Missed TensorFlow Dev Summit? Check out the video playlist. Watch recordings

tf.keras.layers.experimental.preprocessing.Rescaling

View source on GitHub

Multiply inputs by scale.

Inherits From: Layer

tf.keras.layers.experimental.preprocessing.Rescaling(
    scale, name=None, **kwargs
)

For instance, to rescale an input in the [0, 255] range to be in the [0, 1] range, you would pass scale=1./255.

The rescaling is applied both during training and inference.

Input shape:

Arbitrary.

Output shape:

Same as input.

Arguments:

  • scale: Float, the scale to apply to the inputs.
  • name: A string, the name of the layer.