深度学习——07搭建相对完整的自定义神经网络

添加损失函数和优化器，形成相对完整的网络

损失函数

loss = nn.CrossEntropyLoss() #交叉熵损失函数

优化器

optim = torch.optim.SGD(tudui.parameters(),lr=0.01) #梯度下降

代码：

import torchvision
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.data import DataLoader
import torch.nn as nn
import torch

dataset_transform = torchvision.transforms.Compose([
    torchvision.transforms.ToTensor()
])
test_data = torchvision.datasets.CIFAR10(root="./test10_dataset", train=False, transform=dataset_transform)
test_loader = DataLoader(dataset=test_data, batch_size=128)

class MyNet(nn.Module):
    def __init__(self):
        super(MyNet, self).__init__()
        self.model1 = Sequential(
            Conv2d(in_channels=3, out_channels=32, kernel_size=5, padding=2),
            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

# 交叉熵损失函数
loss = nn.CrossEntropyLoss()
MyNet = MyNet()
# 优化器
optim = torch.optim.SGD(MyNet.parameters(),lr=0.01)
for epoch in range(20):
    running_loss = 0.0
    for data in test_loader:
        imgs, target = data
        output = MyNet(imgs)
        result_loss = loss(output,target)
        # 把每个可以调节梯度的梯度调为0
        optim.zero_grad()
        result_loss.backward()
        # 调优
        optim.step()
        running_loss = running_loss + result_loss
    print(running_loss)

训练20次，打印每次的损失函数