No normalization in prepocess_input function

[Schizophreni]

In the file imagenet_utils.py, the prepocess_input function doesn't contain a normalization procedure, so if I am about to use pretrained VGG19, is it necessary to add this normalization procedure.
What's more, why should RGB be changed to BGR. In other websites, the mean value of an image is [123.68, 116.779, 103.939] for RGB, but in this file, it is reversed. which mean value is suitable for the VGG19 in the data format RGB? Do I need to change the image format from RGB to BGR if I want to transfer VGG19 to other tasks?
`def preprocess_input(x, dim_ordering='default'):
if dim_ordering == 'default':
dim_ordering = K.image_dim_ordering()
assert dim_ordering in {'tf', 'th'}

if dim_ordering == 'th':
    x[:, 0, :, :] -= 103.939
    x[:, 1, :, :] -= 116.779
    x[:, 2, :, :] -= 123.68
    # 'RGB'->'BGR'
    x = x[:, ::-1, :, :]
else:
    x[:, :, :, 0] -= 103.939
    x[:, :, :, 1] -= 116.779
    x[:, :, :, 2] -= 123.68
    # 'RGB'->'BGR'
    x = x[:, :, :, ::-1]
return x`

[liu09114]

Have the same problem. Solved?