Randomly flip an image horizontally (left to right) deterministically.
tf.image.stateless_random_flip_left_right( image, seed )
Guarantees 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
).
image = np.array([[[1], [2]], [[3], [4]]]) seed = (2, 3) tf.image.stateless_random_flip_left_right(image, seed).numpy().tolist() [[[2], [1]], [[4], [3]]]
Args | |
---|---|
image | 4-D Tensor of shape [batch, height, width, channels] or 3-D Tensor of shape [height, width, channels] . |
seed | A shape [2] Tensor, the seed to the random number generator. Must have dtype int32 or int64 . (When using XLA, only int32 is allowed.) |
Returns | |
---|---|
A tensor of the same type and shape as image . |
© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/versions/r2.4/api_docs/python/tf/image/stateless_random_flip_left_right