PyTorch入门五 || 多分类问题

PyTorch入门五 || 多分类问题

网络结构：前面的是线性层+sigmoid激活层，最后一层是Softmax层

Softmax的公式为如下：

Softmax的损失函数

-YlogY_pred

code

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) 

torch自带交叉熵损失API，在最后一层线性层后就不要做激活。

code

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]])

loss1 = criterion(y_pred1,Y)
loss2 = criterion(y_pred2,Y)
print('loss1=',loss1,'nloss2=',loss2)

图像数据如何转化为向量

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-z1EHCsAs-1644032532692)(https://gitee.com/chenhao_ANTHONY/mapdepot1/raw/master/img/202202051006838.png)]

该图像的每一个像素点是0-255的一个数值，像素越暗，数值越小，将这些数值/255，归一化到[0,1]区间，0表示黑，1表示白，得到一个28*28的矩阵

交叉熵包含：

​ Softmax：即 数值/(数值和)

​ log：对得到的分数占比x计算 e^x

​ -YlogY_pred：带入公式计算，求和得到loss

code:

import numpy as np
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(),  #将图像转为tensor向量，且取值为0-1
    transforms.Normalize((0.1307,),(0.3081,))   #第一个是均值，第二个是标准差，需要提前算出，这两个参数都是mnist的
])

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(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表示代码会自动运算，当输入N张图片时，系统会将像素/784得到N
        x = F.relu(self.linear1(x))
        x = F.relu(self.linear2(x))
        x = F.relu(self.linear3(x))
        x = F.relu(self.linear4(x))
        x = self.linear5(x) #最后一层要接入softmax 所以不做激活
        return x

model = Net()

#交叉熵包含 softmax 再求对数
criterion = torch.nn.CrossEntropyLoss()
#momentum表示
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

        optimizer.zero_grad()
        outputs = model(inputs)
        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():   #接下来的代码块中不会计算梯度
        for data in test_loader:
            images,labels = data
            outputs = model(images)
            #dim=0 表示列的下标和最大值，dim=1 表示行的下标和最大值
            _,predicted = torch.max(outputs.data,dim=1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
            print('labels:',labels,'noutputs:',outputs,'n_:',_,'npredicted:',predicted)
    print('Accuracy on test set:%d %%'%(100*correct/total))

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