|TensorFlow 1 version||View source on GitHub|
Calculate and return the total variation for one or more images.
Compat aliases for migration
See Migration guide for more details.
tf.image.total_variation( images, name=None )
Used in the notebooks
|Used in the tutorials|
The total variation is the sum of the absolute differences for neighboring pixel-values in the input images. This measures how much noise is in the images.
This can be used as a loss-function during optimization so as to suppress
noise in images. If you have a batch of images, then you should calculate
the scalar loss-value as the sum:
loss = tf.reduce_sum(tf.image.total_variation(images))
This implements the anisotropic 2-D version of the formula described here:
images: 4-D Tensor of shape
[batch, height, width, channels]or 3-D Tensor of shape
[height, width, channels].
name: A name for the operation (optional).
ValueError: if images.shape is not a 3-D or 4-D vector.
The total variation of
images was 4-D, return a 1-D float Tensor of shape
[batch] with the
total variation for each image in the batch.
images was 3-D, return a scalar float with the total variation for