YOLOv5 MODEL CONVERSION

[879514175]

Search before asking

• I have searched the YOLOv5 issues and found no similar bug report.

YOLOv5 Component

No response

Bug

[ERROR:0@1.192] global onnx_importer.cpp:1036 handleNode DNN/ONNX: ERROR during processing node with 1 inputs and 1 outputs: [Floor]:(onnx_node!/model.11/Floor) from domain='ai.onnx'
Traceback (most recent call last):
File "/home/orbbec/pyorbbecsdk/examples/Orbbec-Depth-Sensing-Object-Detection-using-YOLOv5/depthScale_orbbec.py", line 135, in
net = cv2.dnn.readNet('models/yolov5s.onnx')
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
cv2.error: OpenCV(4.11.0) /io/opencv/modules/dnn/src/onnx/onnx_importer.cpp:1058: error: (-2:Unspecified error) in function 'handleNode'

Node [Floor@ai.onnx]:(onnx_node!/model.11/Floor) parse error: OpenCV(4.11.0) /io/opencv/modules/dnn/src/layers/elementwise_layers.cpp:260: error: (-215:Assertion failed) src.size == dst.size && src.type() == dst.type() && src.isContinuous() && dst.isContinuous() && src.type() == CV_32F in function 'forward'

Environment

No response

Minimal Reproducible Example

No response

Additional

No response

Are you willing to submit a PR?

• Yes I'd like to help by submitting a PR!

[UltralyticsAssistant]

👋 Hello @879514175, thank you for your interest in YOLOv5 🚀! This is an automated response to help you get started. An Ultralytics engineer will also review your issue and assist you soon.

If this is a 🐛 Bug Report, please provide a minimum reproducible example (MRE) to help us debug the problem. This should include the exact code, model files, and steps required to reproduce the error you are encountering.

If you're working on custom training or model export ❓, please share as much information as possible, such as model export commands, environment details, and your ONNX/OpenCV versions, and verify you are following our Tips for Best Training Results.

Requirements

Python>=3.8.0 with all requirements.txt installed including PyTorch>=1.8. To get started:

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

Environments

YOLOv5 can be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training, validation, inference, export and benchmarks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

Looking forward to your update! 😊

[879514175]

这是来自QQ邮箱的假期自动回复邮件。   您好，我最近正在休假中，无法亲自回复您的邮件。我将在假期结束后，尽快给您回复。

[879514175]

wget https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5s.pt
python export.py --weights yolov5s.pt --include onnx --opset 11 --dynamic

[pderrenger]

The OpenCV DNN Floor operation error you're encountering is a known compatibility issue. Try exporting your model without dynamic shapes and using a lower opset version that's better supported by OpenCV DNN:

python export.py --weights yolov5s.pt --include onnx --opset 9

OpenCV DNN has limited support for certain ONNX operations and dynamic shapes can cause parsing issues. If you still encounter problems, consider using ONNX Runtime instead of OpenCV DNN for inference, as it has broader ONNX operation support.

[github-actions]

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐

[879514175]

这是来自QQ邮箱的假期自动回复邮件。   您好，我最近正在休假中，无法亲自回复您的邮件。我将在假期结束后，尽快给您回复。

[pderrenger]

Thanks for the heads-up—when you’re back, please try exporting with ONNX simplification and validate the file; if OpenCV DNN still errors, test a different OpenCV build and share the export log plus cv2.version here.

# re-export with simplification
python export.py --weights yolov5s.pt --include onnx --simplify

# quick validity check
python - <<'PY'
import onnx, onnxruntime as ort
onnx.checker.check_model(onnx.load('yolov5s.onnx'))
ort.InferenceSession('yolov5s.onnx')  # should create without error
print("ONNX OK")
PY

See the Ultralytics Docs for details on exports: https://docs.ultralytics.com/modes/export/