tf.keras.ops.average_pool | TensorFlow v2.16.1 (original) (raw)
tf.keras.ops.average_pool
Average pooling operation.
View aliases
Main aliases
tf.keras.ops.average_pool(
inputs,
pool_size,
strides=None,
padding='valid',
data_format=None
)
| Args | |
|---|---|
| inputs | Tensor of rank N+2. inputs has shape(batch_size,) + inputs_spatial_shape + (num_channels,) ifdata_format="channels_last", or(batch_size, num_channels) + inputs_spatial_shape ifdata_format="channels_first". Pooling happens over the spatial dimensions only. |
| pool_size | int or tuple/list of integers of sizelen(inputs_spatial_shape), specifying the size of the pooling window for each spatial dimension of the input tensor. Ifpool_size is int, then every spatial dimension shares the samepool_size. |
| strides | int or tuple/list of integers of sizelen(inputs_spatial_shape). The stride of the sliding window for each spatial dimension of the input tensor. If strides is int, then every spatial dimension shares the same strides. |
| padding | string, either "valid" or "same". "valid" means no padding is applied, and "same" results in padding evenly to the left/right or up/down of the input such that output has the same height/width dimension as the input when strides=1. |
| data_format | A string, either "channels_last" or "channels_first".data_format determines the ordering of the dimensions in the inputs. If data_format="channels_last", inputs is of shape(batch_size, ..., channels) while ifdata_format="channels_first", inputs is of shape(batch_size, channels, ...). |
| Returns |
|---|
| A tensor of rank N+2, the result of the average pooling operation. |
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 2024-06-07 UTC.