Closed hyenal closed 1 year ago
Right now the preprocessing function does not account for uniform images. This can results in bugs which are hard to track.
I would suggest replacing this function, by the normalisation generally done in tensorflow (Normalisation account for std =0).
Normalisation
I am bound to use the same preprocessing method as the one used for model training... And so I am copying whatever is present in timm.
timm
Right now the preprocessing function does not account for uniform images. This can results in bugs which are hard to track.
I would suggest replacing this function, by the normalisation generally done in tensorflow (
Normalisation
account for std =0).