rt-detr about ultralytics

[github-actions]

👋 Hello @skyceeee, 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.

[skyceeee]

this is a bug report. ı did not solve this problem. The error ı got: AttributeError: 'RTDETRDecoder' object has no attribute 'stride. I got this error when I gave last.pt to the model

[glenn-jocher]

Hello! It looks like your issue arises from the RTDETRDecoder not having a stride attribute defined that is expected elsewhere in your code. This attribute is usually set in the model configuration or initialization phase.

A potential solution is to ensure that stride is appropriately defined and set in the RTDETRDecoder class. If you have access to the decoder class code, you can add self.stride = some_value in its __init__ method, where some_value matches the expected stride pattern used by your model/architecture.

If this doesn't resolve your issue, please provide additional context about where and how RTDETRDecoder is used or initialized to further diagnose the problem.