Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update pooling.md - Fix typo in Chinese version #1309

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update pooling.md - Fix typo in Chinese version #1309

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
2 changes: 1 addition & 1 deletion chapter_convolutional-neural-networks/pooling.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ $$

回到本节开头提到的对象边缘检测示例，现在我们将使用卷积层的输出作为$2\times 2$最大汇聚的输入。
设置卷积层输入为`X`，汇聚层输出为`Y`。
无论`X[i, j]`和`X[i, j + 1]`的值相同与否，或`X[i, j + 1]`和`X[i, j + 2]`的值相同与否，汇聚层始终输出`Y[i, j] = 1`。
无论`X[i, j]`，`X[i, j + 1]`，`X[i + 1, j]`和`X[i + 1, j + 1]`的值相同与否，汇聚层始终输出`Y[i, j] = 1`。
也就是说，使用$2\times 2$最大汇聚层，即使在高度或宽度上移动一个元素，卷积层仍然可以识别到模式。

在下面的代码中的`pool2d`函数，我们(**实现汇聚层的前向传播**)。
Expand Down