model.predictor returns None

[PatilMayurS]

Search before asking

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

Question

model.predictor returns None instead of "ultralytics.models.yolo.detect.predict.DetectionPredictor"

from ultralytics import YOLO
model = YOLO("yolov8n.pt")
model.predictor  

returns None.

I am trying to update model.predictor.inference method to custom function with openvino gpu compiled model like below:

def infer(*args):
    result = det_compiled_model(args)
    return torch.from_numpy(result[0])

det_model.predictor.inference = infer
det_model.predictor.model.pt = False

Additional

No response

[github-actions[bot]]

👋 Hello @PatilMayurS, 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]

Hello! It looks like you're trying to access the predictor attribute directly from the YOLO model instance, which isn't initialized by default. You need to explicitly create a DetectionPredictor instance and pass the necessary arguments. Here's how you can do it:

from ultralytics import YOLO
from ultralytics.models.yolo.detect import DetectionPredictor

model = YOLO("yolov8n.pt")
predictor = DetectionPredictor(model=model)

Now, you can modify the inference method of your predictor as needed:

def infer(*args):
    result = det_compiled_model(args)
    return torch.from_numpy(result[0])

predictor.inference = infer

This should set up your custom inference function correctly. Let me know if you need further assistance! 😊

[PatilMayurS]

Hello! It looks like you're trying to access the predictor attribute directly from the YOLO model instance, which isn't initialized by default. You need to explicitly create a DetectionPredictor instance and pass the necessary arguments. Here's how you can do it:

from ultralytics import YOLO
from ultralytics.models.yolo.detect import DetectionPredictor

model = YOLO("yolov8n.pt")
predictor = DetectionPredictor(model=model)

Now, you can modify the inference method of your predictor as needed:

def infer(*args):
    result = det_compiled_model(args)
    return torch.from_numpy(result[0])

predictor.inference = infer

This should set up your custom inference function correctly. Let me know if you need further assistance! 😊

Thanks Glenn. Yes, you are correct. I had tried this method and it worked.

[glenn-jocher]

Great to hear that it worked for you! If you have any more questions or need further assistance as you continue with your project, feel free to reach out. Happy coding! 😊