Pytorch conv_transpose2d是卷积运算还是互相关运算?
对于nn,我们提到它有一个互相关,然而,我的结果表明它有一个卷积算子Pytorch conv_transpose2d是卷积运算还是互相关运算?,pytorch,torch,Pytorch,Torch,对于nn,我们提到它有一个互相关,然而,我的结果表明它有一个卷积算子 import torch import torch.nn.functional as F im = torch.Tensor([[0,1],[2,3]]).unsqueeze(0).unsqueeze(0) kernel = torch.Tensor([[0,1,2],[3,4,5], [6,7,8]]).unsqueeze(0).unsqueeze(0) op = F.conv_transpose2d(im, kernel
import torch
import torch.nn.functional as F
im = torch.Tensor([[0,1],[2,3]]).unsqueeze(0).unsqueeze(0)
kernel = torch.Tensor([[0,1,2],[3,4,5], [6,7,8]]).unsqueeze(0).unsqueeze(0)
op = F.conv_transpose2d(im, kernel, stride=2)
print(op)
它输出:
tensor([[[[ 0., 0., 0., 1., 2.],
[ 0., 0., 3., 4., 5.],
[ 0., 2., 10., 10., 14.],
[ 6., 8., 19., 12., 15.],
[12., 14., 34., 21., 24.]]]])
如果有卷积的话,结果会是这样的,我原以为相关结果是:
tensor([[[[ 0., 0., 8., 7., 6.],
[ 0., 0., 5., 4., 3.],
[16., 14., 38., 22., 18.],
[10., 8., 21., 12., 9.],
[ 4., 2., 6., 3., 0.]]]])
我误解了什么吗