torch之二维卷积层

酥酥 发布于 2022-04-16 86 次阅读

二维卷积层

二维互相关运算

				
					import torch 
from torch import nn

print(torch.__version__)
				
			
1.11.0+cu113
				
					def corr2d(X, K):  # 本函数已保存在d2lzh_pytorch包中方便以后使用
    h, w = K.shape
    X, K = X.float(), K.float()
    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
				
			
				
					X = torch.tensor([[0, 1, 2], [3, 4, 5], [6, 7, 8]])
K = torch.tensor([[0, 1], [2, 3]])
corr2d(X, K)
				
			
				
					class Conv2D(nn.Module):
    def __init__(self, kernel_size):
        super(Conv2D, self).__init__()
        self.weight = nn.Parameter(torch.randn(kernel_size))
        self.bias = nn.Parameter(torch.randn(1))

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

图像中物体边缘检测

				
					X = torch.ones(6, 8)
X[:, 2:6] = 0
X
				
			
tensor([[1., 1., 0., 0., 0., 0., 1., 1.],
        [1., 1., 0., 0., 0., 0., 1., 1.],
        [1., 1., 0., 0., 0., 0., 1., 1.],
        [1., 1., 0., 0., 0., 0., 1., 1.],
        [1., 1., 0., 0., 0., 0., 1., 1.],
        [1., 1., 0., 0., 0., 0., 1., 1.]])
				
					K = torch.tensor([[1, -1]])
Y = corr2d(X, K)
Y
				
			
				
					# 构造一个核数组形状是(1, 2)的二维卷积层
conv2d = Conv2D(kernel_size=(1, 2))

step = 20
lr = 0.01
for i in range(step):
    Y_hat = conv2d(X)
    l = ((Y_hat - Y) ** 2).sum()
    l.backward()
    
    # 梯度下降
    conv2d.weight.data -= lr * conv2d.weight.grad
    conv2d.bias.data -= lr * conv2d.bias.grad
    
    # 梯度清0
    conv2d.weight.grad.fill_(0)
    conv2d.bias.grad.fill_(0)
    if (i + 1) % 5 == 0:
        print('Step %d, loss %.3f' % (i + 1, l.item()))
				
			
Step 5, loss 1.844
Step 10, loss 0.206
Step 15, loss 0.023
Step 20, loss 0.003
				
					print("weight: ", conv2d.weight.data)
print("bias: ", conv2d.bias.data)
				
			
weight:  tensor([[ 0.9948, -1.0092]])
bias:  tensor([0.0080])

填充

				
					# 定义一个函数来计算卷积层。它对输入和输出做相应的升维和降维
def comp_conv2d(conv2d, X):
    # (1, 1)代表批量大小和通道数（“多输入通道和多输出通道”一节将介绍）均为1
    X = X.view((1, 1) + X.shape)
    Y = conv2d(X)
    return Y.view(Y.shape[2:])  # 排除不关心的前两维：批量和通道

# 注意这里是两侧分别填充1行或列，所以在两侧一共填充2行或列
conv2d = nn.Conv2d(in_channels=1, out_channels=1, kernel_size=3, padding=1)

X = torch.rand(8, 8)
comp_conv2d(conv2d, X).shape
				
			
torch.Size([8, 8])
				
					# 使用高为5、宽为3的卷积核。在高和宽两侧的填充数分别为2和1
conv2d = nn.Conv2d(in_channels=1, out_channels=1, kernel_size=(5, 3), padding=(2, 1))
comp_conv2d(conv2d, X).shape
				
			
				
					conv2d = nn.Conv2d(1, 1, kernel_size=3, padding=1, stride=2)
comp_conv2d(conv2d, X).shape
				
			
torch.Size([4, 4])
				
					conv2d = nn.Conv2d(1, 1, kernel_size=(3, 5), padding=(0, 1), stride=(3, 4))
comp_conv2d(conv2d, X).shape
				
			
torch.Size([2, 2])