Transposed Convolution

最新推荐文章于 2020-12-04 21:33:35 发布

weixin_33743248

最新推荐文章于 2020-12-04 21:33:35 发布

阅读量62

点赞数

CC 4.0 BY-SA版权

原文链接：http://www.cnblogs.com/leebxo/p/10095102.html

本文深入探讨了转置卷积，又称分数步长卷积或deconvolutions，其工作原理在于交换卷积的前向和后向传播过程。通过实例说明了如何确定直接卷积与转置卷积，并解释了在某些情况下，可以通过增加输入中的零填充来模拟转置卷积，尽管这通常会导致效率降低。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

　 A guide to convlution arithmetic for deep learning-Transposed Convolution

　　Transposed convolutions – also called fractionally strided convolutions or deconvolutions – work by swapping the forward and backward passes of a convolution. One way to put it is to note that the kernel defines a convolution, but whether it’s a direct convolution or a transposed convolution is determined by how the forward and backward passes are computed.

　　For instance, although the kernel w defines a convolution whose forward and backward passes are computed by multiplying with C and C T respectively, it also defines a transposed convolution whose forward and backward passes are computed by multiplying with C T and (C T ) T = C respectively.

　　Finally note that it is always possible to emulate a transposed convolution with a direct convolution. The disadvantage is that it usually involves adding many columns and rows of zeros to the input, resulting in a much less efficient implementation.

　　Notably, the kernel’s and stride’s sizes remain the same, but the input of the transposed convolution is now zero padded. One way to understand the logic behind zero padding is to consider the connectivity pattern of the transposed convolution and use it to guide the design of the equivalent convolution. For example, the top left pixel of the input of the direct convolution only contribute to the top left pixel of the output, the top right pixel is only connected to the top right output pixel, and so on.

转载于:https://www.cnblogs.com/leebxo/p/10095102.html