tf.keras.layers.AveragePooling3D

View source on GitHub

Average pooling operation for 3D data (spatial or spatio-temporal).

Inherits From: Layer, Operation

tf.keras.layers.AveragePooling3D(
    pool_size,
    strides=None,
    padding='valid',
    data_format=None,
    name=None,
    **kwargs
)

Downsamples the input along its spatial dimensions (depth, height, and width) by taking the average value over an input window (of size defined by pool_size) for each channel of the input. The window is shifted by strides along each dimension.

Input shape:

• If data_format="channels_last": 5D tensor with shape: (batch_size, spatial_dim1, spatial_dim2, spatial_dim3, channels)
• If data_format="channels_first": 5D tensor with shape: (batch_size, channels, spatial_dim1, spatial_dim2, spatial_dim3)

Output shape:

• If data_format="channels_last": 5D tensor with shape: (batch_size, pooled_dim1, pooled_dim2, pooled_dim3, channels)
• If data_format="channels_first": 5D tensor with shape: (batch_size, channels, pooled_dim1, pooled_dim2, pooled_dim3)

Example:

depth = 30
height = 30
width = 30
channels = 3

inputs = keras.layers.Input(shape=(depth, height, width, channels))
layer = keras.layers.AveragePooling3D(pool_size=3)
outputs = layer(inputs)  # Shape: (batch_size, 10, 10, 10, 3)

Methods

from_config

View source

@classmethod
from_config(
    config
)

Creates a layer from its config.

This method is the reverse of get_config, capable of instantiating the same layer from the config dictionary. It does not handle layer connectivity (handled by Network), nor weights (handled by set_weights).

symbolic_call

View source

symbolic_call(
    *args, **kwargs
)