Press "Enter" to skip to content

神经网络做MNIST手写数字识别代码

本站内容均来自兴趣收集,如不慎侵害的您的相关权益,请留言告知,我们将尽快删除.谢谢.

1.MNIST数据集

 

MNIST数据集是由0 到9 的手写数字图像构成的。训练图像有6 万张,测试图像有1 万张每一张图片都有对应的标签数字。因此这个测试集就可以作为验证集使用。

 

MNIST的图像,每张图片是包含28 像素× 28 像素的灰度图像(1 通道),各个像素的取值在0 到255 之间。每张图片都由一个28 ×28 的矩阵表示,每张图片都由一个784 维的向量表示(28*28=784)。

 

详细介绍参考: http://yann.lecun.com/exdb/mnist/

 

2.用神经网络做MNIST手写数字识别

 

模型结构:

 

模型如图所示,输入二维张量展开成一维。再经过若干次组合的,Linear层和激活函数层,最后返回。

 

在模型使用时,后面接到交叉熵损失函数上。所以模型的最后一层不做激活。因为本身交叉熵损失函数带有激活功能。

 

3.代码实现(python+pytorch)

 

分四个步骤:

 

第一步:数据集准备和加载;第二步:设计模型;第三步:构建损失函数和优化器;第四步:模型的训练和验证

 

因pytorc中封装了很多模块。所以我们在实现时,更多的是了解各个模块的功能,以便组合使用。

 

 

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.optim as optim
import torch.nn.functional as F
import matplotlib.pyplot as plt
batch_size = 64
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307),(0.3081)) #两个参数,平均值和标准差
])
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_loder = DataLoader(test_dataset,
                        shuffle = True,
                        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) # 改变张量形状。把输入展开成若干行,784列
        x = F.leaky_relu(self.linear1(x))
        x = F.leaky_relu(self.linear2(x))
        x = F.leaky_relu(self.linear3(x))
        x = F.leaky_relu(self.linear4(x))
        return self.linear5(x) #最后一层不做激活,因为下一步输入到交叉损失函数中,交叉熵包含了激活层

model = Net()
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum= 0.5)
def train(epoch):
    total = 0
    running_loss = 0.0
    train_loss = 0.0 #记录每次epoch的损失
    accuracy = 0 #记录每次epoch的accuracy
    for batch_id, data in enumerate(train_loader,0):
        inputs, target = data
        optimizer.zero_grad()
        # forword + backward + update
        outputs = model(inputs)
        loss = criterion(outputs, target)
        _, predicted = torch.max(outputs.data, dim=1)
        accuracy += (predicted == target).sum().item()
        total += target.size(0)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
        train_loss = running_loss
        #每迭代300次,求一下这三百次迭代的平均
        if batch_id % 300 == 299:
            print('[%d, %5d] loss: %.3f' %(epoch+1, batch_id+1, running_loss / 300))
            running_loss = 0.0
    print('第 %d epoch的 Accuracy on train set: %d %%, Loss on train set: %f' % (epoch + 1, 100 * accuracy / total, train_loss))
    #返回acc和loss
    return 1.0 * accuracy / total, train_loss
def validation(epoch):
    correct = 0
    total = 0
    val_loss = 0.0
    with torch.no_grad():
        for data in test_loder:
            images, target = data
            outputs = model(images)
            loss = criterion(outputs, target)
            val_loss += loss.item()
            _, predicted = torch.max(outputs.data, dim=1)
            total += target.size(0)
            correct += (predicted == target).sum().item()
    print('第 %d epoch的 Accuracy on validation set: %d %%, Loss on validation set: %f' %(epoch+1,100*correct / total, val_loss))
    #返回acc和loss
    return 1.0 * correct / total, val_loss
#pytorch绘制loss和accuracy曲线
def draw_fig(list,name,name2,epoch):
    # 我这里迭代了200次,所以x的取值范围为(0,200),然后再将每次相对应的准确率以及损失率附在x上
    x1 = range(1, epoch+1)
    print(x1)
    y1 = list
    if name=="loss":
        plt.cla()
        plt.title('Train loss vs. epoch', fontsize=20)
        plt.plot(x1, y1, '.-')
        plt.xlabel('epoch', fontsize=20)
        plt.ylabel('Train loss', fontsize=20)
        plt.grid()
        str = "./lossAndacc/"+name2+"_loss.png"
        plt.savefig(str)
        plt.show()
    elif name =="acc":
        plt.cla()
        plt.title('Train accuracy vs. epoch', fontsize=20)
        plt.plot(x1, y1, '.-')
        plt.xlabel('epoch', fontsize=20)
        plt.ylabel('Train accuracy', fontsize=20)
        plt.grid()
        str2 = "./lossAndacc/" + name2 + "_accuracy.png"
        plt.savefig(str2)
        plt.show()
def draw_in_one(list,epoch):
    # x_axix,train_pn_dis这些都是长度相同的list()
    # 开始画图
    x_axix = [x for x in range(1, epoch+1)] #把ranage转化为list
    train_acc = list[0]
    train_loss = list[1]
    val_acc = list[2]
    val_loss = list[3]
    #sub_axix = filter(lambda x: x % 200 == 0, x_axix)
    plt.title('Result Analysis')
    plt.plot(x_axix, train_acc, color='green', label='training accuracy')
    plt.plot(x_axix, train_loss, color='red', label='training loss')
    plt.plot(x_axix, val_acc, color='skyblue', label='val accuracy')
    plt.plot(x_axix, val_loss, color='blue', label='val loss')
    plt.legend()  # 显示图例
    plt.xlabel('epoch times')
    plt.ylabel('rate')
    plt.show()
    # python 一个折线图绘制多个曲线
if __name__ == '__main__':
    train_loss = []
    train_acc = []
    val_loss = []
    val_acc = []
    epoches = 10
    list = []
    for epoch in range(epoches):
        acc1, loss1 = train(epoch)
        train_loss.append(loss1)
        train_acc.append(acc1)
        acc2, loss2 = validation(epoch)
        val_loss.append(loss2)
        val_acc.append(acc2)
    #四幅图分开绘制
    draw_fig(train_loss, "loss","train", epoches)
    draw_fig(train_acc, "acc", "train",epoches)
    draw_fig(val_loss, "loss","val", epoches)
    draw_fig(val_acc, "acc","val", epoches)
    # 四幅图合并绘制
    list.append(train_acc)
    list.append(train_loss)
    list.append(val_acc)
    list.append(val_loss)
    draw_in_one(list, epoches)

