《PyTorch深度学习实践》自学记录 第九讲 多分类问题

B站 刘二大人 ，传送门PyTorch深度学习实践——多分类问题

参考错错莫课代表的PyTorch *深度学习实践 第9讲*

笔记：

源代码如下：

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim

# prepare dataset
batch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])  # 归一化,均值和方差

train_dataset = datasets.MNIST(root='../mnist_dataset/mnist_dataset/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='../mnist_dataset/mnist_dataset/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)

# design model using class
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.linear1 = torch.nn.Linear(784, 512)
        self.linear2 = torch.nn.Linear(512, 256)
        self.linear3 = torch.nn.Linear(256, 128)
        self.linear4 = torch.nn.Linear(128, 64)
        self.linear5 = torch.nn.Linear(64, 10)


    def forward(self, x):
        x = x.view(-1, 784)  # -1其实就是自动获取mini_batch
        x = F.relu(self.linear1(x))
        x = F.relu(self.linear2(x))
        x = F.relu(self.linear3(x))
        x = F.relu(self.linear4(x))
        return self.linear5(x)  # 最后一层不做激活，不进行非线性变换

model = Net()

# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.1, momentum=0.5)

# training cycle forward, backward, update

def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data  # 获得此批次的数据和标签
        optimizer.zero_grad()
        outputs = model(inputs)  # 获得模型预测结果
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if batch_idx % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))
            running_loss = 0.0

def test():
    correct = 0
    total = 0
    with torch.no_gard():
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)  # dim = 1 列是第0个维度，行是第1个维度
            total += labels.size(0)
            correct += (predicted == labels).sum().item()  # 张量之间的比较运算
    print('accuracy on test set: %d %% ' % (100 * correct / total))

if __name__=='__main__':  # if这条语句在windows系统下一定要加，否则会报错，视频里面有讲解
    for epoch in range(10):
        train(epoch)
        test()

部分输出结果：

[1,   300] loss: 2.209
[1,   600] loss: 1.067
[1,   900] loss: 0.456
accuracy on test set: 88 %
[2,   300] loss: 0.311
[2,   600] loss: 0.269
[2,   900] loss: 0.235
accuracy on test set: 93 %
[3,   300] loss: 0.185
[3,   600] loss: 0.183
[3,   900] loss: 0.162
accuracy on test set: 95 %
[4,   300] loss: 0.135
[4,   600] loss: 0.129
[4,   900] loss: 0.125
accuracy on test set: 95 %
[5,   300] loss: 0.105
[5,   600] loss: 0.096
[5,   900] loss: 0.102
accuracy on test set: 97 %
[6,   300] loss: 0.088
[6,   600] loss: 0.075
[6,   900] loss: 0.078
accuracy on test set: 97 %
[7,   300] loss: 0.065
[7,   600] loss: 0.066
[7,   900] loss: 0.067
accuracy on test set: 97 %
[8,   300] loss: 0.051
[8,   600] loss: 0.056
[8,   900] loss: 0.055
accuracy on test set: 97 %
[9,   300] loss: 0.043
[9,   600] loss: 0.045
[9,   900] loss: 0.040
accuracy on test set: 97 %
[10,   300] loss: 0.032
[10,   600] loss: 0.035
[10,   900] loss: 0.037
accuracy on test set: 97 %