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

tf.image.random_flip_left_right

TensorFlow 1 version View source on GitHub

Randomly flip an image horizontally (left to right).

tf.image.random_flip_left_right(
    image, seed=None
)

Used in the notebooks

Used in the tutorials

With a 1 in 2 chance, outputs the contents of image flipped along the second dimension, which is width. Otherwise output the image as-is. When passing a batch of images, each image will be randomly flipped independent of other images.

Example usage:

Randomly flip a single image.

import numpy as np

image = np.array([[[1], [2]], [[3], [4]]]) 
tf.image.random_flip_left_right(image, 5).numpy().tolist() 
[[[2], [1]], [[4], [3]]] 

Randomly flip multiple images.

images = np.array( ... [ ... [[[1], [2]], [[3], [4]]], ... [[[5], [6]], [[7], [8]]] ... ]) tf.image.random_flip_left_right(images, 6).numpy().tolist() [[[[2], [1]], [[4], [3]]], [[[5], [6]], [[7], [8]]]]

Args:

  • image: 4-D Tensor of shape [batch, height, width, channels] or 3-D Tensor of shape [height, width, channels].
  • seed: A Python integer. Used to create a random seed. See tf.compat.v1.set_random_seed for behavior.

Returns:

A tensor of the same type and shape as image.

Raises:

  • ValueError: if the shape of image not supported.