Augmentations during training

Hi! I use sample configs, which provide augmentation_config part. If I don’t use tlt-augment offline (that is - BEFORE the training) does that mean that I run the training without any augmentations?

No, there is still some augmentations.
For example,

Hm, I see. Then what’s the profit of using your augment tool, if we can use the same augmentations during training?

See more details in

Would it possible to use tlt-augment to resize image to the same size from VOC or COCO?

Actually, it can. Please remove the spatial and color part inside the tlt-augment spec.