参数展示： 来自tensorflow2.0的API

tf.keras.layers.MaxPool1D(
    pool_size=2, strides=None, padding='valid', data_format='channels_last',
    **kwargs
)

tf.keras.layers.MaxPool1D() 接受的是一个三维的tensor.

例子：

input_shape = (2420, 1140, 32)
x = tf.random.normal(input_shape)
max_pool_1d = tf.keras.layers.MaxPooling1D(pool_size=2,strides=1, padding='valid')
t = max_pool_1d(x)
print(t.shape)
max_pool_1d = tf.keras.layers.MaxPooling1D(pool_size=2,strides=2, padding='valid')
t = max_pool_1d(x)
print(t.shape)
max_pool_1d = tf.keras.layers.MaxPooling1D(pool_size=2,strides=1, padding='same')
t = max_pool_1d(x)
print(t.shape)

不同步长和不同的padding方式下的 池化后的数据的类型