pytorch深度学习神经网络实现手写字体识别

Posted 2020-11-13 yanjy-onlyone

利用平pytorch搭建简单的神经网络实现minist手写字体的识别，采用三层线性函数迭代运算，使得其具备一定的非线性转化与运算能力，其数学原理如下：

其具体实现代码如下所示：
import torch
import matplotlib.pyplot as  plt
def plot_curve(data):    #曲线输出函数构建
    fig=plt.figure()
    plt.plot(range(len(data)),data,color="blue")
    plt.legend(["value"],loc="upper right")
    plt.xlabel("step")
    plt.ylabel("value")
    plt.show()

def plot_image(img,label,name): #输出二维图像灰度图
    fig=plt.figure()
    for i in range(6):
        plt.subplot(2,3,i+1)
        plt.tight_layout()
        plt.imshow(img[i][0]*0.3081+0.1307,cmap="gray",interpolation="none")
        plt.title("{}:{}".format(name, label[i].item()))
        plt.xticks([])
        plt.yticks([])
    plt.show()
def one_hot(label,depth=10):       #根据分类结果的数目将结果转换为一定的矩阵形式[n,1],n为分类结果的数目
    out=torch.zeros(label.size(0),depth)
    idx=torch.LongTensor(label).view(-1,1)
    out.scatter_(dim=1,index=idx,value=1)
    return out

batch_size=512
import torch
from torch import nn                         #完成神经网络的构建包
from torch.nn import functional as F         #包含常用的函数包
from torch import optim                      #优化工具包
import torchvision                           #视觉工具包
import  matplotlib.pyplot as plt
from utils import plot_curve,plot_image,one_hot
#step1 load dataset   加载数据包
train_loader=torch.utils.data.DataLoader(
    torchvision.datasets.MNIST("minist_data",train=True,download=True,transform=torchvision.transforms.Compose(
        [torchvision.transforms.ToTensor(),torchvision.transforms.Normalize((0.1307,),(0.3081,))
         ])),
    batch_size=batch_size,shuffle=True)
test_loader=torch.utils.data.DataLoader(
    torchvision.datasets.MNIST("minist_data",train=True,download=False,transform=torchvision.transforms.Compose(
        [torchvision.transforms.ToTensor(),torchvision.transforms.Normalize((0.1307,),(0.3081,))
         ])),
    batch_size=batch_size,shuffle=False)
x,y=next(iter(train_loader))
print(x.shape,y.shape)
plot_image(x,y,"image")
print(x)
print(y)

#构建神经网络结构
class Net(nn.Module):
    def __init__(self):
        super(Net,self).__init__()
        #xw+b
        self.fc1=nn.Linear(28*28,256)
        self.fc2=nn.Linear(256,64)
        self.fc3=nn.Linear(64,10)
    def forward(self, x):
        #x:[b,1,28,28]
        #h1=relu(xw1+b1)
        x=F.relu(self.fc1(x))
        #h2=relu(h1w2+b2)
        x=F.relu(self.fc2(x))
        #h3=h2w3+b3
        x=(self.fc3(x))
        return x

net=Net()
#[w1,b1,w2,b2,w3,b3]
optimizer=optim.SGD(net.parameters(),lr=0.01,momentum=0.9)
train_loss=[]
for epoch in range(3):
    for batch_idx,(x,y) in enumerate(train_loader):
        #x:[b,1,28,28],y:[512]
        x=x.view(x.size(0),28*28)
        # => [b,10]
        out =net(x)
        # [b,10]
        y_onehot=one_hot(y)
        #loss=mse(out,y_onehot)
        loss= F.mse_loss(out,y_onehot)

        optimizer.zero_grad()
        loss.backward()
        #w‘=w-lr*grad
        optimizer.step()
        train_loss.append(loss.item())

        if batch_idx %10==0:
            print(epoch,batch_idx,loss.item())  #输出其预测loss损失函数的变化曲线
plot_curve(train_loss)
#get optimal [w1,b1,w2,b2,w3,b3]

total_correct=0
for x,y in test_loader:
    x=x.view(x.size(0),28*28)
    out=net(x)
    pred=out.argmax(dim=1)
    correct=pred.eq(y).sum().float().item()
    total_correct+=correct
total_num=len(test_loader.dataset)
acc=total_correct/total_num
print("test.acc:",acc)  #输出整体预测的准确度

x,y=next(iter(test_loader))
out=net(x.view(x.size(0),28*28))
pred=out.argmax(dim=1)
plot_image(x,pred,"test")
实现结果如下所示：