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?
如何理解最大池化层有几分缩小?
- 写回答
- 好问题 0 提建议
- 关注问题
- 邀请回答
-
1条回答 默认 最新
mianbaohebg 2016-12-17 15:00关注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
解决 无用评论 打赏 举报