data augmentation

[CHN-001]

Hello author, I would like to use online data augmentation in BCNet now. I see that the image size can be randomly processed in the cfg file,So I want to add some other enhancements, such as the ones shown below,

T.RandomBrightness(0.9, 1.1) and T.RandomFlip(prob=0.5)

and I'm not sure how to add them. Should I modify the datamapper.py file? Or should I add some code to my train.py file? I'm looking forward to your reply and i will be grateful if u can help me! Please forgive my poor English.

These are some related works that I found, and i hope these can help us.
https://stackoverflow.com/questions/71774744/how-to-use-detectron2s-augmentation-with-datasets-loaded-using-register-coco-in/71799464#71799464
https://github.com/facebookresearch/detectron2/issues/1578

[kieran0625]

Hello, I'm a project newbie. I encountered the same problem as you. May I ask if you've resolved it? Do I need to create my own custom-mapper?

[CHN-001]

Hello, I'm a project newbie. I encountered the same problem as you. May I ask if you've resolved it? Do I need to create my own custom-mapper?
Hello, I didn't implement data augmentation within BCNet. I did it offline. Moreover, I found that BCNet would automatically crop the size of the input image, so I didn't continue my research at that time. You should need create custom-mapper to achieve online data augmentation.