卷积层 autograd.grad

import torch
from torch import nn


def corr2d(X, K):  #@save
    """计算二维互相关运算"""
    h, w = K.shape
    Y = torch.zeros((X.shape[0] - h + 1, X.shape[1] - w + 1))
    for i in range(Y.shape[0]):
        for j in range(Y.shape[1]):
            Y[i, j] = (X[i:i + h, j:j + w] * K).sum()
    return Y
class Conv2D(nn.Module):
    def __init__(self, kernel_size):
        super().__init__()
        # self.weight = nn.Parameter(torch.rand(kernel_size))
        # self.bias = nn.Parameter(torch.zeros(1))
        self.weight = torch.rand(kernel_size,requires_grad=True)
        self.bias = torch.zeros(1,requires_grad=True)
    def forward(self, x):
        return corr2d(x, self.weight) + self.bias
# 构造一个二维卷积层，它具有1个输出通道和形状为（1，2）的卷积核
conv2d = nn.Conv2d(1,1, kernel_size=(1, 2), bias=False)

# 这个二维卷积层使用四维输入和输出格式（批量大小、通道、高度、宽度），
# 其中批量大小和通道数都为1
X = torch.ones((6, 8))
X[:, 2:6] = 0
K = torch.tensor([[1.0, -1.0]])
Y = corr2d(X, K)
X = X.reshape((1, 1, 6, 8))
Y = Y.reshape((1, 1, 6, 7))
lr = 3e-2  # 学习率

for i in range(10):
    Y_hat = conv2d(X)
    l = (Y_hat - Y) ** 2
    conv2d.zero_grad()
    l.sum().backward()
    # 迭代卷积核
    conv2d.weight.data[:] -= lr * conv2d.weight.grad
    if (i + 1) % 2 == 0:
        print(f'epoch {i+1}, loss {l.sum():.3f}')

import torch
from torch import autograd
x1 = torch.rand(3,4)
x2 = torch.rand(3,4)
x1.requires_grad_()#等价于x1.requires_grad=True
x2.requires_grad_()#等价于x2.requires_grad=True
print(x1)
print(x2)

# 对x中的所有元素求和，得到的结果是标量
z=x1*x2
y = torch.sum(z)
print(y)

grads = autograd.grad(y, (x1,x2))
print(grads[0])
print(grads[1])