DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.
[X] I have read the README carefully. 我已经仔细阅读了README上的操作指引。
[X] 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。
[X] 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
[X] 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?
Before Asking
[X] I have read the README carefully. 我已经仔细阅读了README上的操作指引。
[X] 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。
[X] 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
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