Docs4dev
Docs
tensorflow / 2.9 / keras / layers / randomtranslation.html

tf.keras.layers.RandomTranslation

A preprocessing layer which randomly translates images during training.

Inherits From: Layer, Module

tf.keras.layers.RandomTranslation(
    height_factor,
    width_factor,
    fill_mode='reflect',
    interpolation='bilinear',
    seed=None,
    fill_value=0.0,
    **kwargs
)

This layer will apply random translations to each image during training, filling empty space according to fill_mode.

Input pixel values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger or floating point dtype. By default, the layer will output floats.

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

Args
height_factor a float represented as fraction of value, or a tuple of size 2 representing lower and upper bound for shifting vertically. A negative value means shifting image up, while a positive value means shifting image down. When represented as a single positive float, this value is used for both the upper and lower bound. For instance, height_factor=(-0.2, 0.3) results in an output shifted by a random amount in the range [-20%, +30%]. height_factor=0.2 results in an output height shifted by a random amount in the range [-20%, +20%].
width_factor a float represented as fraction of value, or a tuple of size 2 representing lower and upper bound for shifting horizontally. A negative value means shifting image left, while a positive value means shifting image right. When represented as a single positive float, this value is used for both the upper and lower bound. For instance, width_factor=(-0.2, 0.3) results in an output shifted left by 20%, and shifted right by 30%. width_factor=0.2 results in an output height shifted left or right by 20%.
fill_mode Points outside the boundaries of the input are filled according to the given mode (one of {"constant", "reflect", "wrap", "nearest"}).
  • 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.
  • nearest: (a a a a | a b c d | d d d d) The input is extended by the nearest pixel.
interpolation Interpolation mode. Supported values: "nearest", "bilinear".
seed Integer. Used to create a random seed.
fill_value a float represents the value to be filled outside the boundaries when fill_mode="constant".

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
auto_vectorize Control whether automatic vectorization occurs.

By default the call() method leverages the tf.vectorized_map() function. Auto-vectorization can be disabled by setting self.auto_vectorize = False in your __init__() method. When disabled, call() instead relies on tf.map_fn(). For example:

class SubclassLayer(BaseImageAugmentationLayer):
  def __init__(self):
    super().__init__()
    self.auto_vectorize = False

© 2022 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 4.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/versions/r2.9/api_docs/python/tf/keras/layers/RandomTranslation