Help protect the Great Barrier Reef with TensorFlow on Kaggle Join Challenge


Adjust saturation of RGB images.

Used in the notebooks

Used in the tutorials

This is a convenience method that converts RGB images to float representation, converts them to HSV, adds an offset to the saturation channel, converts back to RGB and then back to the original data type. If several adjustments are chained it is advisable to minimize the number of redundant conversions.

image is an RGB image or images. The image saturation is adjusted by converting the images to HSV and multiplying the saturation (S) channel by saturation_factor and clipping. The images are then converted back to RGB.

Usage Example:

x = [[[1.0, 2.0, 3.0],
      [4.0, 5.0, 6.0]],
    [[7.0, 8.0, 9.0],
      [10.0, 11.0, 12.0]]]
tf.image.adjust_saturation(x, 0.5)
<tf.Tensor: shape=(2, 2, 3), dtype=float32, numpy=
array([[[ 2. ,  2.5,  3. ],
        [ 5. ,  5.5,  6. ]],
       [[ 8. ,  8.5,  9. ],
        [11. , 11.5, 12. ]]], dtype=float32)>

image RGB image or images. The size of the last dimension must be 3.
saturation_factor float. Factor to multiply the saturation by.
name A name for this operation (optional).

Adjusted image(s), same shape and DType as image.

InvalidArgumentError input must have 3 channels