tf.keras.layers.experimental.preprocessing.RandomTranslation

View source on GitHub

Randomly translate each image during training.

Inherits From: Layer

tf.keras.layers.experimental.preprocessing.RandomTranslation(
    height_factor, width_factor, fill_mode='reflect', interpolation='bilinear',
    seed=None, name=None, **kwargs
)

Arguments:

  • height_factor: a positive float represented as fraction of value, or a tuple of size 2 representing lower and upper bound for shifting vertically. When represented as a single float, this value is used for both the upper and lower bound. For instance, height_factor=(0.2, 0.3) results in an output height varying in the range [original - 20%, original + 30%]. height_factor=0.2 results in an output height varying in the range [original - 20%, original + 20%].
  • width_factor: a positive float represented as fraction of value, or a tuple of size 2 representing lower and upper bound for shifting horizontally. When represented as a single float, this value is used for both the upper and lower bound.
  • fill_mode: Points outside the boundaries of the input are filled according to the given mode (one of {'constant', 'reflect', 'wrap'}).
    • reflect: (d c b a | a b c d | d c b a) The input is extended by reflecting about the edge of the last pixel.
    • constant: (k k k k | a b c d | k k k k) The input is extended by filling all values beyond the edge with the same constant value k = 0.
    • wrap: (a b c d | a b c d | a b c d) The input is extended by wrapping around to the opposite edge.
  • interpolation: Interpolation mode. Supported values: "nearest", "bilinear".
  • seed: Integer. Used to create a random seed.
  • name: A string, the name of the layer.

Input shape:

4D tensor with shape: (samples, height, width, channels), data_format='channels_last'.

Output shape:

4D tensor with shape: (samples, height, width, channels), data_format='channels_last'.

Raise:

  • ValueError: if lower bound is not between [0, 1], or upper bound is negative.