Missed TensorFlow World? Check out the recap. Learn more



Defined in tensorflow/python/ops/image_ops_impl.py.

See the guide: Images > Image Adjustments

Linearly scales image to have zero mean and unit norm.

This op computes (x - mean) / adjusted_stddev, where mean is the average of all values in image, and adjusted_stddev = max(stddev, 1.0/sqrt(image.NumElements())).

stddev is the standard deviation of all values in image. It is capped away from zero to protect against division by 0 when handling uniform images.


  • image: 3-D tensor of shape [height, width, channels].


The standardized image with same shape as image.


  • ValueError: if the shape of 'image' is incompatible with this function.