RandomInvert classkeras.layers.RandomInvert(
factor=1.0, value_range=(0, 255), seed=None, data_format=None, **kwargs
)
Preprocessing layer for random inversion of image colors.
This layer randomly inverts the colors of input images with a specified probability range. When applied, each image has a chance of having its colors inverted, where the pixel values are transformed to their complementary values. Images that are not selected for inversion remain unchanged.
Note: This layer is safe to use inside a tf.data or grain pipeline
(independently of which backend you're using).
Arguments
factor controls the probability of inverting the image colors.
If a tuple is provided, the value is sampled between the two values
for each image, where factor[0] is the minimum and factor[1] is
the maximum probability. If a single float is provided, a value
between 0.0 and the provided float is sampled.
Defaults to (0, 1).value_range. Defaults to (0, 255).