b.data[:, 5:5 + m.nc] in yolov5 v7.0

[Bian-666]

https://github.com/ultralytics/yolov5/blob/915bbf294bb74c859f0b41f1c23bc395014ea679/models/yolo.py#LL260C22-L260C22

In yolov5 v7.0, the expression b.data[:, 5:] was changed to b.data[:, 5:5 + m.nc]. What is the significance of this modification?

[github-actions]

👋 Hello @Bian-666, thank you for your interest in YOLOv5 🚀! 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 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.

Requirements

Python>=3.7.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

Environments

YOLOv5 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 YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training, validation, inference, export and benchmarks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

Introducing YOLOv8 🚀

We're excited to announce the launch of our latest state-of-the-art (SOTA) object detection model for 2023 - YOLOv8 🚀!

Designed to be fast, accurate, and easy to use, YOLOv8 is an ideal choice for a wide range of object detection, image segmentation and image classification tasks. With YOLOv8, you'll be able to quickly and accurately detect objects in real-time, streamline your workflows, and achieve new levels of accuracy in your projects.

Check out our YOLOv8 Docs for details and get started with:

pip install ultralytics

[glenn-jocher]

@Bian-666 hi! The modification on line 260 in yolov5/models/yolo.py is specific to multi-class detection. The variable m.nc corresponds to the number of classes in your dataset and the 5 + m.nc indicates that from the 6th column onwards, we consider the class probability distribution for each anchor box. This is done by passing only those columns to the sigmoid function, which returns values between 0 and 1 for each class. These values are then multiplied with the confidence score (the 5th column) to get the final score. This modification improves the accuracy of multi-class detection. Let me know if this helps!

[Bian-666]

Yes，it helps. Thank you for your prompt reply，thanks for your great work!

[glenn-jocher]

@Bian-666 you're welcome! I'm glad to hear that my response was helpful. Thanks for using YOLOv5 and don't hesitate to reach out if you have any other questions or issues in the future. Have a great day!