tf.image.random_flip_left_right
Stay organized with collections
Save and categorize content based on your preferences.
Randomly flip an image horizontally (left to right).
tf.image.random_flip_left_right(
image, seed=None
)
Used in the notebooks
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:
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]]]]
For producing deterministic results given a seed value, use
tf.image.stateless_random_flip_left_right. Unlike using the seed param
with tf.image.random_* ops, tf.image.stateless_random_* ops guarantee the
same results given the same seed independent of how many times the function is
called, and independent of global seed settings (e.g. tf.random.set_seed).
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.
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.
Last updated 2024-04-26 UTC.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2024-04-26 UTC."],[],[],null,["# tf.image.random_flip_left_right\n\n\u003cbr /\u003e\n\n|----------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.16.1/tensorflow/python/ops/image_ops_impl.py#L383-L428) |\n\nRandomly flip an image horizontally (left to right).\n\n#### View aliases\n\n\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.image.random_flip_left_right`](https://www.tensorflow.org/api_docs/python/tf/image/random_flip_left_right)\n\n\u003cbr /\u003e\n\n tf.image.random_flip_left_right(\n image, seed=None\n )\n\n### Used in the notebooks\n\n| Used in the tutorials |\n|------------------------------------------------------------------------|\n| - [CycleGAN](https://www.tensorflow.org/tutorials/generative/cyclegan) |\n\nWith a 1 in 2 chance, outputs the contents of `image` flipped along the\nsecond dimension, which is `width`. Otherwise output the image as-is.\nWhen passing a batch of images, each image will be randomly flipped\nindependent of other images.\n\n#### Example usage:\n\n image = np.array([[[1], [2]], [[3], [4]]])\n tf.image.random_flip_left_right(image, 5).numpy().tolist()\n [[[2], [1]], [[4], [3]]]\n\nRandomly flip multiple images. \n\n images = np.array(\n [\n [[[1], [2]], [[3], [4]]],\n [[[5], [6]], [[7], [8]]]\n ])\n tf.image.random_flip_left_right(images, 6).numpy().tolist()\n [[[[2], [1]], [[4], [3]]], [[[5], [6]], [[7], [8]]]]\n\nFor producing deterministic results given a `seed` value, use\n[`tf.image.stateless_random_flip_left_right`](../../tf/image/stateless_random_flip_left_right). Unlike using the `seed` param\nwith `tf.image.random_*` ops, `tf.image.stateless_random_*` ops guarantee the\nsame results given the same seed independent of how many times the function is\ncalled, and independent of global seed settings (e.g. tf.random.set_seed).\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|---------|----------------------------------------------------------------------------------------------------------------------------------------|\n| `image` | 4-D Tensor of shape `[batch, height, width, channels]` or 3-D Tensor of shape `[height, width, channels]`. |\n| `seed` | A Python integer. Used to create a random seed. See [`tf.compat.v1.set_random_seed`](../../tf/compat/v1/set_random_seed) for behavior. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A tensor of the same type and shape as `image`. ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Raises ------ ||\n|--------------|----------------------------------------|\n| `ValueError` | if the shape of `image` not supported. |\n\n\u003cbr /\u003e"]]
View source on GitHub