pytorch训练6 多分类模型

多分类问题y的标签为one-hot编码，即只有一个标签为1，其余都为0

对于softmax，直接传入线性模型，不需要非线性变换，softmax里会进行e的z次方映射取正，然后归一化，最大值就是y_hat，然后计算损失函数-ylog (y_hat)。 

CrossEntropyLoss <==> LogSoftmax + NLLLoss 

 

 

import numpy as np
import torch
import matplotlib.pyplot as plt
from torchvision import transforms
import torch.nn.functional as F
from torchvision import datasets #与Datasets类相比，不用实现里面的函数，直接就可以取出里面的（x，y）
from torch.utils.data import DataLoader


batch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])
#transforms.ToTensor()将数据从[0,255]范围转换到[0,1]，图像转张量，transforms.Normalize是归一化，后面参数是均值和标准差

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)

class Net(torch.nn.Module):
    def __init__(self):
        super().__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是自动获取minibatch
        x = F.relu(self.l1(x))
        x = F.relu(self.l2(x))
        x = F.relu(self.l3(x))
        x = F.relu(self.l4(x))
        x = self.l5(x) #最后一层不激活
        return x

model = Net()

criterion = torch.nn.CrossEntropyLoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(), lr=0.01,momentum=0.5)

def train(epoch):
    sum_loss = 0
    for i,data in enumerate(train_loader, 0):
        inputs,labels = data
        y_pred = model(inputs)
        loss = criterion(y_pred,labels)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        sum_loss+=loss.item()
        if(i%300==299):
            print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, sum_loss / 300))
            sum_loss = 0.0

def t():
    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)  # dim = 1 列是第0个维度，行是第1个维度
            #_是无用变量，占位的，因为第一个返回值是最大值，predicted是最大值的下标，只需要第二个变量
            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)
        t()