YoloV5-7.0 K-mean autoAnchor

[NedLee1005]

Search before asking

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

Question

Hello Guys,

When I execute K-mean autoanchor, the input image is 480, but the anchor output has an anchor height beyond 480

How can i solve this problem?

Hope you have a nice day.

Additional

No response

[github-actions]

👋 Hello @NedLee1005, 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]

@NedLee1005 hi there,

Thank you for reaching out! It seems like you are facing an issue with the YOLOv5 K-mean autoanchor process where the anchor height is exceeding the input image height of 480.

To address this problem, it is important to make sure that the anchor height does not exceed the input image dimensions. Here are a few suggestions that might help:

1. Check your input data: Ensure that your input images have a consistent height of 480 pixels. If the heights of your images vary, you may need to preprocess them to resize them to the desired dimensions.

2. Review the anchor generation code: Take a look at the code responsible for generating the anchors in the K-mean autoanchor script. Double-check the calculations and verify that the anchor heights are constrained within the dimensions of your input images.

3. Inspect your dataset: Check if there are any anomalies or inconsistencies in your dataset that might be causing this issue. Make sure that your dataset is properly annotated and that the bounding box coordinates are within the image boundaries.

If these suggestions do not resolve the problem, please provide more details about your specific setup and any error messages or logs you encounter. This will help us better understand the issue and provide you with more accurate guidance.

Once again, thank you for your question, and I hope this helps! Let me know if you have any further concerns.

Regards,
Glenn Jocher

[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 ⭐