How would resize portrait images to train a peoplenet model for Tao toolkit. My current portait images are at 1520 w , 2680 h?

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

How would resize portrait images to train a peoplenet model. My current portait images are at 1520 w , 2680 h?

3

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

You can set training spec with

output _image _width: 1520
output _image _height: 2688
enable_auto _resize: true

More info can be found in DetectNet_v2 - NVIDIA Docs

5

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