[人工智能]【PyTorch深度学习】 第八讲：多分类

1.概念

softMax：概率分布，将每个项的值/累加的值=每个结果出现的概率值
NLLLoss：就是把输出与Label对应的那个值拿出来，再去掉负号，再求均值
CrossEntropyLoss：就是把Softmax–Log–NLLLoss合并成一步

2.代码实现

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

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

train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)#trans转化
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)

test_dataset = datasets.MNIST(root='../dataset/mnist/', 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.l1 = torch.nn.Linear(784, 512)
        self.l2 = torch.nn.Linear(512, 256)
        self.l3 = torch.nn.Linear(256, 128)
        self.l4 = torch.nn.Linear(128, 64)
        self.l5 = torch.nn.Linear(64, 10)

    def forward(self, x):
        x = x.view(-1, 784)  # 将（N,1,28,28）--->二维矩阵；-1自动求N   N*784
        x = F.relu(self.l1(x))
        x = F.relu(self.l2(x))
        x = F.relu(self.l3(x))
        x = F.relu(self.l4(x))
        return self.l5(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() # 交叉熵损失
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# momentum冲量


# training cycle forward, backward, update


def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        # 获得一个批次的数据和标签
        inputs, target = data
        optimizer.zero_grad()
        # 获得模型预测结果(64, 10)
        outputs = model(inputs)
        # 交叉熵代价函数outputs(64,10),target（64）
        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_grad():#不需要计算梯度
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1) #沿着第一个维度，寻找最大值下标，得出下标和值
            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__':
    for epoch in range(10):
        train(epoch)
        test()

3.结果展示

[1,   300] loss: 2.196
[1,   600] loss: 0.929
[1,   900] loss: 0.412
accuracy on test set: 88 % 
[2,   300] loss: 0.312
[2,   600] loss: 0.271
[2,   900] loss: 0.232
accuracy on test set: 93 % 
[3,   300] loss: 0.189
[3,   600] loss: 0.181
[3,   900] loss: 0.162
accuracy on test set: 95 % 
[4,   300] loss: 0.136
[4,   600] loss: 0.128
[4,   900] loss: 0.122
accuracy on test set: 96 % 
[5,   300] loss: 0.098
[5,   600] loss: 0.104
[5,   900] loss: 0.093
accuracy on test set: 96 % 
[6,   300] loss: 0.080
[6,   600] loss: 0.077
[6,   900] loss: 0.077
accuracy on test set: 96 % 
[7,   300] loss: 0.061
[7,   600] loss: 0.064
[7,   900] loss: 0.062
accuracy on test set: 97 % 
[8,   300] loss: 0.050
[8,   600] loss: 0.055
[8,   900] loss: 0.051
accuracy on test set: 97 % 
[9,   300] loss: 0.039
[9,   600] loss: 0.041
[9,   900] loss: 0.047
accuracy on test set: 97 % 
[10,   300] loss: 0.036
[10,   600] loss: 0.033
[10,   900] loss: 0.034
accuracy on test set: 97 %