反卷积的真正含义

Transpose convolution （was Deconvolution）

转载自：http://datascience.stackexchange.com/questions/6107/what-are-deconvolutional-layers

Deconvolution layer is a very unfortunate name and should rather be called a transposed convolutional layer.

Visually, for a transposed convolution with stride one and no padding, we just pad the original input (blue entries) with zeroes (white entries) (Figure 1).

In case of stride two and padding, the transposed convolution would look like this (Figure 2):

You can find more (great) visualisations of convolutional arithmetics here.