刘老师的《Pytorch深度学习实践》第九讲：多分类问题 代码

import numpy as np
y=np.array([1,0,0])
z=np.array([0.2,0.1,-0.1])
y_pred=np.exp(z)/np.exp(z).sum()
loss=(-y*np.log(y_pred)).sum()
print(loss)

可转化为下面这种有CrossEntropyLoss模块的形式： 

import torch
y=torch.LongTensor([0])#长整型 第0类
z=torch.Tensor([[1.2,0.1,-0.1]])
criterion=torch.nn.CrossEntropyLoss()#最后一层不要做激活,因为softmax已经包含在这个模块中
loss=criterion(z,y)
print(loss)

比较两种交叉熵

import torch
criterion=torch.nn.CrossEntropyLoss()
Y=torch.LongTensor([2,0,1])

Y_pred1=torch.Tensor([[0.1,0.2,0.9],[1.1,0.1,0.2],[0.2,2.1,0.1]])
Y_pred2=torch.Tensor([[0.8,0.2,0.3],[0.2,0.3,0.5],[0.2,0.2,0.5]])
l1=criterion(Y_pred1,Y)
l2=criterion(Y_pred2,Y)
print("Batch Loss1=",l1.data,"\nBatch Loss2=",l2.data)

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

batch_size=64
transform=transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.1307, ),(0.3081, ))])
#ToTensor把单通道变为通道，Normalize为归一化，（均值，）（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=True,download=True,transform=transform)
test_loader=DataLoader(test_dataset,shuffle=False,batch_size=batch_size)

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)  # 最后要输出十个

    def forward(self,x):
        x = x.view(-1, 784)  # view改变张量形状，从三维降到二维（矩阵）；-1会自动算出数值，总数/784列
        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)
model=Net()

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

def train(epoch):
    running_loss=0.0
    for batch_idx,data in enumerate(train_loader,0):
        inputs,target = data #x为inputs，y存到target
        optimizer.zero_grad()

        outputs=model(inputs)
        loss=criterion(outputs,target)
        loss.backward()
        optimizer.step()

        running_loss+=loss.item()#拿出值
        if batch_idx % 300==200:
            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():#不用计算梯度
        for data in test_loader:
            images,labels=data
            outputs=model(images)
            _,predicted=torch.max(outputs.data,dim=1)#找最大值的下标
            total+=labels.size(0)
            correct+=(predicted==labels).sum().item()
    print('Accuracy on test set:%d %%' % (100*correct/total))

if __name__=='__main__':
    for epoch in range(10):
        train(epoch)
        test()

注意缩进 forward没有缩进第一次运行时导致NotImplementedError: Module [Net] is missing the required "forward" function