基础学习：（5）不同卷积

---

前言

本文言简意赅的说明了反卷积（deconvlution），卷积（convolution），转置卷积（transposed convolution），空洞卷积（dilated convolution）的区别

---

1 deconvlution == transposed convolution

之前人觉得叫deconvolution 不够严谨，所以改成了叫 transposed convolution
deconv 就是 还原尺寸，其他没啥。

Vincent Dumoulin, Francesco Visin - A guide to convolution arithmetic for deep learning (BibTeX)

2 对比

这里我看到网上github 上讲的最好，有时候打开github 比较慢，我这里复制了下来
链接：https://github.com/vdumoulin/conv_arithmetic/tree/master

2.1 Convolution animations

N.B.: Blue maps are inputs, and cyan maps are outputs.

no padding, no strides	Arbitrary padding, no strides	Half padding, no strides	Full padding, no strides	No padding, strides	Padding, strides	Padding, strides (odd)

2.2 Transposed convolution animations

N.B.: Blue maps are inputs, and cyan maps are outputs.

no padding, no strides, transposed	Arbitrary padding, no strides, transposed	Half padding, no strides, transposed	Full padding, no strides, transposed	No padding, strides, transposed	Padding, strides, transposed	Padding, strides (odd), transposed

2.3 Dilated convolution

N.B.: Blue maps are inputs, and cyan maps are outputs.

No padding, no stride, dilation