Training with Detectnet_V2 using multiple resolutions

[Levi_Pereira]

Hi,
I’m a bit confusing about automatic resizing of images during training.
The train tool does not support training on images of multiple resolutions, but Dataloader support automatic resizing of images .
Dataloader is automatic during train process?

https://docs.nvidia.com/tao/tao-toolkit/text/object_detection/detectnet_v2.html?highlight=augmentation_config

Docs says two things:
First Note:

The train tool does not support training on images of multiple resolutions. However, the dataloader does support resizing images to the input resolution defined in the specification file. This can be enabled by setting the enable_auto_resize parameter to true in the augmentation_config module of the spec file.

Second Note:
The train tool does not support training on images of multiple resolutions, or resizing images during training. All of the images must be resized offline to the final training size and the corresponding bounding boxes must be scaled accordingly.

[Morganh]

@Levi_Pereira

enable_auto_resize parameter to true

Please set enable_auto_resize parameter to true.
Then it can train with multiple resolutions images.
We will improve the doc.