 

结果:

 

train acc

 

train loss

 

val acc

 

注:图的title代码中有误。读者自行更改

 

val loss

 

四幅图合并绘制

 

 

在计算这四个值时,代码可能有点小错误。导致画的图不很准确。读者发现后,自行更改吧

 

控制台输出内容:

 

E:\anaconda3\envs\pytorch\python.exe D:/PycharmProjects/pytorchProject/手写数字识别.py
[1,   300] loss: 2.211
[1,   600] loss: 0.881
[1,   900] loss: 0.439
第 1 epoch的 Accuracy on train set: 65 %, Loss on train set: 14.349343
第 1 epoch的 Accuracy on validation set: 89 %, Loss on validation set: 55.763730
[2,   300] loss: 0.325
[2,   600] loss: 0.284
[2,   900] loss: 0.242
第 2 epoch的 Accuracy on train set: 91 %, Loss on train set: 8.700389
第 2 epoch的 Accuracy on validation set: 93 %, Loss on validation set: 34.062688
[3,   300] loss: 0.199
[3,   600] loss: 0.180
[3,   900] loss: 0.159
第 3 epoch的 Accuracy on train set: 94 %, Loss on train set: 5.356741
第 3 epoch的 Accuracy on validation set: 94 %, Loss on validation set: 25.656663
[4,   300] loss: 0.138
[4,   600] loss: 0.131
[4,   900] loss: 0.117
第 4 epoch的 Accuracy on train set: 96 %, Loss on train set: 4.067950
第 4 epoch的 Accuracy on validation set: 96 %, Loss on validation set: 19.429859
[5,   300] loss: 0.110
[5,   600] loss: 0.093
[5,   900] loss: 0.095
第 5 epoch的 Accuracy on train set: 97 %, Loss on train set: 3.809268
第 5 epoch的 Accuracy on validation set: 96 %, Loss on validation set: 17.569023
[6,   300] loss: 0.080
[6,   600] loss: 0.082
[6,   900] loss: 0.074
第 6 epoch的 Accuracy on train set: 97 %, Loss on train set: 3.285731
第 6 epoch的 Accuracy on validation set: 97 %, Loss on validation set: 14.668039
[7,   300] loss: 0.062
[7,   600] loss: 0.068
[7,   900] loss: 0.064
第 7 epoch的 Accuracy on train set: 98 %, Loss on train set: 2.248924
第 7 epoch的 Accuracy on validation set: 97 %, Loss on validation set: 15.119584
[8,   300] loss: 0.048
[8,   600] loss: 0.055
[8,   900] loss: 0.053
第 8 epoch的 Accuracy on train set: 98 %, Loss on train set: 2.621493
第 8 epoch的 Accuracy on validation set: 97 %, Loss on validation set: 13.119277
[9,   300] loss: 0.042
[9,   600] loss: 0.041
[9,   900] loss: 0.047
第 9 epoch的 Accuracy on train set: 98 %, Loss on train set: 1.698503
第 9 epoch的 Accuracy on validation set: 97 %, Loss on validation set: 13.277307
[10,   300] loss: 0.029
[10,   600] loss: 0.037
[10,   900] loss: 0.040
第 10 epoch的 Accuracy on train set: 98 %, Loss on train set: 1.292258
第 10 epoch的 Accuracy on validation set: 97 %, Loss on validation set: 13.084560
range(1, 11)
range(1, 11)
range(1, 11)
range(1, 11)
Process finished with exit code 0

Be First to Comment

发表回复

您的电子邮箱地址不会被公开。 必填项已用*标注