tf.keras.layers.experimental.preprocessing.RandomHeight
Stay organized with collections
Save and categorize content based on your preferences.
Randomly vary the height of a batch of images during training.
Inherits From: PreprocessingLayer, Layer, Module
tf.keras.layers.experimental.preprocessing.RandomHeight(
factor, interpolation='bilinear', seed=None, name=None, **kwargs
)
Adjusts the height of a batch of images by a random factor. The input
should be a 4-D tensor in the "channels_last" image data format.
By default, this layer is inactive during inference.
Arguments |
|---|
factor
|
A positive float (fraction of original height), or a tuple of size 2
representing lower and upper bound for resizing vertically. 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 with
height changed by a random amount in the range [20%, 30%].
factor=(-0.2, 0.3) results in an output with height changed by a random
amount in the range [-20%, +30%].factor=0.2results in an output with
height changed by a random amount in the range[-20%, +20%].
</td>
</tr><tr>
<td>interpolation</td>
<td>
String, the interpolation method. Defaults tobilinear.
Supportsbilinear,nearest,bicubic,area,lanczos3,lanczos5,gaussian,mitchellcubic</td>
</tr><tr>
<td>seed</td>
<td>
Integer. Used to create a random seed.
</td>
</tr><tr>
<td>name`
|
A string, the name of the layer.
|
4D tensor with shape: (samples, height, width, channels)
(data_format='channels_last').
Output shape:
4D tensor with shape: (samples, random_height, width, channels).
Methods
adapt
View source
adapt(
data, reset_state=True
)
Fits the state of the preprocessing layer to the data being passed.
| Arguments |
|---|
data
|
The data to train on. It can be passed either as a tf.data
Dataset, or as a numpy array.
|
reset_state
|
Optional argument specifying whether to clear the state of
the layer at the start of the call to adapt, or whether to start
from the existing state. This argument may not be relevant to all
preprocessing layers: a subclass of PreprocessingLayer may choose to
throw if 'reset_state' is set to False.
|
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 2021-02-18 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 2021-02-18 UTC."],[],[],null,["# tf.keras.layers.experimental.preprocessing.RandomHeight\n\n\u003cbr /\u003e\n\n|---------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.4.0/tensorflow/python/keras/layers/preprocessing/image_preprocessing.py#L1158-L1253) |\n\nRandomly vary the height of a batch of images during training.\n\nInherits From: [`PreprocessingLayer`](../../../../../tf/keras/layers/experimental/preprocessing/PreprocessingLayer), [`Layer`](../../../../../tf/keras/layers/Layer), [`Module`](../../../../../tf/Module)\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.RandomHeight`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/experimental/preprocessing/RandomHeight)\n\n\u003cbr /\u003e\n\n tf.keras.layers.experimental.preprocessing.RandomHeight(\n factor, interpolation='bilinear', seed=None, name=None, **kwargs\n )\n\nAdjusts the height of a batch of images by a random factor. The input\nshould be a 4-D tensor in the \"channels_last\" image data format.\n\nBy default, this layer is inactive during inference.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Arguments --------- ||\n|----------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------|\n| `factor` | A positive float (fraction of original height), or a tuple of size 2 representing lower and upper bound for resizing vertically. 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 with height changed by a random amount in the range `[20%, 30%]`. `factor=(-0.2, 0.3)` results in an output with height changed by a random amount in the range `[-20%, +30%].`factor=0.2`results in an output with height changed by a random amount in the range`\\[-20%, +20%\\]`. \u003c/td\u003e \u003c/tr\u003e\u003ctr\u003e \u003ctd\u003e`interpolation`\u003c/td\u003e \u003ctd\u003e String, the interpolation method. Defaults to`bilinear`. Supports`bilinear`,`nearest`,`bicubic`,`area`,`lanczos3`,`lanczos5`,`gaussian`,`mitchellcubic`\u003c/td\u003e \u003c/tr\u003e\u003ctr\u003e \u003ctd\u003e`seed`\u003c/td\u003e \u003ctd\u003e Integer. Used to create a random seed. \u003c/td\u003e \u003c/tr\u003e\u003ctr\u003e \u003ctd\u003e`name\\` | A string, the name of the layer. |\n\n\u003cbr /\u003e\n\n#### Input shape:\n\n4D tensor with shape: `(samples, height, width, channels)`\n(data_format='channels_last').\n\n#### Output shape:\n\n4D tensor with shape: `(samples, random_height, width, channels)`.\n\nMethods\n-------\n\n### `adapt`\n\n[View source](https://github.com/tensorflow/tensorflow/blob/v2.4.0/tensorflow/python/keras/engine/base_preprocessing_layer.py#L53-L66) \n\n adapt(\n data, reset_state=True\n )\n\nFits the state of the preprocessing layer to the data being passed.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Arguments ||\n|---------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `data` | The data to train on. It can be passed either as a tf.data Dataset, or as a numpy array. |\n| `reset_state` | Optional argument specifying whether to clear the state of the layer at the start of the call to `adapt`, or whether to start from the existing state. This argument may not be relevant to all preprocessing layers: a subclass of PreprocessingLayer may choose to throw if 'reset_state' is set to False. |\n\n\u003cbr /\u003e"]]
View source on GitHub