tf.keras.layers.RandomWidth
Stay organized with collections
Save and categorize content based on your preferences.
A preprocessing layer which randomly varies image width during training.
Inherits From: Layer, Module
tf.keras.layers.RandomWidth(
factor, interpolation='bilinear', seed=None, **kwargs
)
This layer will randomly adjusts the width of a batch of images of a
batch of images by a random factor. The input should be a 3D (unbatched) or
4D (batched) tensor in the "channels_last" image data format. Input pixel
values can be of any range (e.g. [0., 1.) or [0, 255]) and of interger
or floating point dtype. By default, the layer will output floats.
By default, this layer is inactive during inference.
For an overview and full list of preprocessing layers, see the preprocessing
guide.
Args |
|---|
factor
|
A positive float (fraction of original width), 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
width changed by a random amount in the range [20%, 30%].
factor=(-0.2, 0.3) results in an output with width changed by a random
amount in the range [-20%, +30%]. factor=0.2 results in an output
with width changed by a random amount in the range [-20%, +20%].
|
interpolation
|
String, the interpolation method. Defaults to bilinear.
Supports "bilinear", "nearest", "bicubic", "area", "lanczos3",
"lanczos5", "gaussian", "mitchellcubic".
|
seed
|
Integer. Used to create a random seed.
|
|
|---|
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, random_width, channels).
|
Attributes |
|---|
auto_vectorize
|
Control whether automatic vectorization occurs.
By default the call() method leverages the tf.vectorized_map()
function. Auto-vectorization can be disabled by setting
self.auto_vectorize = False in your __init__() method. When
disabled, call() instead relies on tf.map_fn(). For example:
class SubclassLayer(BaseImageAugmentationLayer):
def __init__(self):
super().__init__()
self.auto_vectorize = 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 2023-10-06 UTC.
[null,null,["Last updated 2023-10-06 UTC."],[],[],null,["# tf.keras.layers.RandomWidth\n\n\u003cbr /\u003e\n\n|-----------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v2.11.0/keras/layers/preprocessing/image_preprocessing.py#L1893-L2015) |\n\nA preprocessing layer which randomly varies image width during training.\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.RandomWidth`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomWidth)\n\n\u003cbr /\u003e\n\n tf.keras.layers.RandomWidth(\n factor, interpolation='bilinear', seed=None, **kwargs\n )\n\nThis layer will randomly adjusts the width of a batch of images of a\nbatch of images by a random factor. The input should be a 3D (unbatched) or\n4D (batched) tensor in the `\"channels_last\"` image data format. Input pixel\nvalues can be of any range (e.g. `[0., 1.)` or `[0, 255]`) and of interger\nor floating point dtype. By default, the layer will output floats.\n\nBy default, this layer is inactive during inference.\n\nFor an overview and full list of preprocessing layers, see the preprocessing\n[guide](https://www.tensorflow.org/guide/keras/preprocessing_layers).\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-----------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `factor` | A positive float (fraction of original width), 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 width changed by a random amount in the range `[20%, 30%]`. `factor=(-0.2, 0.3)` results in an output with width changed by a random amount in the range `[-20%, +30%]`. `factor=0.2` results in an output with width changed by a random amount in the range `[-20%, +20%]`. |\n| `interpolation` | String, the interpolation method. Defaults to `bilinear`. Supports `\"bilinear\"`, `\"nearest\"`, `\"bicubic\"`, `\"area\"`, `\"lanczos3\"`, `\"lanczos5\"`, `\"gaussian\"`, `\"mitchellcubic\"`. |\n| `seed` | Integer. Used to create a random seed. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Input shape ----------- ||\n|------|----------------------------------------------------------------------------------------------------------------------|\n| `3D` | `unbatched) or 4D (batched) tensor with shape` \u003cbr /\u003e `(..., height, width, channels)`, in `\"channels_last\"` format. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Output shape ------------ ||\n|------|------------------------------------------------------------------------------------------------|\n| `3D` | `unbatched) or 4D (batched) tensor with shape` \u003cbr /\u003e `(..., height, random_width, channels)`. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Attributes ---------- ||\n|------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `auto_vectorize` | Control whether automatic vectorization occurs. \u003cbr /\u003e By default the `call()` method leverages the [`tf.vectorized_map()`](../../../tf/vectorized_map) function. Auto-vectorization can be disabled by setting `self.auto_vectorize = False` in your `__init__()` method. When disabled, `call()` instead relies on [`tf.map_fn()`](../../../tf/map_fn). For example: class SubclassLayer(BaseImageAugmentationLayer): def __init__(self): super().__init__() self.auto_vectorize = False \u003cbr /\u003e |\n\n\u003cbr /\u003e"]]
View source on GitHub