High Precision, Recall, and mAP after only a couple epochs?

whittenator commented 1 year ago

Search before asking

[X] I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

I am training a custom model on 4 classes using the YoloV5L and the Precision and Recall have jumped up into the 90s after just 5 epochs. I have trained several other 1-2 class YoloV5L models and it has taken much longer for them to get such high precision and recall. Please see the tensorboard output below:

To give a little bit of stats on the dataset: Total Images

Train: 89,541
Test: 12,791
Val: 25,584

The dataset is a bit imbalanced with the following class instances: Class 0: 90350 instances Class 1: 7034 instances Class 2: 23785 instances Class 3: 7779 instances

Could it be that this dataset is too imbalanced? Or something else I am missing?

Thanks

Additional

No response

github-actions[bot] commented 1 year ago

👋 Hello @whittenator, 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 commented 1 year ago

@whittenator hi there! It's great to hear that your YOLOv5 training is yielding high precision and recall within just a few epochs! The speed at which these metrics increase can vary depending on multiple factors, such as the complexity of the dataset, the quality of annotations, and the diversity of object instances.

In your case, the imbalanced nature of your dataset might contribute to the rapid increase in precision and recall. Since class 0 has significantly more instances compared to the other classes, the model may focus more on learning to detect objects from class 0, resulting in high metrics for that particular class.

However, it's essential to note that precision, recall, and mAP are just one aspect of model evaluation. It's always a good idea to thoroughly examine the model's performance on your specific use case and evaluate its generalization ability on unseen data. You may want to consider strategies like data augmentation, balancing techniques, or adjusting training parameters to further improve the model's performance.

If you have any further questions or need assistance with YOLOv5, feel free to ask. We're here to help!

github-actions[bot] commented 1 year ago

👋 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 ⭐

ultralytics / yolov5