Fail to run torchscript after exporting

[Andy824]

Search before asking

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

Question

I run my yolov5 model through colab. It works successfully. However, after exporting my yolov5m best.pt to torchscript format. The error occurs. The error message is as shown below. Does anyone know the reason? Thank you

!

Additional

No response

[github-actions]

👋 Hello @Andy824, 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.

[Andy824]

[Andy824]

I retrained my model again, but after exporting to torchscript, I got the same error. Does anyone encounter the same problem?

[glenn-jocher]

@Andy824 thanks for the bug report! We recently updated this section of the code, I'll take a look.

[glenn-jocher]

@Andy824 I'm not able to reproduce any errors using the pretrained YOLOv5s model exported to torchscript. Are you sure you are using the latest code?

[glenn-jocher]

@Andy824 EDIT: able to reproduce on custom trained model. Will investigate.

[glenn-jocher]

Traced to JSON dumps converting int keys to strings during export, i.e.
https://stackoverflow.com/questions/1450957/pythons-json-module-converts-int-dictionary-keys-to-strings

[Andy824]

Thank you for your reply~ ^ ^

[glenn-jocher]

@Andy824 good news 😃! Your original issue may now be fixed ✅ in PR #9015. 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 🚀!

[Andy824]

Thank you very much

[glenn-jocher]

@Andy824 you're very welcome! I'm here anytime if you have more questions, feature requests or bug reports. Happy to help!