After the YOLOv5 version update, does it affect model performance?

[bjh03205]

I am testing different software to visualize the results, such as heatmaps.

However, there are compatibility differences depending on the model version, such as v6.1-YOLOv5 and v7.0-YOLOv5, for the application.

Therefore, I want to use v6.1-YOLOv5, which is available.

I did not find any updates that would affect the model's performance like mAP in the releases.

I'd like to know if I am missing something.

After updating from v6.1-YOLOv5 to v7.0-YOLOv5, does it affect the model's performance?

[github-actions]

👋 Hello @bjh03205, 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>=3.8.0 with all requirements.txt installed including PyTorch>=1.8. 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]

@bjh03205 hello,

Thank you for reaching out with your question! It's great to see your interest in understanding the impact of YOLOv5 version updates on model performance.

Impact of YOLOv5 Version Updates on Model Performance

YOLOv5 is actively maintained and regularly updated to improve performance, add new features, and fix bugs. While these updates generally aim to enhance the model's capabilities, they can sometimes lead to variations in performance metrics such as precision, recall, and inference speed.

To assess the impact of a version update on your specific use case, I recommend the following steps:

1. Baseline Performance Evaluation:
   Before updating, evaluate your current model's performance using the validation script:

   python val.py --weights your_model.pt --data your_data.yaml --img 640 --half

   This will give you a set of baseline metrics to compare against.

2. Update YOLOv5:
   Ensure you are using the latest version of YOLOv5 and PyTorch:

   git pull  # update YOLOv5
   pip install -r requirements.txt  # update dependencies

3. Re-evaluate Performance:
   After updating, re-evaluate the model using the same validation script:

   python val.py --weights your_model.pt --data your_data.yaml --img 640 --half

4. Compare Results:
   Compare the performance metrics (e.g., mAP, inference time) from before and after the update to determine any changes.

Example Code for Performance Evaluation

Here is an example of how you can evaluate the model performance before and after the update:

# Before update
python val.py --weights yolov5x.pt --data coco.yaml --img 640 --half

# Update YOLOv5
git pull
pip install -r requirements.txt

# After update
python val.py --weights yolov5x.pt --data coco.yaml --img 640 --half

Additional Resources

For more detailed information on model evaluation and pruning, you can refer to our Pruning/Sparsity Tutorial.

If you encounter any specific issues or discrepancies, please provide a minimum reproducible example as outlined here. This will help us investigate and address any potential bugs effectively.

Feel free to reach out if you have any further questions or need additional assistance. The YOLO community and the Ultralytics team are always here to help!

[bjh03205]

Thanks a lot for your quick answer :)

[glenn-jocher]

@bjh03205 you're welcome! 😊

To ensure we can effectively address your issue, could you please provide a minimum reproducible code example? This will help us understand the context and reproduce the bug on our end. You can find guidelines on how to create one here.

Additionally, please make sure you are using the latest versions of torch and the YOLOv5 repository. You can update your YOLOv5 repo and dependencies with the following commands:

git pull  # update YOLOv5
pip install -r requirements.txt  # update dependencies

Once you've done that, please run your code again to see if the issue persists. If it does, share the reproducible example, and we'll be happy to investigate further.

Thank you for your cooperation, and we look forward to resolving this for you!