Combine Segmentation and Detection model (Yolov7 & Yolov8)

[FazanAfzal]

Search before asking

• I have searched the YOLOv8 issues and discussions and found no similar questions.

Question

I have trained multiple models. One model is a segmentation model, which is YOLOv7. The other is a detection model, which is YOLOv8. I want to combine these two models. Is it possible? Does YOLOv8 have any features related to this?

Additional

No response

[github-actions]

👋 Hello @FazanAfzal, 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]

@FazanAfzal hello! Combining a YOLOv7 segmentation model with a YOLOv8 detection model directly within the same framework is not supported out-of-the-box. Each version of YOLO (v7 and v8) operates independently with its own architectural design and functionalities.

However, you can integrate the outputs of both models in your application logic. Simply run each model separately on your input data, then merge or analyze their outputs according to your requirements. Here is a very basic Python example to illustrate how you might approach this:

from ultralytics import YOLO

# Load your trained models
model_v7 = YOLO('path/to/yolov7_segmentation_model.pt')
model_v8 = YOLO('path/to/yolov8_detection_model.pt')

# Process the same image with both models
img = 'path/to/image.jpg'
segmentation_results = model_v7(img)
detection_results = model_v8(img)

# Now, you can combine the results from segmentation_results and detection_results as needed

Remember, the actual integration and usage might depend on what exactly you need from these combined results. This approach allows using the specific strengths of both models while maintaining flexibility in processing and outcome.