卷积神经网络10（卷积基础知识补充）+实操代码，手写体识别，准确率高达98+%

对于batch 1 28 28 的图像
用10个5 * 5核进行卷积，得到batch 10 （28 - 4） * （28 - 4) 即》（batch 10 24 * 24）
经过一个2 * 2 最大池化，得到（batch 10 12 * 12）

然后又经过20个5 * 5卷积核 输出（batch 20 8 * 8）
经过一个2 * 2 最大池化，得到（batch 20 4 * 4）
最后将其展开,输送到全连接层 20 * 4 * 4 = 320

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
import matplotlib.pyplot as plt

batch_size = 64
transform = transforms.Compose([
    transforms.ToTensor(), #转成张量
    transforms.Normalize((0.1307,),(0.3081,)) # 神经网络使用(0,1)分布
])

train_dataset = datasets.MNIST('MNIST_data',
                               train=True,
                               download=True,
                               transform=transform)

train_loader = DataLoader(train_dataset,
                                shuffle = True,
                                batch_size = batch_size)

test_dataset = datasets.MNIST('MNIST_data',
                               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.conv1 = torch.nn.Conv2d(1,10,kernel_size=5)
        self.conv2 = torch.nn.Conv2d(10,20,kernel_size=5)
        self.pooling = torch.nn.MaxPool2d(2)
        self.fc = torch.nn.Linear(320,10)

    def forward(self,x):
        batch_size = x.size(0)
        x = F.relu(self.pooling(self.conv1(x)))
        x = F.relu(self.pooling(self.conv2(x)))
        x = x.view(batch_size,-1) # flatten
        x = self.fc(x)
        return x

model = Net()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")  # 可以选择已经配置好的GPU

criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(),lr = 0.01,momentum=0.5)  # 带冲量的momentum
model.to(device)


def train(epoch):
    running_loss = 0.0
    loss_1 = []
    epoch_l = []
    for batch_idx, data in enumerate(train_loader,0):
        inputs,target = data

        input,target = inputs.to(device),target.to(device)  #也要迁移到显卡上


        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs,target)
        loss.backward()
        optimizer.step()
        # epoch_l.append(batch_idx)
        # loss_1.append(loss)

        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
        # plt.plot(epoch_l, loss_1, c='r')
        # plt.show()


def test():
    correct = 0
    total = 0
    epoch_l = []
    loss_2 = []
    with torch.no_grad():  # 这里不会再做梯度计算
        for data in test_loader:
            images,labels = data
            outputs = model(images)
            _,predicted = torch.max(outputs.data,dim = 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
            # epoch_l.append(epoch)
            # correct1 = 100*correct/total
            # loss_2.append(correct1)
    a = 100 * correct / total
    # loss_2.append(a)
    print('Accuracy on test set:%d %%[%d%d]' % (100 * correct / total,correct,total))
    # return epoch_l,loss_2
    return a


if __name__ == '__main__':
    a1= []
    b1 = []
    for epoch in range(50):
        train(epoch)
        b = test()
        a1.append(epoch)
        b1.append(b)

    print(a1)
    print(b)
    plt.plot(a1, b1, c='r')
    plt.show()