Now, pretrained VGG13~19 models with batch normalization are provided.
Are preprocess for them same as process for models without batch normalization?
(transforms.Normalize(mean=[0.485, 0.456, 0.406],std=[0.229, 0.224, 0.225]))
I would like to confirm since bellowing paper mentioned normalizing for input image was omitted and it make sense because it could be substituted by batch norm layer.
How were models provided in the first link trained?