ONNX DNN inference bug: (-215:Assertion failed) inputs.size() in function 'getMemoryShapes'

[glenn-jocher]

I followed the tutorial to OpenCV inference with ONNX models， but it has some problems.

Originally posted by @longtimenoseeyou in #251 (comment)

Reproduce:

!python export.py --include onnx
!python detect.py --weights yolov5s.onnx --dnn

[github-actions]

👋 Hello @glenn-jocher, thank you for your interest in YOLOv5 🚀! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://ultralytics.com or email support@ultralytics.com.

Requirements

Python>=3.7.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

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

Environments

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

• Google Colab and Kaggle 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 (train.py), validation (val.py), inference (detect.py) and export (export.py) on macOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@longtimenoseeyou I would raise this issue directly on the opencv repository as the error originates in cv2.

[glenn-jocher]

@longtimenoseeyou in #8439 it looks like this issue is related to torch==1.12 and downgrading to torch<=1.11.0 will resolve the bug.

[longtimenoseeyou]

Thank you, Glenn, I solve the problem

[knoppmyth]

@longtimenoseeyou How did you solve this? Was it downgrading to 1.11? While that works, I cannot then train with 1.11 as it errors. At this point, I'd have to train w/ 1.12 then have another environment w/ 1.11 to export.

[longtimenoseeyou]

@knoppmyth Yeah, I downgraded to torch ==1.11. Now I train datasets normally and do not see any other problem

[longtimenoseeyou]

At the end of training with torch=1.11 , I get the error:
AttributeError: 'NoneType' object has no attribute '_free_weak_ref'

[knoppmyth]

@longtimenoseeyou I went back to an older container and notes... The error you get at the end of training w/ 1.11.0 is non-fatal.

[github-actions]

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

• Wiki – https://github.com/ultralytics/yolov5/wiki
• Tutorials – https://docs.ultralytics.com/yolov5
• Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

• Ultralytics HUB – https://ultralytics.com/hub
• Vision API – https://ultralytics.com/yolov5
• About Us – https://ultralytics.com/about
• Join Our Team – https://ultralytics.com/work
• Contact Us – https://ultralytics.com/contact

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 YOLOv5 🚀 and Vision AI ⭐!

[elw1ng]

@longtimenoseeyou in #8439 it looks like this issue is related to torch==1.12 and downgrading to torch<=1.11.0 will resolve the bug.

i got this error ONNX: export failure 0.0s: Unsupported ONNX opset version: 17
when tried to export onnx model from pt after downgraded to torch==1.11.0
on default version i got this error, even on colab

[fangfap]

python export.py --weights models/yolov5n.pt --opset 11 --include onnx
downgrade opset to 11 work for me :))

[glenn-jocher]

@fangfap great to hear that downgrading the ONNX opset version to 11 resolved the issue for you! Thank you for sharing your solution.