How is online data augmentation done?

How is online data augmentation done? Is there any open source code?

TAO is already open source. They can be found in the bottom of NVIDIA Corporation · GitHub

Is it in GitHub - NVIDIA/tao_dataset_suite: Set of advanced data augmentation and analytics tools?
I don’t see online enhancements, but I do see offline enhancements.
Can you elaborate on where these files are located?

Which network did you use?

yolov4 tiny.

You can refer to the dataloader in https://github.com/NVIDIA/tao_tensorflow1_backend/tree/main/nvidia_tao_tf1/cv/yolo_v4/dataio

1 Like

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.