[人工智能]Pytorch--手写数字识别

实现步骤

1、加载图片（7万张）
2、建立模型（三层非线性层）
3、训练
4、测试

可视化图片、曲线的代码

###绘制曲线
def plot_curve(data):
    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()


###写数字
def plot_image(img, label, name):
    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()
### 编码工具
def one_hot(label, depth=10):
    out = torch.zeros(label.size(0), depth)
    idx = torch.LongTensor(label).view(-1, 1)
    out.scatter_(dim=1, index=idx, value=1)
    return out

1、加载数据集

batch_size = 512
#train表示下载的是训练集还是测试集
#download表示是下载
#torchvision.transforms.Normalize((0.1307,), (0.3081,))表示将数据都放在0附近
#batch_size表示一次下载几条
#shuffle表示加载的时候做一个随机的打散
train_loader = torch.utils.data.DataLoader(
    torchvision.datasets.MNIST('mnist_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('mnist_data/', train=False, download=True,
                               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))

看看我们的数据

plot_image(x,y,"image_sample")

2、创建网路

#创建网络
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()

        ##第一层xw+b
        self.fc1=nn.Linear(28*28,256)
        self.fc2=nn.Linear(256,64)
        self.fc3=nn.Linear(64,10)#十分类
    def forward(self,x):
        # x:[b,1,28,28]
        #h1=wx+b
        #relu(h1)
        x=F.relu(self.fc1(x))
        #h2=relu(h1w2+b2)
        x=F.relu(self.fc2(x))
        #h3=softmax(h2w3+b3)
        x = self.fc3(x)
        
        return x

3、模型训练

#训练
net=Net()
#优化器
optimizer=optim.SGD(net.parameters(),lr=0.01,momentum=0.9)
train_loss=[]
for epoch in range(3):#迭代三编
    for batch_idx,(x,y) in enumerate(train_loader):
        # print(x.shape,y.shape)
        #torch.Size([512, 1, 28, 28]) torch.Size([512])
        #打平数据[b,1,28,28]=>[b,feature]
        x=x.view(x.size(0),28*28)
        #=>[b,10]
        out=net(x)
        y_onehot=one_hot(y)
        #loss=mes(out,y_onehot)
        loss=F.mse_loss(out,y_onehot)##计算均方差
        #清零梯度
        optimizer.zero_grad()
        #计算梯度
        loss.backward()
        #w'=w-lr*grad
        optimizer.step()
        train_loss.append(loss.item())
        if batch_idx%10==0:
            print(epoch,batch_idx,loss.item())

绘制曲线

plot_curve(train_loss)

4、测试

#测试
total_correct=0
for x,y in test_loader:
    x=x.view(x.size(0),28*28)
    out=net(x)
    #out:[b,10]
    #返回值最大的索引
    pred=out.argmax(dim=1)
    #预测对的总个数
    correct=pred.eq(y).sum().float().item()
    total_correct+=correct

total_num=len(test_loader.dataset)

#计算准确度
acc=total_correct/total_num

print(acc)
x,y=next(iter(test_loader))
out=net(x.view(x.size(0),28*28))
pred=out.argmax(dim=1)

测试绘图

plot_image(x,pred,"test")

全局代码

#
import torch
from matplotlib import pyplot as plt
from torch import nn
from torch.nn import  functional as F
from torch import optim
import torchvision
###绘制曲线
def plot_curve(data):
    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()


###写数字
def plot_image(img, label, name):
    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()
### 编码工具
def one_hot(label, depth=10):
    out = torch.zeros(label.size(0), depth)
    idx = torch.LongTensor(label).view(-1, 1)
    out.scatter_(dim=1, index=idx, value=1)
    return out

##第一步、加载数据集
batch_size = 512
#train表示下载的是训练集还是测试集
#download表示是下载
#torchvision.transforms.Normalize((0.1307,), (0.3081,))表示将数据都放在0附近
#batch_size表示一次下载几条
#shuffle表示加载的时候做一个随机的打散
train_loader = torch.utils.data.DataLoader(
    torchvision.datasets.MNIST('mnist_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('mnist_data/', train=False, download=True,
                               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))

#创建网络
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()

        ##第一层xw+b
        self.fc1=nn.Linear(28*28,256)
        self.fc2=nn.Linear(256,64)
        self.fc3=nn.Linear(64,10)#十分类
    def forward(self,x):
        # x:[b,1,28,28]
        #h1=wx+b
        #relu(h1)
        x=F.relu(self.fc1(x))
        #h2=relu(h1w2+b2)
        x=F.relu(self.fc2(x))
        #h3=softmax(h2w3+b3)
        x = self.fc3(x)

        return x

#训练
net=Net()
#优化器
optimizer=optim.SGD(net.parameters(),lr=0.01,momentum=0.9)
train_loss=[]
for epoch in range(3):#迭代三编
    for batch_idx,(x,y) in enumerate(train_loader):
        # print(x.shape,y.shape)
        #torch.Size([512, 1, 28, 28]) torch.Size([512])
        #打平数据[b,1,28,28]=>[b,feature]
        x=x.view(x.size(0),28*28)
        #=>[b,10]
        out=net(x)
        y_onehot=one_hot(y)
        #loss=mes(out,y_onehot)
        loss=F.mse_loss(out,y_onehot)##计算均方差
        #清零梯度
        optimizer.zero_grad()
        #计算梯度
        loss.backward()
        #w'=w-lr*grad
        optimizer.step()
        train_loss.append(loss.item())
        if batch_idx%10==0:
            print(epoch,batch_idx,loss.item())
# 得到w1，b1，w2，b2，w3，b3
plot_curve(train_loss)

#测试
total_correct=0
for x,y in test_loader:
    x=x.view(x.size(0),28*28)
    out=net(x)
    #out:[b,10]
    #返回值最大的索引
    pred=out.argmax(dim=1)
    #预测对的总个数
    correct=pred.eq(y).sum().float().item()
    total_correct+=correct

total_num=len(test_loader.dataset)

#计算准确度
acc=total_correct/total_num

print(acc)
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")