看李沐小视频学的,觉得很有意思,记录一下,都是抄李沐老师的书的!!
目录
1、定义互相关运算
import torch
from torch import nn
from d2l import torch as d2l
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
2、定义的一个类,初始化权重和前向传播
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))
def forward(self, x):
return corr2d(x, self.weight) + self.bias
3、定义一些输入啥的,还有预期想要的结果(Y)
X = torch.ones((6, 8))
X[:, 2:6] = 0
K = torch.tensor([[1.0, -1.0]])
Y = corr2d(X, K) #这里就是一个简单的垂直边缘检测
4、手写梯度下降!
# 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 = 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}')
5、最后输出结果
conv2d.weight.data.reshape((1, 2))
#output
tensor([[ 1.0010, -0.9739]]) #可以看出与上面的K很接近了!!
可以看出效果不错!!