Normalize Input Images with SSD

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

I am using SSD with TLT 2.0, does the input images get subtracted by the image’s mean so they become normalized before training?

3

In TLT the preprocessing of SSD image is like below:

  • assume RGB input values which range from 0.0 to 255.0 as float
  • change from RGB to BGR
  • then subtract channels of input values by 103.939;116.779;123.68 separately for BGR channels.