PyTorch中的自定义卷积核和环形卷积。

Question

PyTorch中的自定义卷积核和环形卷积。

paddingconvolutionpytorchconv-neural-network

4

我希望对PyTorch卷积进行两个操作，这些操作在文档或代码中没有提到：

I want to create a convolution with a fixed kernel like this:
```
000010000
000010000
100010001
000010000
000010000
```
The horizontal aspect is like dilation, I guess, but the vertical part is different. I see that dilation is available as a parameter in the code, but it has to be a scalar or single-element tuple (not one element per dimension), so I don't think it can do what I want here.
I would like my convolutions to "wrap around" like a toroid, rather than use padding.

EDIT TO ADD: I see that there is an open issue for this , which also provides a suboptimal workaround. So, I guess that there's no "right" way to do it, yet.

- jmmcd

1个回答

网页内容由stack overflow 提供, 点击上面的

可以查看英文原文，
原文链接

- benjaminplanche · Accepted Answer

与torch.nn.conv2d()不同的是（它实例化自己的可训练核），torch.nn.functional.conv2d()接受您的矩阵和核作为参数，因此您可以传递任何自定义核。
正如@zou3519在Github问题中建议的那样（链接到您自己提到的问题），您可以通过“在nxn网格中重复张量，然后裁剪出您需要的部分”来实现2D循环填充：

def circular_pad_2d(x, pad=(1, 1)):
   # Snipped by @zou3519 (https://github.com/zou3519)
   return x.repeat(*x_shape[:2])[
        (x.shape[0]-pad[0]):(2*x.shape[0]+pad[0]), 
        (x.shape[1]-pad[1]):(2*x.shape[1]+pad[1])
   ]

# Example:
x = torch.tensor([[1,2,3],[4,5,6]])
y = circular_pad_2d(x, pad=(2, 3))
print(y)
#     1     2     3     1     2     3     1     2     3
#     4     5     6     4     5     6     4     5     6
#     1     2     3     1     2     3     1     2     3
#     4     5     6     4     5     6     4     5     6

(previous) 在 torch.nn.functional 模块中，torch.nn.functional.pad() 也可以接受参数 mode=reflect，我想这就是你想要的吧？你可以使用此方法在执行卷积之前手动填充输入矩阵。 （注意：你还可以使用 torch.nn.ReflectionPad2d 层，专门为反射固定2D填充而设计）