AveragePooling3D
类keras.layers.AveragePooling3D(
pool_size, strides=None, padding="valid", data_format=None, name=None, **kwargs
)
用于 3D 数据(空间或时空)的平均池化操作。
通过对输入的每个通道,在其空间维度(深度、高度和宽度)上采用输入窗口(大小由 pool_size
定义)内的平均值来对输入进行下采样。窗口沿着每个维度以 strides
为步长进行滑动。
参数
pool_size
。如果只指定一个整数,则所有维度将使用相同的步长大小。"valid"
或 "same"
(不区分大小写)。"valid"
表示无填充。"same"
会在输入的左/右或上/下均匀填充,使得输出具有与输入相同的空间维度。"channels_last"
或 "channels_first"
。输入中维度的顺序。"channels_last"
对应于形状为 (batch, spatial_dim1, spatial_dim2, spatial_dim3, channels)
的输入,而 "channels_first"
对应于形状为 (batch, channels, spatial_dim1, spatial_dim2, spatial_dim3)
的输入。它默认为 Keras 配置文件 ~/.keras/keras.json
中的 image_data_format
值。如果你从未设置过,则默认为 "channels_last"
。输入形状
data_format="channels_last"
:形状为 (batch_size, spatial_dim1, spatial_dim2, spatial_dim3, channels)
的 5D 张量data_format="channels_first"
:形状为 (batch_size, channels, spatial_dim1, spatial_dim2, spatial_dim3)
的 5D 张量输出形状
data_format="channels_last"
:形状为 (batch_size, pooled_dim1, pooled_dim2, pooled_dim3, channels)
的 5D 张量data_format="channels_first"
:形状为 (batch_size, channels, pooled_dim1, pooled_dim2, pooled_dim3)
的 5D 张量示例
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)