tf.keras.layers.RandomCrop
Stay organized with collections
Save and categorize content based on your preferences.
Randomly crop the images to target height and width.
Inherits From: Layer, Module
tf.keras.layers.RandomCrop(
height, width, seed=None, **kwargs
)
This layer will crop all the images in the same batch to the same cropping
location.
By default, random cropping is only applied during training. At inference
time, the images will be first rescaled to preserve the shorter side, and
center cropped. If you need to apply random cropping at inference time,
set training to True when calling the layer.
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:
(..., target_height, target_width, channels).
Args |
|---|
height
|
Integer, the height of the output shape.
|
width
|
Integer, the width of the output shape.
|
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.RandomCrop\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#L197-L311) |\n\nRandomly crop the images to target height and width.\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.RandomCrop`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomCrop)\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.RandomCrop`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomCrop), [`tf.compat.v1.keras.layers.experimental.preprocessing.RandomCrop`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/RandomCrop)\n\n\u003cbr /\u003e\n\n tf.keras.layers.RandomCrop(\n height, width, seed=None, **kwargs\n )\n\nThis layer will crop all the images in the same batch to the same cropping\nlocation.\nBy default, random cropping is only applied during training. At inference\ntime, the images will be first rescaled to preserve the shorter side, and\ncenter cropped. If you need to apply random cropping at inference time,\nset `training` to True when calling the layer.\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`(..., target_height, target_width, channels)`.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|----------|------------------------------------------|\n| `height` | Integer, the height of the output shape. |\n| `width` | Integer, the width of the output shape. |\n| `seed` | Integer. Used to create a random seed. |\n\n\u003cbr /\u003e"]]
View source on GitHub