从线性代数中我们知道线性算子是可交换的和关联的。
在深度学习世界中,此概念用于证明在NN层之间引入非线性是合理的,这种现象俗称为linear lasagna,(reference)。
在信号处理中,这是优化内存和/或运行时要求(reference)的众所周知的技巧。
因此,从不同的角度来看,合并卷积是一个非常有用的工具。如何使用PyTorch实施它?
答案 0 :(得分:5)
如果我们有y = x * a * b
(其中*
表示卷积,而a, b
是您的内核),则可以定义c = a * b
,使y = x * c = x * a * b
如下: / p>
import torch
def merge_conv_kernels(k1, k2):
"""
:input k1: A tensor of shape ``(out1, in1, s1, s1)``
:input k1: A tensor of shape ``(out2, in2, s2, s2)``
:returns: A tensor of shape ``(out2, in1, s1+s2-1, s1+s2-1)``
so that convolving with it equals convolving with k1 and
then with k2.
"""
padding = k2.shape[-1] - 1
# Flip because this is actually correlation, and permute to adapt to BHCW
k3 = torch.conv2d(k1.permute(1, 0, 2, 3), k2.flip(-1, -2),
padding=padding).permute(1, 0, 2, 3)
return k3
为说明等效性,此示例将分别具有900个参数和5000个参数的两个内核组合为一个由28个参数组成的等效内核:
# Create 2 conv. kernels
out1, in1, s1 = (100, 1, 3)
out2, in2, s2 = (2, 100, 5)
kernel1 = torch.rand(out1, in1, s1, s1, dtype=torch.float64)
kernel2 = torch.rand(out2, in2, s2, s2, dtype=torch.float64)
# propagate a random tensor through them. Note that padding
# corresponds to the "full" mathematical operation (s-1)
b, c, h, w = 1, 1, 6, 6
x = torch.rand(b, c, h, w, dtype=torch.float64) * 10
c1 = torch.conv2d(x, kernel1, padding=s1 - 1)
c2 = torch.conv2d(c1, kernel2, padding=s2 - 1)
# check that the collapsed conv2d is same as c2:
kernel3 = merge_conv_kernels(kernel1, kernel2)
c3 = torch.conv2d(x, kernel3, padding=kernel3.shape[-1] - 1)
print(kernel3.shape)
print((c2 - c3).abs().sum() < 1e-5)
注意:等效条件是假设我们具有无限的数值分辨率。我认为已经进行了有关堆叠许多低分辨率浮点线性运算的研究,并表明网络可以从数值误差中获利,但我找不到它。任何参考表示赞赏!