converting .pt to onnx with dynamic flag

[git-hamza]

Search before asking

• I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

I am trying to convert .pt model to onnx, it successfully gets converted to onnx without the --dynamic flag but with it, it give me some error. I have tried to debug it but haven't had a luck for now. Have anybody else faced the same issue?

Additional

Execution command followed:
python3 export.py --weights checkpoints/yolov5n.pt --device 0 --include onnx

Error:
frame #55: __libc_start_main + 0xf3 (0x7f6a3025c083 in /lib/x86_64-linux-gnu/libc.so.6)
(function ComputeConstantFolding)
ONNX: export failure: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument index in method wrapper__index_select)

Note: Now I know it says that two device are detected but I clearly mentioned device=0 in argument and it works without dynamic flag.

[github-actions]

👋 Hello @git-hamza, 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]

@git-hamza thanks for the bug report! I am able to reproduce an error with the following command. Will ad a TODO to investigate:

python3 export.py --weights yolov5n.pt  --include onnx --dynamic --device 0

[glenn-jocher]

@git-hamza needs further investigation but workaround may be just to export on cpu and then run inference on any device:

[git-hamza]

@glenn-jocher Perfect. I will try to do that for now. Thank you for such a rapid reply. Meanwhile If I find the exact culprit, I will update here.

[glenn-jocher]

@git-hamza good news 😃! Your original issue may now be fixed ✅ in PR #8378. To receive this update:

• Git – git pull from within your yolov5/ directory or git clone https://github.com/ultralytics/yolov5 again
• PyTorch Hub – Force-reload model = torch.hub.load('ultralytics/yolov5', 'yolov5s', force_reload=True)
• Notebooks – View updated notebooks
• Docker – sudo docker pull ultralytics/yolov5:latest to update your image

Thank you for spotting this issue and informing us of the problem. Please let us know if this update resolves the issue for you, and feel free to inform us of any other issues you discover or feature requests that come to mind. Happy trainings with YOLOv5 🚀!