Data Augmentations Available for Tao-Unet model

[nitinp14920914]

Hello,

We are trying to do Data augmentation for Unet-Model but it looks like we are only limited to only a few methods on it

1. spatial_augmentation
2. brightness_augmentation

But I come across this https://docs.nvidia.com/tao/tao-toolkit/text/offline_data_augmentation.html#id2 the
page which has an extensive range of Augmentation functions but looks like these are only functional with KITTI Dataset can Somone help me if is there any prospect that I can use these functions with my UnetModel As well. Thanks in Advance !!!

• Hardware (T4]
• Network Type (Unet)
• TLT Version

Configuration of the TAO Toolkit Instance

dockers: 		
	nvidia/tao/tao-toolkit-tf: 			
		v3.21.11-tf1.15.5-py3: 				
			docker_registry: nvcr.io
			tasks: 
				1. augment
				2. bpnet
		v3.21.11-tf1.15.4-py3: 				
			docker_registry: nvcr.io
			tasks: 
				1. detectnet_v2
				2. faster_rcnn
	nvidia/tao/tao-toolkit-pyt: 			
		v3.21.11-py3: 				
			docker_registry: nvcr.io
			tasks: 
				1. speech_to_text
				2. speech_to_text_citrinet
				3. text_classification
				4. question_answering
				5. token_classification
				6. intent_slot_classification
				7. punctuation_and_capitalization
				8. spectro_gen
				9. vocoder
				10. action_recognition
	nvidia/tao/tao-toolkit-lm: 			
		v3.21.08-py3: 				
			docker_registry: nvcr.io
			tasks: 
				1. n_gram
format_version: 2.0
toolkit_version: 3.21.11
published_date: 11/08/2021

• Augmentation spec But its not working with UnetModel

spatial_config{
  rotation_config{
    angle: 5.0
    units: "degrees"
  }
  shear_config{
    shear_ratio_x: 0.3
  }
  translation_config{
    translate_x: 8
  }
}
color_config{
  hue_saturation_config{
    hue_rotation_angle: 25.0
    saturation_shift: 1.0
  }
}
dataset_config {
    image_path: "/workspace/tao-experiments/Delivery2/*****/test/******_clip4.mp4.frame.33985.png"
    label_path: "/workspace/tao-experiments/Delivery2/*****/testannot/*****_clip4.mp4.frame.33985.png"
}
output_image_width: 1920
output_image_height: 1080
output_image_channel: 3
image_extension: ".png"

[Morganh]

Hi @nitinp14920914 ,
The Offline Data Augmentation — TAO Toolkit 3.21.11 documentation
is an offline augmentation tool called augment . Offline augmentation can dramatically increase the size of the dataset when collecting and labeling data is expensive or not possible.

For its usage, you can refer to jupyter notebook as well.
https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/resources/cv_samples/files
https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/resources/cv_samples/version/v1.3.0/files/augment/augment.ipynb
https://docs.nvidia.com/tao/tao-toolkit/text/tao_toolkit_quick_start_guide.html#download-jupyter-notebook

It cannot be set directly in Unet. For augmentation in Unet, please refer to https://docs.nvidia.com/tao/tao-toolkit/text/semantic_segmentation/unet.html#dataset