mean std value for LAB/YCbCr normalization

[PhilLint]

With regards to the mean and std values required for normalization: How do the values arise for LAB and YCbCr respectively? My assumption was, that the training images were transformed into the new color space and then statistics across channels are computed which are then used for normalization. That would explain YCbCr, but what does the formula for LAB color space mean? Is it the min and max values averaged?

`def get_train_loader(args): """get the train loader""" data_folder = os.path.join(args.data_folder, 'train')

if args.view == 'Lab':
    mean = [(0 + 100) / 2, (-86.183 + 98.233) / 2, (-107.857 + 94.478) / 2]
    std = [(100 - 0) / 2, (86.183 + 98.233) / 2, (107.857 + 94.478) / 2]
    color_transfer = RGB2Lab()
elif args.view == 'YCbCr':
    mean = [116.151, 121.080, 132.342]
    std = [109.500, 111.855, 111.964]
    color_transfer = RGB2YCbCr()`

[HobbitLong]

Hi @PhilLint,

You are right. For YCbCr I used the mean and std. For Lab, I just normalize the input to [-1, 1].