版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/fantacy10000/article/details/83244295
关键词：Maxpooling、Averagepooling、Globalmaxpooling、Globalaveragepooling
原文地址：文档对应地址
1.MaxPooling1D层、MaxPooling2D层、MaxPooling3D层
作用：最大值池化
keras.layers.pooling.MaxPooling1D(pool_size=2, strides=None, padding='valid')
keras.layers.pooling.MaxPooling2D(pool_size=(2, 2), strides=None, padding='valid', data_format=None)
keras.layers.pooling.MaxPooling3D(pool_size=(2, 2, 2), strides=None, padding='valid', data_format=None)
2.AveragePooling1D层、AveragePooling2D层、AveragePooling3D层
作用：平均值池化
keras.layers.pooling.AveragePooling1D(pool_size=2, strides=None, padding='valid')
keras.layers.pooling.AveragePooling2D(pool_size=(2, 2), strides=None, padding='valid', data_format=None)
keras.layers.pooling.AveragePooling3D(pool_size=(2, 2, 2), strides=None, padding='valid', data_format=None)
3.GlobalMaxPooling1D层、GlobalMaxPooling2D层
4.GlobalAveragePooling1D层、GlobalAveragePooling2D层