21多输入多输出通道

点击查看代码

import torch
from d2l import torch as d2l

def corr2d_multi_in(X, K):
    # 先遍历“X”和“K”的第0个维度（通道维度），再把它们加在一起
    # print('K.shape = ', K.shape)
    return sum(d2l.corr2d(x, k) for x, k in zip(X, K))

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))
"""
tensor([[ 56.,  72.],
        [104., 120.]])
"""

def corr2d_multi_in_out(X, K):
    # 迭代“K”的第0个维度，每次都对输入“X”执行互相关运算。
    # 最后将所有结果都叠加在一起
    return torch.stack([corr2d_multi_in(X, k) for k in K], 0)

# K = torch.tensor([[[0.0, 1.0], [2.0, 3.0]], [[1.0, 2.0], [3.0, 4.0]]])
# print(K.shape)
"""torch.Size([2, 2, 2])"""
K = torch.stack((K, K + 1, K + 2), 0)
# print(K.shape)
"""torch.Size([3, 2, 2, 2])"""
# print(corr2d_multi_in_out(X, K).shape)
"""
tensor([[[ 56.,  72.],
         [104., 120.]],

        [[ 76., 100.],
         [148., 172.]],

        [[ 96., 128.],
         [192., 224.]]])
corr2d_multi_in_out(X, K).shape = torch.Size([3, 2, 2])
"""

# 使用全连接层实现1*1卷积
# 对输入和输出的数据形状进行调整
def corr2d_multi_in_out_1x1(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))
    # 全连接层中的矩阵乘法
    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_1x1(X, K)
Y2 = corr2d_multi_in_out(X, K)
assert float(torch.abs(Y1 - Y2).sum()) < 1e-6