Pytorch搭建CNN网络读取40个42×42的矩阵,和40和0或1的标签
时间: 2023-12-06 13:44:39 浏览: 23
以下是一个基本的CNN网络,可以用Pytorch搭建,读取42x42的矩阵,并且进行二分类(0或1):
```python
import torch
import torch.nn as nn
class CNN(nn.Module):
def __init__(self):
super(CNN, self).__init__()
self.conv1 = nn.Conv2d(in_channels=1, out_channels=16, kernel_size=3, stride=1, padding=1)
self.pool = nn.MaxPool2d(kernel_size=2, stride=2)
self.conv2 = nn.Conv2d(in_channels=16, out_channels=32, kernel_size=3, stride=1, padding=1)
self.fc1 = nn.Linear(32 * 11 * 11, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 2)
self.relu = nn.ReLU()
def forward(self, x):
x = self.conv1(x)
x = self.relu(x)
x = self.pool(x)
x = self.conv2(x)
x = self.relu(x)
x = self.pool(x)
x = x.view(-1, 32 * 11 * 11)
x = self.fc1(x)
x = self.relu(x)
x = self.fc2(x)
x = self.relu(x)
x = self.fc3(x)
return x
model = CNN()
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
# 假设数据已经载入到train_data和train_labels中
for epoch in range(100):
running_loss = 0.0
for i in range(len(train_data)):
inputs = torch.tensor(train_data[i], dtype=torch.float).unsqueeze(0).unsqueeze(0)
labels = torch.tensor([train_labels[i]], dtype=torch.long)
optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
print('[%d] loss: %.3f' % (epoch + 1, running_loss / len(train_data)))
```
注意,这里使用了`nn.CrossEntropyLoss()`作为损失函数,因此标签应该是从0开始的整数。如果你的标签是0和1,可以将标签转换为整数。