tf.nn.max_pool
Stay organized with collections
Save and categorize content based on your preferences.
Performs the max pooling on the input.
tf.nn.max_pool(
input, ksize, strides, padding, data_format=None, name=None
)
Args |
|---|
input
|
Tensor of rank N+2, of shape [batch_size] + input_spatial_shape +
[num_channels] if data_format does not start with "NC" (default), or
[batch_size, num_channels] + input_spatial_shape if data_format starts
with "NC". Pooling happens over the spatial dimensions only.
|
ksize
|
An int or list of ints that has length 1, N or N+2. The size
of the window for each dimension of the input tensor.
|
strides
|
An int or list of ints that has length 1, N or N+2. The
stride of the sliding window for each dimension of the input tensor.
|
padding
|
Either the string"SAME"or"VALID"indicating the type of
padding algorithm to use, or a list indicating the explicit paddings at
the start and end of each dimension. When explicit padding is used and
data_format is"NHWC", this should be in the form[[0, 0], [pad_top,
pad_bottom], [pad_left, pad_right], [0, 0]]. When explicit padding used
and data_format is"NCHW", this should be in the form[[0, 0], [0, 0],
[pad_top, pad_bottom], [pad_left, pad_right]]. When using explicit
padding, the size of the paddings cannot be greater than the sliding
window size.
</td>
</tr><tr>
<td>data_format</td>
<td>
A string. Specifies the channel dimension. For N=1 it can be
either "NWC" (default) or "NCW", for N=2 it can be either "NHWC" (default)
or "NCHW" and for N=3 either "NDHWC" (default) or "NCDHW".
</td>
</tr><tr>
<td>name`
|
Optional name for the operation.
|
Returns |
|---|
A Tensor of format specified by data_format.
The max pooled output tensor.
|
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.
[null,null,["Last updated 2021-02-18 UTC."],[],[],null,["# tf.nn.max_pool\n\n\u003cbr /\u003e\n\n|------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------|\n| [TensorFlow 1 version](/versions/r1.15/api_docs/python/tf/nn/max_pool) | [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.4.0/tensorflow/python/ops/nn_ops.py#L4479-L4551) |\n\nPerforms the max pooling on the input.\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.nn.max_pool_v2`](https://www.tensorflow.org/api_docs/python/tf/nn/max_pool)\n\n\u003cbr /\u003e\n\n tf.nn.max_pool(\n input, ksize, strides, padding, data_format=None, name=None\n )\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-----------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------|\n| `input` | Tensor of rank N+2, of shape `[batch_size] + input_spatial_shape + [num_channels]` if `data_format` does not start with \"NC\" (default), or `[batch_size, num_channels] + input_spatial_shape` if data_format starts with \"NC\". Pooling happens over the spatial dimensions only. |\n| `ksize` | An int or list of `ints` that has length `1`, `N` or `N+2`. The size of the window for each dimension of the input tensor. |\n| `strides` | An int or list of `ints` that has length `1`, `N` or `N+2`. The stride of the sliding window for each dimension of the input tensor. |\n| `padding` | Either the `string`\"SAME\"`or`\"VALID\"`indicating the type of padding algorithm to use, or a list indicating the explicit paddings at the start and end of each dimension. When explicit padding is used and data_format is`\"NHWC\"`, this should be in the form`\\[\\[0, 0\\], \\[pad_top, pad_bottom\\], \\[pad_left, pad_right\\], \\[0, 0\\]\\]`. When explicit padding used and data_format is`\"NCHW\"`, this should be in the form`\\[\\[0, 0\\], \\[0, 0\\], \\[pad_top, pad_bottom\\], \\[pad_left, pad_right\\]\\]`. When using explicit padding, the size of the paddings cannot be greater than the sliding window size. \u003c/td\u003e \u003c/tr\u003e\u003ctr\u003e \u003ctd\u003e`data_format`\u003c/td\u003e \u003ctd\u003e A string. Specifies the channel dimension. For N=1 it can be either \"NWC\" (default) or \"NCW\", for N=2 it can be either \"NHWC\" (default) or \"NCHW\" and for N=3 either \"NDHWC\" (default) or \"NCDHW\". \u003c/td\u003e \u003c/tr\u003e\u003ctr\u003e \u003ctd\u003e`name\\` | Optional name for the operation. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A `Tensor` of format specified by `data_format`. The max pooled output tensor. ||\n\n\u003cbr /\u003e"]]
TensorFlow 1 version
View source on GitHub