tf.keras.layers.RandomContrast
Stay organized with collections
Save and categorize content based on your preferences.
Adjust the contrast of an image or images by a random factor.
Inherits From: Layer, Module
tf.keras.layers.RandomContrast(
factor, seed=None, **kwargs
)
Contrast is adjusted independently for each channel of each image during
training.
For each channel, this layer computes the mean of the image pixels in the
channel and then adjusts each component x of each pixel to
(x - mean) * contrast_factor + mean.
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 |
|---|
factor
|
a positive float represented as fraction of value, or a tuple of
size 2 representing lower and upper bound. When represented as a single
float, lower = upper. The contrast factor will be randomly picked between
[1.0 - lower, 1.0 + upper].
|
seed
|
Integer. Used to create a random seed.
|
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 2021-08-16 UTC.
[null,null,["Last updated 2021-08-16 UTC."],[],[],null,["# tf.keras.layers.RandomContrast\n\n\u003cbr /\u003e\n\n|----------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/master/keras/layers/preprocessing/image_preprocessing.py#L1095-L1160) |\n\nAdjust the contrast of an image or images by a random factor.\n\nInherits From: [`Layer`](../../../tf/keras/layers/Layer), [`Module`](../../../tf/Module)\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tf.keras.layers.experimental.preprocessing.RandomContrast`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomContrast)\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.keras.layers.RandomContrast`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomContrast), [`tf.compat.v1.keras.layers.experimental.preprocessing.RandomContrast`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomContrast)\n\n\u003cbr /\u003e\n\n tf.keras.layers.RandomContrast(\n factor, seed=None, **kwargs\n )\n\nContrast is adjusted independently for each channel of each image during\ntraining.\n\nFor each channel, this layer computes the mean of the image pixels in the\nchannel and then adjusts each component `x` of each pixel to\n`(x - mean) * contrast_factor + mean`.\n\n#### Input shape:\n\n3D (unbatched) or 4D (batched) tensor with shape:\n`(..., height, width, channels)`, in `\"channels_last\"` format.\n\n#### Output shape:\n\n3D (unbatched) or 4D (batched) tensor with shape:\n`(..., height, width, channels)`, in `\"channels_last\"` format.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Attributes ---------- ||\n|----------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `factor` | a positive float represented as fraction of value, or a tuple of size 2 representing lower and upper bound. When represented as a single float, lower = upper. The contrast factor will be randomly picked between `[1.0 - lower, 1.0 + upper]`. |\n| `seed` | Integer. Used to create a random seed. |\n\n\u003cbr /\u003e"]]
View source on GitHub