tf.keras.layers.GlobalMaxPooling1D
Stay organized with collections
Save and categorize content based on your preferences.
Global max pooling operation for 1D temporal data.
Inherits From: Layer, Module
tf.keras.layers.GlobalMaxPooling1D(
data_format='channels_last', keepdims=False, **kwargs
)
Downsamples the input representation by taking the maximum value over
the time dimension.
For example:
x = tf.constant([[1., 2., 3.], [4., 5., 6.], [7., 8., 9.]])
x = tf.reshape(x, [3, 3, 1])
x
<tf.Tensor: shape=(3, 3, 1), dtype=float32, numpy=
array([[[1.], [2.], [3.]],
[[4.], [5.], [6.]],
[[7.], [8.], [9.]]], dtype=float32)>
max_pool_1d = tf.keras.layers.GlobalMaxPooling1D()
max_pool_1d(x)
<tf.Tensor: shape=(3, 1), dtype=float32, numpy=
array([[3.],
[6.],
[9.], dtype=float32)>
Args |
|---|
data_format
|
A string,
one of channels_last (default) or channels_first.
The ordering of the dimensions in the inputs.
channels_last corresponds to inputs with shape
(batch, steps, features) while channels_first
corresponds to inputs with shape
(batch, features, steps).
|
keepdims
|
A boolean, whether to keep the temporal dimension or not.
If keepdims is False (default), the rank of the tensor is reduced
for spatial dimensions.
If keepdims is True, the temporal dimension are retained with
length 1.
The behavior is the same as for tf.reduce_max or np.max.
|
|
|---|
- If
data_format='channels_last':
3D tensor with shape:
(batch_size, steps, features)
- If
data_format='channels_first':
3D tensor with shape:
(batch_size, features, steps)
|
Output shape |
|---|
- If
keepdims=False:
2D tensor with shape (batch_size, features).
- If
keepdims=True:
- If
data_format='channels_last':
3D tensor with shape (batch_size, 1, features)
- If
data_format='channels_first':
3D tensor with shape (batch_size, features, 1)
|
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 2024-01-23 UTC.
[null,null,["Last updated 2024-01-23 UTC."],[],[],null,["# tf.keras.layers.GlobalMaxPooling1D\n\n\u003cbr /\u003e\n\n|--------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v2.15.0/keras/layers/pooling/global_max_pooling1d.py#L25-L83) |\n\nGlobal max pooling operation for 1D temporal data.\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.GlobalMaxPool1D`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/GlobalMaxPooling1D)\n\n\u003cbr /\u003e\n\n tf.keras.layers.GlobalMaxPooling1D(\n data_format='channels_last', keepdims=False, **kwargs\n )\n\nDownsamples the input representation by taking the maximum value over\nthe time dimension.\n\n#### For example:\n\n x = tf.constant([[1., 2., 3.], [4., 5., 6.], [7., 8., 9.]])\n x = tf.reshape(x, [3, 3, 1])\n x\n \u003ctf.Tensor: shape=(3, 3, 1), dtype=float32, numpy=\n array([[[1.], [2.], [3.]],\n [[4.], [5.], [6.]],\n [[7.], [8.], [9.]]], dtype=float32)\u003e\n max_pool_1d = tf.keras.layers.GlobalMaxPooling1D()\n max_pool_1d(x)\n \u003ctf.Tensor: shape=(3, 1), dtype=float32, numpy=\n array([[3.],\n [6.],\n [9.], dtype=float32)\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|---------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `data_format` | A string, one of `channels_last` (default) or `channels_first`. The ordering of the dimensions in the inputs. `channels_last` corresponds to inputs with shape `(batch, steps, features)` while `channels_first` corresponds to inputs with shape `(batch, features, steps)`. |\n| `keepdims` | A boolean, whether to keep the temporal dimension or not. If `keepdims` is `False` (default), the rank of the tensor is reduced for spatial dimensions. If `keepdims` is `True`, the temporal dimension are retained with length 1. The behavior is the same as for [`tf.reduce_max`](../../../tf/math/reduce_max) or `np.max`. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Input shape ----------- ||\n|---|---|\n| \u003cbr /\u003e - If `data_format='channels_last'`: 3D tensor with shape: `(batch_size, steps, features)` - If `data_format='channels_first'`: 3D tensor with shape: `(batch_size, features, steps)` ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Output shape ------------ ||\n|---|---|\n| \u003cbr /\u003e - If `keepdims`=False: 2D tensor with shape `(batch_size, features)`. - If `keepdims`=True: - If `data_format='channels_last'`: 3D tensor with shape `(batch_size, 1, features)` - If `data_format='channels_first'`: 3D tensor with shape `(batch_size, features, 1)` ||\n\n\u003cbr /\u003e"]]
View source on GitHub