Image normalization strategy

[VitalyyBezuglyj]

Before Asking

• I have read the README carefully. 我已经仔细阅读了README上的操作指引。

• I want to train my custom dataset, and I have read the tutorials for finetune on your data carefully and organize my dataset correctly; 我想训练自定义数据集，我已经仔细阅读了训练自定义数据的教程，以及按照正确的目录结构存放数据集。

• I have pulled the latest code of main branch to run again and the problem still existed. 我已经拉取了主分支上最新的代码，重新运行之后，问题仍不能解决。

Search before asking

• I have searched the DAMO-YOLO issues and found no similar questions.

Question

Good afternoon!
Thanks for your work, awesome model and working, readable code!

I have a question about the image normalisation strategy during training, in the configuration files and in all augmentation functions the values mean=(0,0,0,0) and std=(1, 1, 1)-that is, normalisation is not performed.

It seems as if normalising the input data is a common practice to improve the quality of the model.

Is there any reason why you don't normalise the input data?

Additional

No response

[ofekp]

Hoping to bring this thread to the authors' attention, I would also like to add that the input values are [0..255] and not float values [0..1.], meaning there is also no normalization of the raw pixel values.