一、优化器的基本框架
#class Tudui()的书写省略
loss = nn.CrossEntropyLoss()#引入损失函数
tudui = Tudui()
optim = torch.optim.SGD(tudui.parameters(),lr=0.01)#建立优化器
for epoch in range(20):
runing_loss = 0.0
for data in dataloader:
imgs,target = data
output = tudui(imgs)
result_loss=loss(output,target)
result_loss.backward()
optim.zero_grad()#上一轮的梯度清零
result_loss.backward()#反向传递误差
optim.step()#调用优化器
runing_loss = runing_loss + result_loss
print(runing_loss)
框架如下:
loss = nn.CrossEntropyLoss()#引入损失函数
tudui = Tudui()
optim = torch.optim.SGD(tudui.parameters(),lr=0.01)#建立优化器
for i in range:
optim.zero_grad()#上一轮的梯度清零
result_loss.backward()#反向传递误差
optim.step()#调用优化器
二、损失函数详讲
https://blog.csdn.net/nstarlds/article/details/104733459/