Comment by minimaxir

> At a pixel level, the average of every image is a grayish rectangle; that's obviously not what we mean and AI does not produce that.

That isn't correct since images in the real world aren't uniformly distributed from [0, 255] color-wise. Take, for example, the famous ImageNet normalization magic numbers:

    normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                     std=[0.229, 0.224, 0.225])

If it were actually uniformly distributed, the mean for each channel would be 0.5 and the standard deviation would be 0.289. Also due to z-normalization, the "image" most image models see is not how humans typically see images.