分割？

[pjh11214]

Search before asking

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

Question

Segmentation code is instance segmentation or semantic segmentation？ I am optimistic that many data are said to be instance segmentation, then I want to until how to let the target output of the same class is a different color mask?

Additional

No response

[UltralyticsAssistant]

👋 Hello @pjh11214, thank you for reaching out and your interest in YOLOv5 🚀! This is an automated response to your query, and an Ultralytics engineer will assist you soon.

Please explore our ⭐️ Tutorials where you can dive into various tasks, including Custom Data Training and advanced sections.

If your query relates to setup or usage, please ensure you are following the setup instructions:

Requirements

Make sure you have Python>=3.8.0 installed, with all dependencies from requirements.txt including PyTorch>=1.8. Begin by running:

git clone https://github.com/ultralytics/yolov5
cd yolov5
pip install -r requirements.txt

Explore Environments

You can run YOLOv5 in verified environments for convenience:

• Notebooks:
• Google Cloud: See GCP Quickstart Guide
• Amazon: See AWS Quickstart Guide
• Docker: See Docker Quickstart Guide

For your segmentation question, understanding the distinction between instance and semantic segmentation is crucial. Ensure your implementation aligns with your segmentation needs. If this is a bug report or if you encounter unexpected behavior, kindly provide a minimum reproducible example.

Check Our Latest

Don't miss out on our latest YOLOv8 🚀! Learn more at YOLOv8 Docs and get started with:

pip install ultralytics

Feel free to refer to the YOLOv5 GitHub Actions to verify active testing status:

Thank you for your patience, and we're excited to assist you further! 😊

[pderrenger]

@pjh11214 yOLOv5 primarily supports object detection, not segmentation. For instance segmentation, you might consider using models like YOLOv5-IS or other frameworks specifically designed for segmentation tasks.