How to interpret the precision and recall vs epoch curve?

[YukunXia]

❔Question

If I understand correctly, the default train.py will call the test function to calculate the metrics, and the default conf_thred is 0.001. The final precision and recall I had were both pretty high: 0.984 and 0.883. I feel confused that such a small conf_thred could lead to a precision close to 1. I checked the P_curve.png, and at confidence close to 0, the precision decreased to 0, which makes sense to me, but seems to be contradictory to the 0.984 precision.

Additional context

My training curves:

P curve:

R curve:

PR curve:

[github-actions]

👋 Hello @YukunXia, 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 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://ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python>=3.6.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

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

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):

• 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 YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), validation (val.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@YukunXia P and R are reported at maximum F1 confidence, not at 0.001, which would not make any sense as then R would be near 1 and P would be near zero. See F1_curve.png for this value.

[YukunXia]

Thank you! F1 curve says "all classes 0.93 at 0.505", so the conf_thred for precision and recall is actually 0.505.

[glenn-jocher]

@YukunXia yes

[github-actions]

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

• Wiki – https://github.com/ultralytics/yolov5/wiki
• Tutorials – https://docs.ultralytics.com/yolov5
• Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

• Ultralytics HUB – https://ultralytics.com/hub
• Vision API – https://ultralytics.com/yolov5
• About Us – https://ultralytics.com/about
• Join Our Team – https://ultralytics.com/work
• Contact Us – https://ultralytics.com/contact

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 YOLOv5 🚀 and Vision AI ⭐!

[jet-c-21]

@glenn-jocher what kind of confidence represented on the horizontal axis? Is it IOU thresh or Class thresh?

How can set confidence threshold when I am doing inference?

[glenn-jocher]

@jet-c-21 The confidence on the horizontal axis of the precision-recall curves and F1 curves is the objectness score threshold, not the IoU or class score threshold. You can set the confidence threshold during inference with the --conf argument. Check out the YOLOv5 documentation for more details.