PyTorch深度学习实践 第9讲 多分类问题

B站--刘二大人《PyTorch深度学习实践》完结合集   09.多分类问题

 PPT 链接：网盘          提取码：cxe4

1.10分类如何设计神经网络

• 10分类-->10个输出，所有元素的概率≥0，且相加=1
• 网络前 些层用sigmoid函数，最后输出前需要用softmax函数，使输出结果为概率
• a

• Pytorch中有交叉熵损失函数，其中包含softmax_log函数， 因此不需要添加激活函数
• 如果使用NLLLoss，则需要最后一层先进行softmax处理，在进行log

！DO

• What are the differences?
• Reading the document:

            https://pytorch.org/docs/stable/nn.html#crossentropylosso 

            https://pytorch.org/docs/stable/nn.html#nllloss          

•  Try to know why:

CrossEntropyLoss <==> LogSoftmax + NLLLoss

代码实现

123+4（training cycle+Test）

import torch
from torchvision import transforms  #transforms对图像进行处理
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F   #用relu进行激活
import torch.optim as optim   #优化器包
 
# prepare dataset
 
batch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])    # 将图像转换成图像张量，归一化,均值0.1307和方差0.3081,
                #compose[]:把[]中的数据组合起来，串联多个图片变换的操作，具体是对图像进行各种转换操作，并用函数compose将这些转换操作组合起来；
 
train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)

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)  # -1其实就是自动获取mini_batch
        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()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
 
# 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()  #取计算值
        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():
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1) 
                           #torch.max的返回值有两个，第一个是每一行的最大值是多少，第二个是每一行最大值的下标(索引)是多少
                           # 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，之后求和
    print('accuracy on test set: %d %% ' % (100*correct/total))
 
 
if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()

参考链接：

Pytorch 深度学习实践 第9讲--刘二大人_刘二大人多分类问题_NCUTer的博客-CSDN博客