if there are multi detected targets of the same class in output, how are they sorted?

[zssure-thu]

❔Question

if there are multi detected targets of the same class in output, how are they sorted?

Additional context

As shown in the picture above, it contains two persons, the left one and the right one. And they are recorded in the first two lines in label file XXX.txt, like" 0.481719 0.634028 0.690625 0.713278" and "0.741094 0.524306 0.314750 0.933389". I want to know is there a sorting logic in the label file?

[github-actions[bot]]

👋 Hello @zssure-thu, thank you for your interest in YOLOv3 🚀! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://www.ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

Environments

YOLOv3 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Google Colab and Kaggle 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 YOLOv3 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv3 training (train.py), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@zssure-thu there is no default sorting on labels or predictions within an image.

[zssure-thu]

@glenn-jocher > there is no default sorting on labels or predictions within an image Thanks. So if we want to trace the target man, we should do post-processing on labels by ourselves.

[glenn-jocher]

@zssure-thu actually I just remembered, I think the outputs in detect.py at least are sorted by reverse confidence, lowest first. This is to allow the higher confidence boxes to overlay the lower confidence ones if there is a conflict.

[zssure-thu]

@zssure-thu actually I just remembered, I think the outputs in detect.py at least are sorted by reverse confidence, lowest first. This is to allow the higher confidence boxes to overlay the lower confidence ones if there is a conflict.

@glenn-jocher THANKS.

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[glenn-jocher]

@zssure-thu you're welcome! Always happy to help. The YOLO community and Ultralytics team are constantly working to improve the framework.