神经网络学习之优化器

1.官方文档：

for input, target in dataset:# 梯度清零    optimizer.zero_grad()    output = model(input)    loss = loss_fn(output, target)    loss.backward()    optimizer.step()

代码实战：

import torchimport torchvisionfrom torch import nnfrom torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linearfrom torch.utils.data import DataLoaderdataset = torchvision.datasets.CIFAR10("data", train=False, download=True,    transform=torchvision.transforms.ToTensor())# 将数据集用DataLoader加载dataloader = DataLoader(dataset, batch_size=1)# 创建相应网络class Peipei(nn.Module):    def __init__(self) -> None: super(Peipei, self).__init__() self.model1 = Sequential(     Conv2d(3, 32, 5, padding=2, stride=1),     MaxPool2d(2),     Conv2d(32, 32, 5, padding=2),     MaxPool2d(2),     Conv2d(32, 64, 5, padding=2),     MaxPool2d(2),     Flatten(),     Linear(1024, 64),     Linear(64, 10) )    def forward(self, x): x = self.model1(x) return x# 搭建相应网络peipei = Peipei()# 定义损失函数loss = nn.CrossEntropyLoss()# 选择优化器optim = torch.optim.SGD(peipei.parameters(), lr=0.01)for epoch in range(20):    running_loss = 0.00    for data in dataloader: imgs, targets = data outputs = peipei(imgs) result_loss = loss(outputs, targets) # 优化器梯度清零 optim.zero_grad() # 反向传播，计算每个节点的梯度/参数，以便于后续选择合适的优化器 result_loss.backward() # 进行优化 optim.step() running_loss = running_loss + result_loss    print(running_loss)

结果：（可以看到loss在减小）