1、在利用以swin transformer为主干特征提取网络的faster rcnn的目标检测模型上进行滑坡检测出现以下情况:
请问因为在训练时精度达到了90%几,但是在验证集上就最高才70%几,这种情况应该是过拟合了,想问一下有什么办法解决吗?
2、如果要利用正则化方法那我应该在代码哪里进行修改呢?
备注:在resnet50为特征提取主干网络上也出现了以上现象
1、在利用以swin transformer为主干特征提取网络的faster rcnn的目标检测模型上进行滑坡检测出现以下情况:
python
import torch.nn as nn
import torch.optim as optim
# 定义网络
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.fc1 = nn.Linear(10, 5)
self.fc2 = nn.Linear(5, 1)
self.dropout = nn.Dropout(p=0.2) # 添加 Dropout
def forward(self, x):
x = self.fc1(x)
x = nn.functional.relu(x)
x = self.dropout(x) # 在这里使用 Dropout
x = self.fc2(x)
return x
net = Net()
# 定义损失函数和优化器
criterion = nn.MSELoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9, weight_decay=0.01) # 在这里设置 weight decay
# 训练网络
for epoch in range(10):
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
inputs, labels = data
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
if i % 2000 == 1999:
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / 2000))
running_loss = 0.0