Interpretation Training Results (M) vs. (B)

[katiefux]

Dear reader,

I have trained a model and i have a question regarding the results file that shows the loss/precision/recall/mAP... of every epoch:
What is the meaning of (M) vs. (B) in brackets for the measures precision, recall, mAP_0.5 and mAP_0.5:0.95?

Thanks a lot in advance for a response!

[github-actions]

👋 Hello @katiefux, 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]

@katiefux hello!

(M) refers to "macro" average, which calculates the average performance metric over each class. (B) refers to "best" performance metric achieved by the model during the training process. So for example, "mAP_0.5 (B)" would refer to the best mean average precision at an IoU threshold of 0.5 achieved by the model during training, while "mAP_0.5 (M)" would refer to the macro average mean average precision at an IoU threshold of 0.5 across all classes.

I hope this answers your question! Let us know if there's anything else we can help you with.

[github-actions]

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐

[uri-el99]

Hi dear @glenn-jocher, thanks for all your support and hope you are doing it pretty well.
Considering what you mentioned before, I am still a little bit confused. I have read other similar issues, but when do I consider M as Macro and B as best? and also Mask or Bos when using segmentation task.

[glenn-jocher]

@uri-el99 hello! In the context of YOLOv5, (M) stands for "macro" average and (B) for "best" performance during training. For segmentation tasks, "Mask" refers to the segmentation mask, while "Box" refers to bounding box metrics. Let me know if you need further clarification!

[uri-el99]

@glenn-jocher so basically for YOLOv5 (M) and (B) refer to Macro and Best, but when talking about YOLOv8 and YOLOv9 when doing segmentation, (M) and (B) are Mask and Box, am I right?

[glenn-jocher]

Yes, that's correct. In YOLOv5, (M) and (B) refer to Macro and

[Paryavi]

Hi @glenn-jocher I am using Yolov8 for detection, and I get (B) in performance metrics. Is the following statement correct?

In Yolov8, for object detection, in Detmetrics class, it looks like B also means bounding box;
https://github.com/ultralytics/ultralytics/blob/77c3c0aaac25e8738c0fe976f3e17c65aca12445/ultralytics/utils/metrics.py#L855

not to be confused with Mask in same metrics.py file where M is used in SegmentMetrics class;
https://github.com/ultralytics/ultralytics/blob/77c3c0aaac25e8738c0fe976f3e17c65aca12445/ultralytics/utils/metrics.py#L1017