import torch
from torch import nn
from d2l import torch as d2l

# 互相关运算
def corr2d(X, K):
    """计算二维互相关运算"""
    h, w = K.shape  # 行数和列数
    Y = torch.zeros((X.shape[0] - h + 1, X.shape[1] - w + 1))  # 输出的矩阵
    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()  # 与核矩阵按元素做哈达玛积，再求和
    return Y

# 实现二维卷积层
class Conv2D(nn.Module):
    def __init__(self, kernel_size):
        super().__init__()
        self.weight = nn.Parameter(torch.rand(kernel_size)) # 卷积核和bias都是可学的
        self.bias = nn.Parameter(torch.zeros(1))

    def forward(self, x):
        return corr2d(x, self.weight) + self.bias

# 图像中目标的边缘检测
X = torch.ones((6, 8))
X[:, 2:6] = 0
print(X)

K = torch.tensor([[1.0, -1.0]])
Y = corr2d(X, K)
print(Y)

# 这个卷积核K只可以检测垂直边缘
print(corr2d(X.t(), K))

# 学习由X生成Y的卷积核
conv2d = nn.Conv2d(1, 1, kernel_size=(1, 2), bias=False)

X = X.reshape((1, 1, 6, 8))
Y = Y.reshape((1, 1, 6, 7))

for i in range(50):
    Y_hat = conv2d(X)
    l = (Y_hat - Y)**2
    conv2d.zero_grad()
    l.sum().backward()
    conv2d.weight.data[:] -= 3e-2 * conv2d.weight.grad
    if(i + 1) % 2 == 0:
        print(f'batch {i + 1}, loss {l.sum():.3f}')

print(conv2d.weight.data.reshape((1, 2)))