Implementation-CVPR2015-CNN-for-ReID
Implementation-CVPR2015-CNN-for-ReID copied to clipboard
Ning-Ding
Data augmentation
Hi, First of all, thanks for your work!
In a previous issue you said that you have 130000 images, they are image pairs, are they ? In data augmentation, I understand that you double the dataset by a random transform.
Do you consider to add more transformation to enlarge your data set ? or it may be to noisy ? thanks!
Yes, they are image pairs without data augmentation. In the paper, the author said they made five random transform for each images. Also, they have flipped the image once. So after data augmentation, they have 10 images for one original images. Generally, data augmentation is very important for getting a good result. I would prefer a online random transformation during training, not a offline image preparation.
