how to convert pt to onnx to trt

[gdfapokgdpafog]

Search before asking

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

Question

how to convert pt to onnx to trt

Additional

im doing this

python export.py --weights best.pt --include onnx --opset 12

after trtexec --onnx=best.onnx --saveEngine=best.trt

after I try to load the model I get this

I used to be able to do it, but six months later I forgot how I did it.

Please help

[github-actions]

👋 Hello @gdfapokgdpafog, 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 a minimum reproducible example to help us debug it.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset image examples and training logs, 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 may 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.

Introducing YOLOv8 🚀

We're excited to announce the launch of our latest state-of-the-art (SOTA) object detection model for 2023 - YOLOv8 🚀!

Designed to be fast, accurate, and easy to use, YOLOv8 is an ideal choice for a wide range of object detection, image segmentation and image classification tasks. With YOLOv8, you'll be able to quickly and accurately detect objects in real-time, streamline your workflows, and achieve new levels of accuracy in your projects.

Check out our YOLOv8 Docs for details and get started with:

pip install ultralytics

[gdfapokgdpafog]

cuda 11.6

tensorrt 8.4.1.5

pytorch 1.9.0

[glenn-jocher]

@gdfapokgdpafog hello,

Thank you for reaching out! It looks like you're on the right track with exporting your model from PyTorch to ONNX and then to TensorRT. Let's go through the steps to ensure everything is set up correctly.

1. Export to ONNX:
   You've already done this with:

   python export.py --weights best.pt --include onnx --opset 12

   This should generate best.onnx.

2. Convert ONNX to TensorRT:
   Using trtexec is the correct approach:

   trtexec --onnx=best.onnx --saveEngine=best.trt

3. Loading the TensorRT Engine:
   Ensure that your environment is correctly set up to use TensorRT. Sometimes, issues can arise from mismatched versions or incorrect paths.

Given the error message you encountered, it seems there might be an issue with the TensorRT engine creation. Here are a few things to check:

• Compatibility: Ensure that your CUDA, TensorRT, and PyTorch versions are compatible. You mentioned using CUDA 11.6, TensorRT 8.4.1.5, and PyTorch 1.9.0. These should generally be compatible, but it's always good to double-check the NVIDIA compatibility matrix.

• ONNX Model: Verify that the ONNX model is correctly exported and can be loaded without errors. You can use the onnx Python package to check the model:

  import onnx
  
  model = onnx.load("best.onnx")
  onnx.checker.check_model(model)

• TensorRT Logs: When running trtexec, add the --verbose flag to get more detailed logs, which can help diagnose the issue:

  trtexec --onnx=best.onnx --saveEngine=best.trt --verbose

If the issue persists, please provide any additional logs or error messages you receive. This will help us better understand the problem and provide more targeted assistance.

For more detailed instructions on exporting models, you can refer to the Ultralytics YOLOv5 Model Export Documentation.

Feel free to reach out if you have any further questions or need additional assistance. The YOLO community and the Ultralytics team are here to help!

[gdfapokgdpafog]

onnx model is fine

log
log.txt

but I've already done it all and I've succeeded, I don't understand why it's not working now and an error pops up

maybe I used other parameters when converting to onnx

if you can tell me what parameters I can use when converting to onnx and trt and so that everything works for me

[gdfapokgdpafog]

fixed, sorry for bothering

[glenn-jocher]

Hello @gdfapokgdpafog,

No problem at all! I'm glad to hear that you were able to resolve the issue. If you have any more questions or run into any other issues in the future, feel free to reach out. The YOLO community and the Ultralytics team are always here to help!

If you ever need to revisit the parameters for converting models, you can always refer to the Ultralytics YOLOv5 Model Export Documentation for detailed guidance.

Happy coding! 🚀

[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 ⭐