tf.keras.layers.experimental.preprocessing.RandomRotation
Stay organized with collections
Save and categorize content based on your preferences.
Randomly rotate each image.
Inherits From: Layer
tf.keras.layers.experimental.preprocessing.RandomRotation(
factor, fill_mode='reflect', interpolation='bilinear', seed=None, name=None,
**kwargs
)
By default, random rotations are only applied during training.
At inference time, the layer does nothing. If you need to apply random
rotations at inference time, set training to True when calling the layer.
4D tensor with shape:
(samples, height, width, channels), data_format='channels_last'.
Output shape:
4D tensor with shape:
(samples, height, width, channels), data_format='channels_last'.
4D tensor with shape: (samples, height, width, channels),
data_format='channels_last'.
Output shape:
4D tensor with shape: (samples, height, width, channels),
data_format='channels_last'.
Raise |
|---|
ValueError
|
if either bound is not between [0, 1], or upper bound is
less than lower bound.
|
Attributes |
|---|
factor
|
a float represented as fraction of 2pi, or a tuple of size
2 representing lower and upper bound for rotating clockwise and
counter-clockwise. A positive values means rotating counter clock-wise,
while a negative value means clock-wise. When represented as a single
float, this value is used for both the upper and lower bound. For
instance, factor=(-0.2, 0.3) results in an output
rotation by a random amount in the range [-20% * 2pi, 30% * 2pi].
factor=0.2 results in an output rotating by a random amount in the range
[-20% * 2pi, 20% * 2pi].
|
fill_mode
|
Points outside the boundaries of the input are filled according
to the given mode (one of {'constant', 'reflect', 'wrap'}).
- 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)
|
interpolation
|
Interpolation mode. Supported values: "nearest", "bilinear".
|
seed
|
Integer. Used to create a random seed.
|
name
|
A string, the name of the layer.
|
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.
Last updated 2020-10-01 UTC.
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# tf.keras.layers.experimental.preprocessing.RandomRotation\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.3.0/tensorflow/python/keras/layers/preprocessing/image_preprocessing.py#L728-L838) |\n\nRandomly rotate each image.\n\nInherits From: [`Layer`](../../../../../tf/keras/layers/Layer)\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.keras.layers.experimental.preprocessing.RandomRotation`](/api_docs/python/tf/keras/layers/experimental/preprocessing/RandomRotation)\n\n\u003cbr /\u003e\n\n tf.keras.layers.experimental.preprocessing.RandomRotation(\n factor, fill_mode='reflect', interpolation='bilinear', seed=None, name=None,\n **kwargs\n )\n\nBy default, random rotations are only applied during training.\nAt inference time, the layer does nothing. If you need to apply random\nrotations at inference time, set `training` to True when calling the layer.\n\n#### Input shape:\n\n4D tensor with shape:\n`(samples, height, width, channels)`, data_format='channels_last'.\n\n#### Output shape:\n\n4D tensor with shape:\n`(samples, height, width, channels)`, data_format='channels_last'.\n\n#### Input shape:\n\n4D tensor with shape: `(samples, height, width, channels)`,\ndata_format='channels_last'.\n\n#### Output shape:\n\n4D tensor with shape: `(samples, height, width, channels)`,\ndata_format='channels_last'.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Raise ----- ||\n|--------------|-----------------------------------------------------------------------------------|\n| `ValueError` | if either bound is not between \\[0, 1\\], or upper bound is less than lower bound. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Attributes ---------- ||\n|-----------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `factor` | a float represented as fraction of 2pi, or a tuple of size 2 representing lower and upper bound for rotating clockwise and counter-clockwise. A positive values means rotating counter clock-wise, while a negative value means clock-wise. When represented as a single float, this value is used for both the upper and lower bound. For instance, `factor=(-0.2, 0.3)` results in an output rotation by a random amount in the range `[-20% * 2pi, 30% * 2pi]`. `factor=0.2` results in an output rotating by a random amount in the range `[-20% * 2pi, 20% * 2pi]`. |\n| `fill_mode` | Points outside the boundaries of the input are filled according to the given mode (one of `{'constant', 'reflect', 'wrap'}`). \u003cbr /\u003e - *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)` |\n| `interpolation` | Interpolation mode. Supported values: \"nearest\", \"bilinear\". |\n| `seed` | Integer. Used to create a random seed. |\n| `name` | A string, the name of the layer. |"]]
View source on GitHub