Linearly scales each image in
image to have mean 0 and variance 1.
For each 3-D image
(x - mean) / adjusted_stddev,
meanis the average of all values in
adjusted_stddev = max(stddev, 1.0/sqrt(N))is capped away from 0 to protect against division by 0 when handling uniform images
Nis the number of elements in
stddevis the standard deviation of all values in
image: An n-D Tensor with at least 3 dimensions, the last 3 of which are the dimensions of each image.
Tensor with same shape and dtype as
ValueError: if the shape of 'image' is incompatible with this function.