I am building a 1D Convolutional Neural Network (CNN). From many sources I have understood that performance of the CNN increases if more layers are added.
Pooling allows features to shift relative to each other resulting in robust matching of features even in the presence of small distortions. There are also many other benefits of doing pooling, like:
Reduces the spatial dimension of the feature map.
And hence also reducing the number of parameters high up the processing hierarchy. This simplifies the overall model complexity.
这并不总是真的。它通常取决于您拥有的数据和您试图解决的任务。在
引用https://www.quora.com/Why-do-we-use-pooling-layer-in-convolutional-neural-networks
然后,根据步幅、池大小和填充,您可能会自愿减少输出形状。在
回到你的问题,如果你不想你的形状变小,考虑使用跨步=1和padding='same'。在
(见https://keras.io/layers/pooling)
相关问题 更多 >
编程相关推荐