MaxPooling3D 类tf_keras.layers.MaxPooling3D(
pool_size=(2, 2, 2), strides=None, padding="valid", data_format=None, **kwargs
)
用于 3D 数据(空间或时空)的最大池化操作。
通过对输入窗口(大小由 pool_size 定义)中的最大值进行计算,并针对输入的每个通道,沿其空间维度(深度、高度和宽度)进行下采样。窗口沿每个维度由 strides 进行移动。
参数
(2, 2, 2) 将使 3D 输入在每个维度的大小减半。"valid" 或 "same"(不区分大小写)之一。"valid" 表示无填充。"same" 会在输入的左/右或上/下进行均匀填充,使得输出与输入具有相同的高度/宽度维度。channels_last(默认)或 channels_first。输入张量的维度顺序。channels_last 对应形状为 (batch, spatial_dim1, spatial_dim2, spatial_dim3, channels) 的输入,而 channels_first 对应形状为 (batch, channels, spatial_dim1, spatial_dim2, spatial_dim3) 的输入。如果不指定,将使用您 TF-Keras 配置文件 ~/.keras/keras.json 中找到的 image_data_format 值(如果存在),否则默认为 'channels_last'。默认为 'channels_last'。输入形状
data_format='channels_last':5D 张量,形状为:(batch_size, spatial_dim1, spatial_dim2, spatial_dim3, channels)data_format='channels_first':5D 张量,形状为:(batch_size, channels, spatial_dim1, spatial_dim2, spatial_dim3)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
input_channels = 3
inputs = tf.keras.Input(shape=(depth, height, width, input_channels))
layer = tf.keras.layers.MaxPooling3D(pool_size=3)
outputs = layer(inputs) # Shape: (batch_size, 10, 10, 10, 3)