Max-pooling layers kind of “zoom out”. They allow later convolutional layers to work on larger sections of the data, because a small patch after the pooling layer corresponds to a much larger patch before it. They also make us invariant to some very small transformations of the data.
a small patch after the pooling layer corresponds to a much larger patch before it. 这个怎么解释，池化后一个small patch对应之前一个大一点的patch?
如何修改驱动参数使之变成竖屏。通过修改注册表只能把显示调整成竖屏，即LCD旋转90度，但是触摸点的位置还是原来的。所以真能通过调整驱动来实