MNIST手写数字识别

import torch
import numpy as np
from matplotlib import pyplot as plt
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision import datasets
import torch.nn.functional as F
import torch.nn as nn
import torch.optim as optim

"""
卷积运算 使用mnist数据集，和10-4，11类似的，只是这里：1.输出训练轮的acc 2.模型上使用torch.nn.Sequential
添加载入测试集数据
"""
# Super parameter ------------------------------------------------------------------------------------
batch_size = 64
learning_rate = 0.01
momentum = 0.5
EPOCH = 10
# Prepare dataset ------------------------------------------------------------------------------------
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])
# softmax归一化指数函数(https://blog.csdn.net/lz_peter/article/details/84574716),其中0.1307是mean均值和0.3081是std标准差

train_dataset = datasets.MNIST(root='./data/', train=True, download=False, transform=transform) 
# download=False加载本地数据集，否则自动下载；train=True训练集，=False测试集
#从本地导入，transform的方式与训练集数据一致
test_dataset =  datasets.MNIST(root='./data/', train=False, download=True, transform=transform) 

train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True) #shuffle=True 表示数据集打乱
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)

fig = plt.figure()
for i in range(12):
    plt.subplot(3, 4, i+1)
    plt.tight_layout()
    plt.imshow(train_dataset.train_data[i], cmap='gray', interpolation='none')
    plt.title("Labels: {}".format(train_dataset.train_labels[i]))
    plt.xticks([])
    plt.yticks([])
plt.show()

class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Sequential(
            torch.nn.Conv2d(1, 10, kernel_size=5),
            torch.nn.ReLU(),
            torch.nn.MaxPool2d(kernel_size=2),
        )
        # 第二层卷积核维度是[10, 20, 5 ,5], 输入通道是10, 输出通道是20, 卷积核大小是 5*5, (默认padding=0, stride = 1)
        # 第二层的激活函数是Relu
        # 第二层池化层: 采用的是MaxPooling, 大小是2*2.
        
        self.conv2 = torch.nn.Sequential(
            torch.nn.Conv2d(10, 20, kernel_size=5),
            torch.nn.ReLU(),
            torch.nn.MaxPool2d(kernel_size=2),
        )
            
        self.fc = torch.nn.Sequential(
            torch.nn.Linear(320, 50),
            torch.nn.Linear(50, 10),
        )

    def forward(self, x):
        batch_size = x.size(0)
        x = self.conv1(x)  # 一层卷积层,一层池化层,一层激活层(图是先卷积后激活再池化，差别不大)
        x = self.conv2(x)  # 再来一次
        x = x.view(batch_size, -1)  # flatten 变成全连接网络需要的输入 (batch, 20,4,4) ==> (batch,320), -1 此处自动算出的是320
        x = self.fc(x)
        return x  # 最后输出的是维度为10的，也就是（对应数学符号的0~9）

# 实例化模型：
model = Net()
# 损失函数和优化器损失函数　　使用交叉熵损失参数优化使用随机梯度下降
# Construct loss and optimizer ------------------------------------------------------------------------------
criterion = torch.nn.CrossEntropyLoss()  # 交叉熵损失
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, momentum=momentum)  # lr学习率，momentum冲量

def train(epoch):
    running_loss = 0.0  # 这整个epoch的loss清零
    running_total = 0
    running_correct = 0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data
        optimizer.zero_grad()

        # forward + backward + update
        outputs = model(inputs)
        loss = criterion(outputs, target)

        loss.backward()
        optimizer.step()

        # 把运行中的loss累加起来，为了下面300次一除
        running_loss += loss.item()
        # 把运行中的准确率acc算出来
        _, predicted = torch.max(outputs.data, dim=1)
        running_total += inputs.shape[0]
        running_correct += (predicted == target).sum().item()

        if batch_idx % 300 == 299:  # 不想要每一次都出loss，浪费时间，选择每300次出一个平均损失,和准确率
            print('[%d, %5d]: loss: %.3f , acc: %.2f %%'
                  % (epoch + 1, batch_idx + 1, running_loss / 300, 100 * running_correct / running_total))
            running_loss = 0.0  # 这小批300的loss清零
            running_total = 0
            running_correct = 0  # 这小批300的acc清零
            torch.save(model.state_dict(), './model.pth') #保存模型参数
            torch.save(optimizer.state_dict(), './optimizer.pth') #保存优化器参数

def test():
    model.eval()
    correct = 0
    total = 0
    with torch.no_grad():  # 测试集不用算梯度
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)  # dim = 1 列是第0个维度，行是第1个维度，沿着行(第1个维度)去找1.最大值和2.最大值的下标
            total += labels.size(0)  # 张量之间的比较运算，表示预测标签的所有次数
            correct += (predicted == labels).sum().item() #标签预测准确的次数
    # acc表示标签预测的准确率，即预测准确次数除以预测标签的所有次数，acc的计算代码公式
    
    acc = correct/total
    print('[%d / %d]: Accuracy on test set: %.1f %% ' % (epoch+1, EPOCH, 100 * acc))  # 求测试的准确率，正确数/总数
    return acc

if __name__ == '__main__':
    acc_list_test = [] #创建保存测试数据的列表
    for epoch in range(EPOCH):
        train(epoch)
        # if epoch % 10 == 9:  #每训练10轮 测试1次
        acc_test = test()
        #接下来需要把每次的测试结果即acc_test，添加到列表acc_list_test中
        acc_list_test.append(acc_test)
        
    plt.plot(acc_list_test)
    plt.xlabel('TEST-EPOCH')
    plt.ylabel('Accuracy On TestSet')
    plt.show()