In [4]:
Copied!
import torch
from torch import nn
def corr2d(X, K):
h, w = K.shape
Y = torch.zeros(X.shape[0] - h + 1, X.shape[1] - w + 1, device=X.device, dtype=X.dtype)
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.rand(1))
def forward(self, x):
return corr2d(x, self.weight) + self.bias
import torch
from torch import nn
def corr2d(X, K):
h, w = K.shape
Y = torch.zeros(X.shape[0] - h + 1, X.shape[1] - w + 1, device=X.device, dtype=X.dtype)
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.rand(1))
def forward(self, x):
return corr2d(x, self.weight) + self.bias
In [5]:
Copied!
# 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
# 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
Out[5]:
torch.Size([8, 8])
In [6]:
Copied!
# 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
# 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
Out[6]:
torch.Size([8, 8])
步幅¶
In [7]:
Copied!
conv2d = nn.Conv2d(1, 1, kernel_size=(3, 5), padding=(0, 1), stride=(3, 4))
comp_conv2d(conv2d, X).shape
conv2d = nn.Conv2d(1, 1, kernel_size=(3, 5), padding=(0, 1), stride=(3, 4))
comp_conv2d(conv2d, X).shape
Out[7]:
torch.Size([2, 2])