VGG16远程服务器训练CIFAR10_vgg16要用服务器跑吗

由于方向原因一直没有仔细研究过神经网络，终于抽出两天肝出来了。
1、pychrm连接远程服务器
2、手写程序
3、配置GPU训练
4、运行状态图

import torch.cuda
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

device = torch.device("cuda:1")
train_data = torchvision.datasets.CIFAR10(root="./dataset", train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root="./dataset", train=False, transform=torchvision.transforms.ToTensor(),
                                         download=True)
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集长度为: {}".format(train_data_size))
print("测试数据集长度为: {}".format(test_data_size))
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)


class module(nn.Module):
    def __init__(self):
        super().__init__()
        self.model = nn.Sequential(
            nn.Conv2d(3, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(64 * 4 * 4, 64),
            nn.Linear(64, 10))

    def forward(self, x):
        x = self.model(x)
        return x


daqiu = module()
daqiu = daqiu.to(device)
loss_fn = nn.CrossEntropyLoss()
learning_rate = 0.01
optimizer = torch.optim.SGD(daqiu.parameters(), lr=learning_rate)
total_train_step = 0
total_test_step = 0
epoch = 10
writer = SummaryWriter("logs_train_GPU04")
for i in range(epoch):
    print("-------第{}轮训练开始-------".format(i + 1))
    daqiu.train()
    for data in train_dataloader:
        imgs, targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)
        outputs = daqiu(imgs)
        loss = loss_fn(outputs, targets)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        total_train_step = total_train_step + 1
        if total_train_step % 100 == 0:
            print("训练次数: {}, Loss: {}".format(total_train_step, loss.item()))
            writer.add_scalar("train_loss", loss.item(), total_train_step)
    daqiu.eval()
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            imgs = imgs.to(device)
            targets = targets.to(device)
            outputs = daqiu(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss = total_test_loss + loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            total_accuracy = total_accuracy + accuracy
    print("整体测试集的Loss: {}".format(total_test_loss))
    print("整体测试集的正确率: {}".format(total_accuracy / test_data_size))
    writer.add_scalar("test_loss", total_test_loss, total_test_step)
    writer.add_scalar("test_accuracy", total_accuracy / test_data_size, total_test_step)
    total_test_step = total_test_step + 1
writer.close()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82