What's the meaning of mean and norm when use AWNN converter

[diazGT94]

Hello, I trained an object detector with Yolo and I would like to know how to convert it to AWNN. I was able to convert the .cfg and .weights files to .bin a .para files that belongs to a NCNN. However, I'm confused of the values that I should use for the NCNN to AWNN online converter tool. The input of the images on my yolo network are 320x240 however I don't know how to get the mean and normalization factor.

[Neutree]

mean and norm describe how input data be normalized( (input_data - mean) * norm )

e.g.

if you want normalized input data ∈ [-1, 1] , and input pixel data ∈ [0, 255], your mean and norm can be: mean = 127.5, norm=0.0078125 (that is 1/128)

the first pixel: (255, 0, 150)

then after nomalize, the pixel data is ( (255 - 127.5)/128, (0 - 127.5)/128, (150 - 127.5)/128)