yolov5 on Intel compute stick2?

[sujithgunturu]

❔Question

How to run my yolov5 with weights "best.pt" on intel compute stick.

Additional context

I have trained yolo on 3200 images with yolo large model. Then converted ".pt" to ".onnx" with "export.py". Later converted ".onnx" format to ".bin" and ".xml" format with openvino's model optimizer to run the model on intel compute stick. All the predictions done are incorrect and make no sense. for example: confidence and class label are negative. how to do it in right way.

I have trained my yolo in this way
python train.py --img 1024 --batch 24 --epochs 100 --data wheat.yaml --cfg models/yolov5l.yaml --name wml

[github-actions]

👋 Hello @sujithgunturu, 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://www.ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

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), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@sujithgunturu we don't have an NCS2 tutorial, but one thing I would advise you is to first try to deploy an official model before trying to deploy your custom trained model. This way you can isolate sources of error and have a better understanding of where to focus your debugging efforts.

[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/pricing
• 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 ⭐!

[glenn-jocher]

@sujithgunturu good news 😃! Your original issue may now be fixed ✅ in PR #6057. This PR adds native YOLOv5 OpenVINO export:

python export.py --include openvino

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 🚀!

[Averen19]

Hi, I have trained a custom dataset and would like to deploy on the NCS2 using Raspberry Pi. I converted the .pt file to .xml with the python export.py --include openvino code. However, my class_ids name are wrong as it still shows the original class ids like people and bicycle for class ids 0 and 1. Any solution?

[glenn-jocher]

@Averen19 answered in #7076

[Averen19]

hey @sujithgunturu, did you manage to run your yolo model on ncs2? If you did, do you mind sharing the code to deploy the model after converting to ir format?