The speed averaged over COCO val images include pre-process,inference and post-process or only inference?

[xiaomafei]

Search before asking

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

Question

Hi, friend, I have a question, the speed you tested averaged over COCO val images both on CPU ONNX and A100 TensorRT include pre-process,inference and post-process or only inference?

Additional

No response

[github-actions[bot]]

👋 Hello @xiaomafei, 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.

[xiaomafei]

sorry, not found answer

[pderrenger]

@xiaomafei the speed measurements averaged over COCO val images include the entire process: pre-processing, inference, and post-processing. This comprehensive approach ensures that the reported times reflect the real-world performance you can expect when deploying the models. If you have any further questions or need additional details, feel free to ask!