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.

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

update conv-layer about receptive field #1290

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion chapter_convolutional-neural-networks/conv-layer.md
Original file line number Diff line number Diff line change
Expand Up @@ -347,7 +347,8 @@ d2l.reshape(conv2d.weight, (1, 2))
请注意,感受野可能大于输入的实际大小。让我们用 :numref:`fig_correlation`为例来解释感受野:
给定$2 \times 2$卷积核,阴影输出元素值$19$的感受野是输入阴影部分的四个元素。
假设之前输出为$\mathbf{Y}$,其大小为$2 \times 2$,现在我们在其后附加一个卷积层,该卷积层以$\mathbf{Y}$为输入,输出单个元素$z$。
在这种情况下,$\mathbf{Y}$上的$z$的感受野包括$\mathbf{Y}$的所有四个元素,而输入的感受野包括最初所有九个输入元素。
在这种情况下,$z$在层$\mathbf{Y}$上的感受野包括$\mathbf{Y}$的所有四个元素,
而在输入的$3 \times 3$的张量上的感受野包括最初所有九个输入元素。
因此,当一个特征图中的任意元素需要检测更广区域的输入特征时,我们可以构建一个更深的网络。

## 小结
Expand Down
Loading