Do you apply data augmentation?

[doantientai]

Hi @zhaohengyuan1 and the team,

Congratulations on the great work! Well done! :smile:

Just a small question. Do you think it would be a good idea to apply data augmentations on images during the training? I guess the model would be even more robust. And if I want to do it, do you have any advice on how, and where should I do it in your source?

Thank you very much and have a nice day!

[doantientai]

Oh, I think I found it. You already applied them here: https://github.com/zhaohengyuan1/Color2Embed/blob/main/train.py#L327

[zhaohengyuan1]

ok