Size In Covolutional Layer: l
\text{Size In Covolutional Layer: l}\\
Size In Covolutional Layer: l
Filter Size:f[l]Width and hight of a filterPadding:p[l]The extra edge added aroundStride:s[l]The step for filter to moveChannel:nc[l]Equal to the numbers of filtersFilter:f[l]×f[l]×nc[l−1]Input:nh[l−1]×nw[l−1]×nc[l−1]e.g.An image shaped(32,32,3)Output:nh[l]×nw[l]×nc[l]nn/w[l]=⌊nn/w[l−1]+2p[l]−f[l]s[l]+1⌋Note1:Deeper, nh/w[l]↑while nc[l]↓Note2:Input→Conv→Add Bias→ReLU→Output
\begin{aligned}
&& Filter\ Size&: & f^{[l]} &\quad \text{Width and hight of a filter}\\
&& Padding &: &p^{[l]} &\quad \text{The extra edge added around}\\
&& Stride & : &s^{[l]} &\quad \text{The step for filter to move}\\
&& Channel &: &n_c^{[l]}&\quad \text{Equal to the numbers of filters}\\
&& Filter&: & f^{[l]} \times f^{[l]} \times n_c^{[l-1]}\\
&& Input&: & n_h^{[l-1]} \times n_w^{[l-1]} \times n_c^{[l-1]} &\quad \text{e.g.An image shaped(32,32,3)}\\
&& Output&: & n_h^{[l]} \times n_w^{[l]} \times n_c^{[l]}\\
&& n_{n/w}^{[l]} &= & \biggl \lfloor\frac{n_{n/w}^{[l-1]} + 2p^{[l]}-f^{[l]}}{s^{[l]}}+1 \biggr \rfloor\\
&& Note1 & : & \text{Deeper, } n_{h/w}^{[l]} \uparrow \text{while } n_c^{[l]} \downarrow\\
&& Note2 & : &Input \rightarrow Conv \rightarrow Add\ Bias & \rightarrow ReLU \rightarrow Output
\end{aligned}
Filter SizePaddingStrideChannelFilterInputOutputnn/w[l]Note1Note2:::::::=::f[l]p[l]s[l]nc[l]f[l]×f[l]×nc[l−1]nh[l−1]×nw[l−1]×nc[l−1]nh[l]×nw[l]×nc[l]⌊s[l]nn/w[l−1]+2p[l]−f[l]+1⌋Deeper, nh/w[l]↑while nc[l]↓Input→Conv→Add BiasWidth and hight of a filterThe extra edge added aroundThe step for filter to moveEqual to the numbers of filterse.g.An image shaped(32,32,3)→ReLU→Output
【助记】CNN的维度变化
最新推荐文章于 2025-01-27 23:21:02 发布
扫一扫
2122
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
