标签：multi 1.0 卷积 torch corr2d 神经网络 李沐 out
多通道卷积计算
特殊的卷积层1*1卷积核
代码：
"""
多输入多输出的互相关运算
"""
import torch
from torch import nn
from d2l import torch as d2l
"""
实现多输入通道互相关运算
"""
def corr2d_multi_in(x, k):
return sum(d2l.corr2d(x, k) for x, k in zip(x, k))
"""
验证互相关运算的输出
"""
X = torch.tensor([[[0.0, 1.0, 2.0], [3.0, 4.0, 5.0], [6.0, 7.0, 8.0]],
[[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]]])
K = torch.tensor([[[0.0, 1.0], [2.0, 3.0]], [[1.0, 2.0], [3.0, 4.0]]])
print(corr2d_multi_in(X, K))
"""
计算多个通道的输出的互相关函数
"""
def corr2d_multi_in_out(X, K):
return torch.stack([corr2d_multi_in(X, k) for k in K], 0)
K = torch.stack((K, K + 1, K + 2), 0)
print(K.shape)
print(corr2d_multi_in_out(X, K))
"""
1*1卷积
"""
def corr2d_multi_in_out_1_1(X, K):
c_i, h, w = X.shape
c_o = K.shape[0]
X = X.reshape((c_i, h * w))
K = K.reshape((c_o, c_i))
Y = torch.matmul(K, X)
return Y.reshape((c_o, h, w))
X = torch.normal(0, 1, (3, 3, 3))
K = torch.normal(0, 1, (2, 3, 1, 1))
Y1 = corr2d_multi_in_out_1_1(X, K)
Y2 = corr2d_multi_in_out(X, K)
assert float(torch.abs(Y1 - Y2).sum()) < 1e-6
标签：multi,
1.0,
卷积,
torch,
corr2d,
神经网络,
李沐,
out
From： https://blog.csdn.net/2401_87085787/article/details/142107878