tf.keras.layers.RandomFlip

A preprocessing layer which randomly flips images during training.

Inherits From: Layer, Module

View aliases

Main aliases

tf.keras.layers.experimental.preprocessing.RandomFlip

Compat aliases for migration

See Migration guide for more details.

`tf.compat.v1.keras.layers.RandomFlip`, `tf.compat.v1.keras.layers.experimental.preprocessing.RandomFlip`

tf.keras.layers.RandomFlip(
    mode=HORIZONTAL_AND_VERTICAL, seed=None, **kwargs
)

This layer will flip the images horizontally and or vertically based on the mode attribute. During inference time, the output will be identical to input. Call the layer with training=True to flip the input.

For an overview and full list of preprocessing layers, see the preprocessing guide.

Input shape
3D (unbatched) or 4D (batched) tensor with shape: (..., height, width, channels), in "channels_last" format.

Output shape
3D (unbatched) or 4D (batched) tensor with shape: (..., height, width, channels), in "channels_last" format.

Attributes
mode	String indicating which flip mode to use. Can be "horizontal", "vertical", or "horizontal_and_vertical". Defaults to "horizontal_and_vertical". "horizontal" is a left-right flip and "vertical" is a top-bottom flip.
seed	Integer. Used to create a random seed.