tf.keras.layers.Reshape
Stay organized with collections
Save and categorize content based on your preferences.
Layer that reshapes inputs into the given shape.
Inherits From: Layer, Module
View aliases
Compat aliases for migration
See
Migration guide for
more details.
`tf.compat.v1.keras.layers.Reshape`
tf.keras.layers.Reshape(
target_shape, **kwargs
)
|
|---|
Arbitrary, although all dimensions in the input shape must be known/fixed.
Use the keyword argument input_shape (tuple of integers, does not
include the samples/batch size axis) when using this layer as the first
layer in a model.
|
Output shape |
|---|
(batch_size,) + target_shape
|
Example:
# as first layer in a Sequential model
model = tf.keras.Sequential()
model.add(tf.keras.layers.Reshape((3, 4), input_shape=(12,)))
# model.output_shape == (None, 3, 4), `None` is the batch size.
model.output_shape
(None, 3, 4)
# as intermediate layer in a Sequential model
model.add(tf.keras.layers.Reshape((6, 2)))
model.output_shape
(None, 6, 2)
# also supports shape inference using `-1` as dimension
model.add(tf.keras.layers.Reshape((-1, 2, 2)))
model.output_shape
(None, 3, 2, 2)
Args |
|---|
target_shape
|
Target shape. Tuple of integers, does not include the
samples dimension (batch size).
|
**kwargs
|
Any additional layer keyword arguments.
|
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.Reshape\n\n\u003cbr /\u003e\n\n|----------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v2.10.0/keras/layers/reshaping/reshape.py#L27-L148) |\n\nLayer that reshapes inputs into the given shape.\n\nInherits From: [`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.Reshape\\`\n\n\u003cbr /\u003e\n\n tf.keras.layers.Reshape(\n target_shape, **kwargs\n )\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Input shape ----------- ||\n|---|---|\n| Arbitrary, although all dimensions in the input shape must be known/fixed. Use the keyword argument `input_shape` (tuple of integers, does not include the samples/batch size axis) when using this layer as the first layer in a model. ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Output shape ------------ ||\n|---|---|\n| `(batch_size,) + target_shape` ||\n\n\u003cbr /\u003e\n\n#### Example:\n\n # as first layer in a Sequential model\n model = tf.keras.Sequential()\n model.add(tf.keras.layers.Reshape((3, 4), input_shape=(12,)))\n # model.output_shape == (None, 3, 4), `None` is the batch size.\n model.output_shape\n (None, 3, 4)\n\n # as intermediate layer in a Sequential model\n model.add(tf.keras.layers.Reshape((6, 2)))\n model.output_shape\n (None, 6, 2)\n\n # also supports shape inference using `-1` as dimension\n model.add(tf.keras.layers.Reshape((-1, 2, 2)))\n model.output_shape\n (None, 3, 2, 2)\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|----------------|---------------------------------------------------------------------------------------|\n| `target_shape` | Target shape. Tuple of integers, does not include the samples dimension (batch size). |\n| `**kwargs` | Any additional layer keyword arguments. |\n\n\u003cbr /\u003e"]]
View source on GitHub