The judgment results of the same environment model are inconsistent

[hemingwinner]

Search before asking

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

Question

I am using version 8.0.222 of Ultralytics and trained based on the base model yolov8x-cls.pt. The train and val sets contain the same images. I trained twice, with the only difference being that the filenames of the images were modified. When testing the two models with the same images, I found that the results were inconsistent. I don't know what caused this. I hope to get your reply. Thank you.

Additional

No response

[github-actions[bot]]

👋 Hello @hemingwinner, 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.

[hemingwinner]

You don't seem to understand my problem.

[Y-T-G]

That's normal. Different training runs can lead to different performance and results

[hemingwinner]

I have trained twice, but the images remain unchanged, except for the file name of the second image being modified. Will this cause the two models to be inconsistent?

That's normal. Different training runs can lead to different performance and results

[Y-T-G]

Could be related to this

https://github.com/ultralytics/ultralytics/issues/13509

[hemingwinner]

Well, thank you. Let me see if I can solve my problem.

[pderrenger]

You're welcome! If you continue to experience issues, please ensure you're using the latest version of the Ultralytics package. Sometimes, updates can resolve unexpected behaviors. If the problem persists, feel free to provide more details, and we'll do our best to assist you further.