A very confusing issues about converting .pt to .onnx

[Greatlover]

Search before asking

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

YOLOv5 Component

No response

Bug

Hi, I'm getting the following error when trying to convert a Pytorch YoloV5 model to ONNX format:

Traceback (most recent call last):

File "E:\yolov5-master\py_to_onnx.py", line 17, in
torch.onnx.export(

File "E:\anaconda\envs\yolo_v5\lib\site-packages\torch\onnx\utils.py", line 504, in export
_export(

File "E:\anaconda\envs\yolo_v5\lib\site-packages\torch\onnx\utils.py", line 1506, in _export
with exporter_context(model, training, verbose):

File "E:\anaconda\envs\yolo_v5\lib\contextlib.py", line 117, in enter
return next(self.gen)

File "E:\anaconda\envs\yolo_v5\lib\site-packages\torch\onnx\utils.py", line 176, in exporter_context
with select_model_mode_for_export(

File "E:\anaconda\envs\yolo_v5\lib\contextlib.py", line 117, in enter
return next(self.gen)

File "E:\anaconda\envs\yolo_v5\lib\site-packages\torch\onnx\utils.py", line 137, in disable_apex_o2_state_dict_hook
for module in model.modules():

AttributeError: 'dict' object has no attribute 'modules'
No matter how I modify the code, using the official YoloV5 models or my own trained models, I get this error when converting to ONNX. Is there any way to resolve this? Any help would be greatly appreciated!

Environment

Python 3.9.0
pytroch 1.13.0+cu116
cuda 11.6
yolov5

Minimal Reproducible Example

Here is the .py code
import torch
import torch.nn

model_file = 'E:\yolov5-master\runs\train\exp9\weights\best.pt'

export_file = 'E:\yolov5-master\export_all\onnxs\try\train\fuck.onnx'

model = torch.load(model_file)

dummy_input = torch.randn(1, 2, 640, 640)

torch.onnx.export(
model,
dummy_input,
export_file,
opset_version=11
)

Additional

Here is the .py code
import torch
import torch.nn

model_file = 'E:\yolov5-master\runs\train\exp9\weights\best.pt'

export_file = 'E:\yolov5-master\export_all\onnxs\try\train\fuck.onnx'

model = torch.load(model_file)

dummy_input = torch.randn(1, 2, 640, 640)

torch.onnx.export(
model,
dummy_input,
export_file,
opset_version=11
)

Are you willing to submit a PR?

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

[github-actions]

👋 Hello @Greatlover, 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>=3.7.0 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):

• 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

[glenn-jocher]

@Greatlover hi there! It seems like you're encountering an error when trying to convert a PyTorch YOLOv5 model to ONNX format. The error message suggests that the 'dict' object you're using doesn't have the 'modules' attribute.

To resolve this issue, you need to load the YOLOv5 model using the torch.hub.load function instead of torch.load. Here's an updated version of your code:

import torch
import torch.nn as nn
import torchvision

model_file = 'E:\\yolov5-master\\runs\\train\\exp9\\weights\\best.pt'
export_file = 'E:\\yolov5-master\\export_all\\onnxs\\try\\train\\fuck.onnx'

model = torch.hub.load('ultralytics/yolov5', 'custom', path=model_file)

dummy_input = torch.randn(1, 2, 640, 640)

torch.onnx.export(
    model,
    dummy_input,
    export_file,
    opset_version=11
)

Make sure you have the latest version of YOLOv5 installed by running pip install --upgrade yolov5. Also, please ensure that you have the correct versions of PyTorch and CUDA installed. In your case, you mentioned using PyTorch 1.13.0, which seems to be a typo. It should be PyTorch 1.7.0 or above.

Let me know if this solves your issue, and don't hesitate to reach out if you have any further questions!

[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 ⭐