refer to the corresponding documentation for more details https://github.com/ultralytics/ultralytics

YOLOv6 #

The sample was mainly tested with YOLOv6 v3.0 but should work with other version with minor to no modifications.

Installing yolov6 #

YOLOv6 can be installed directly from pip using the following command:

git clone https://github.com/meituan/YOLOv6
cd YOLOv6
pip install -r requirements.txt
pip install onnx>=1.10.0

ONNX file export #

wget https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6s.pt
python ./deploy/ONNX/export_onnx.py \
    --weights yolov6s.pt \
    --img 640 \
    --batch 1 \
    --simplify

For a custom model model the weight file can be changed:

python ./deploy/ONNX/export_onnx.py \
    --weights yolov6l_custom_model.pt \
    --img 640 \
    --batch 1 \
    --simplify

Please refer to the corresponding documentation for more details https://github.com/meituan/YOLOv6/tree/main/deploy/ONNX

YOLOv7 #

Installing yolov7 #

YOLOv7 can be installed directly from pip using the following command:

git clone https://github.com/WongKinYiu/yolov7.git
cd yolov7
python -m pip install -r requirements.txt

ONNX file export #

In this documentation, we’ll use the export script export.py

python export.py --weights ./yolov7-tiny.pt --grid --simplify --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640

📌 Note: The --end2end option must NOT be used to run the inference with the ZED SDK for compatibility reasons.

For a custom model model the weight file can be changed:

python export.py --weights ./yolov7_custom_model.pt --grid --simplify --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 512 512

Please refer to the corresponding documentation for more details https://github.com/WongKinYiu/yolov7/tree/main?tab=readme-ov-file#export

YOLOv5 #

Installing yolov5 #

YOLOv5 can be installed directly from pip using the following command:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

ONNX file export #

python export.py --weights yolov5s.pt --include onnx --imgsz 640

For a custom model model the weight file can be changed:

python export.py --weights yolov8l_custom_model.pt --include onnx

Please refer to the corresponding documentation for more details https://docs.ultralytics.com/yolov5/tutorials/model_export/