A generalized YOLOv8 model with DET, OBB, SEG and POSE tasks.

[zhouzq-thu]

Search before asking

• I have searched the YOLOv8 issues and found no similar feature requests.

Description

Currently, we can only use the YOLOv8 model to handle one of obb, seg and pose tasks.

Idea

Since one of the output layers of the YOLOv8 model has the output with shape as follows:

• det: [bs, num_classes + 4 * reg_max, lw, lh]
• obb: [bs, num_classes + 4 * reg_max + 1, lw, lh]
• seg: [bs, num_classes + 4 * reg_max + num_masks, lw, lh]
• pose: [bs, num_classes + 4 * reg_max + 3 * num_kpts, lw, lh]

We can define a generalized YOLOv8 model with output as follows:

• gen: [bs, num_classes + 4 * reg_max + is_obb + num_masks + 3 * num_kpts, lw, lh]

Use case

class GeneralizedHead(nn.Module):
    """YOLOv8 Generalized head."""
    def __init__(self, nc=80, is_obb=False, nm=0, npr=256, kpt_shape=None, ch=()):
        ...

With the generalized YOLOv8 model:

• If we want the obb+seg model, then set is_obb = True, nm = 32. (Is yolov8 able to do instance segmentation in obb box? #7918)
• If we want the seg+pose model, then set nm = 32, kpt_shape = (17, 3). (Combine segmentation and pose estimation #2405)

Additional

No response

Are you willing to submit a PR?

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

[github-actions]

👋 Hello @zhouzq-thu, thank you for your interest in Ultralytics YOLOv8 🚀! We recommend a visit to the Docs for new users where you can find many Python and CLI usage examples and where many of the most common questions may already be answered.

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.

Join the vibrant Ultralytics Discord 🎧 community for real-time conversations and collaborations. This platform offers a perfect space to inquire, showcase your work, and connect with fellow Ultralytics users.

Install

Pip install the ultralytics package including all requirements in a Python>=3.8 environment with PyTorch>=1.8.

pip install ultralytics

Environments

YOLOv8 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 Ultralytics CI tests are currently passing. CI tests verify correct operation of all YOLOv8 Modes and Tasks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@zhouzq-thu hello there! Thank you for your detailed suggestion regarding a generalized YOLOv8 model that can handle multiple tasks (DET, OBB, SEG, and POSE) in one framework. This is indeed a very interesting idea and could significantly enhance YOLOv8's versatility.

Your proposed approach to integrating a generalized head that can dynamically configure to handle combinations of different tasks is compelling. It would allow the user customization based on specific requirements, and using flags like is_obb, nm, and kpt_shape as parameters offers a straightforward method to toggle functionalities.

I encourage you to proceed with submitting a PR since you are already considering it. The community, including the development team, would greatly benefit from this capability and can provide feedback directly on your implementation. Looking forward to seeing your contribution! 😊🚀

Best of luck!

[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 ⭐