I augmented my custom dataset in Roboflow. Is it redundant since there is already augmentation in the hyperparameters file?

[qjygsantos]

Search before asking

• I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

I am trying to train a model with the new YOLO11. As for my dataset, I used Roboflow for annotating, splitting dataset, preprocessing, and augmentation.

This is what I chose for augmentation in Roboflow:

Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Blur: Up to 2px
Noise: Up to 1.96% of pixels

But, I noticed that in the hyp.scratch-low.yaml file, there are also augmentation parameters/values. Should I skip augmenting with Roboflow and just use the hyps file? Can I do all those above by tweaking the values?

Additional

No response

[UltralyticsAssistant]

👋 Hello @qjygsantos, thank you for your interest in YOLOv5 🚀! This is an automated response to assist you. An Ultralytics engineer will also review your issue soon.

For questions about data augmentation, you might find it useful to review our Custom Data Training tutorial. 🚀

Regarding augmentation techniques, it's important to note that you can combine external augmentation from tools like Roboflow with YOLOv5's built-in features. However, if you encounter any issues, providing a minimum reproducible example will be helpful to diagnose the problem.

Make sure you're following our Tips for Best Training Results to ensure optimal model performance.

Requirements

Verify that you have Python>=3.8.0 with all requirements.txt dependencies installed:

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

Environments

Experiment with YOLOv5 in these environments:

• Notebooks:

Status

Green badge? All CI tests are passing on YOLOv5 functionalities!

Introducing YOLOv8 🚀

Check out YOLOv8 for the latest advancements in object detection and more!

If additional guidance is needed, feel free to provide more details. Happy experimenting! 🎉