Correctness of flip formula

[ratthachat]

First of all thanks so much for making this Yolo V5! It's now the best model in Kaggle Wheat detection : https://www.kaggle.com/c/global-wheat-detection

Trying to modify TTA, I found you use the following lr-flip formula for bbox :

In models/yolo.py
y[1][..., 0] = img_size[1] - y[1][..., 0] # flip lr ---- Equation (1)

I have checked on Yolo V3 and it's the same, so I am sure the formula is correct.

However, in my understanding we should change both xmin and xmax for lr-flip but the formula above only change xmin.
For examples, the famous albumentations formula is :

https://github.com/albumentations-team/albumentations/blob/master/albumentations/augmentations/functional.py
In def bbox_hflip
new_xmin, new_ymin, new_xmax, new_ymax = 1 - x_max, y_min, 1 - x_min, y_max

Or explained intuitively here : https://blog.paperspace.com/data-augmentation-for-bounding-boxes/

So my question is how can the above equation (1) is correct ??
It should be

y[1][..., 2] = img_size[1] - y[1][..., 0] # flip lr new xmax
y[1][..., 0] = img_size[1] - y[1][..., 2] # flip lr new xmin

EDIT : I got it. Yolo use xcenter, ycenter, w, h, so it explains Equation (1) . Close the issue.

[github-actions]

Hello @ratthachat, thank you for your interest in our work! Please visit our Custom Training Tutorial to get started, and see our Jupyter Notebook , Docker Image, and Google Cloud Quickstart Guide for example environments.

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 model or data training question, please note that Ultralytics does not provide free personal support. As a leader in vision ML and AI, we do offer professional consulting, from simple expert advice up to delivery of fully customized, end-to-end production solutions for our clients, such as:

• Cloud-based AI systems operating on hundreds of HD video streams in realtime.
• Edge AI integrated into custom iOS and Android apps for realtime 30 FPS video inference.
• Custom data training, hyperparameter evolution, and model exportation to any destination.

For more information please visit https://www.ultralytics.com.

[glenn-jocher]

Yes, xywh format.