《PyTorch深度学习实战》第十讲

Basic CNN

传送门：https://www.bilibili.com/video/BV1Y7411d7Ys?p=10

模型框架：

代码

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

#1.prepare dataset
#2.design model using class
#3.construct loss and optimizer
#4.training cycle+test

#1.准备数据集

batch_size = 64
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307, ), (0.3081, ))#均值，标准化
])
train_dataset = datasets.MNIST(root='./dataset/mnist',
                               train=True,
                               transform=transform,
                               download=True)
print(train_dataset[0])
test_dataset = datasets.MNIST(root='./dataset/mnist',
                              train=False,
                              transform=transform,
                              download=True)

train_loader = DataLoader(dataset=train_dataset,
                          batch_size=32,
                          shuffle=True)
test_loader = DataLoader(dataset=test_dataset,
                         batch_size=32,
                         shuffle=False)

# ---------------------------卷积模型---------------------------
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(kernel_size=2, stride=2)

        self.fc = torch.nn.Linear(40, 20)

    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)
        x = self.fc(x)
        return x
        
model = Net()
# 开启显卡
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

#3.构建loss和optimzer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

#4.循环
def train(epoch):
    running_loss = 0.0
    for batch_idx, (inputs, target) in enumerate(train_loader):
        inputs, target = inputs.to(device), target.to(device) #显卡加速

        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs, target)

        loss.backward()
        optimizer.step()

        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

def test():
    correct = 0
    total = 0
    with torch.no_grad():
        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()
        print('Accuracy on test set: %d %%' % (100*correct / total))
    return correct / total

if __name__ == '__main__':
    epoch_list = []
    acc_list = []

    for epoch in range(10):
        train(epoch)
        acc = test()
        epoch_list.append(epoch)
        acc_list.append(acc)
        # if epoch % 10 == 9:
        #     test()
    import os
    os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE'
    plt.plot(epoch_list, acc_list)
    plt.xlabel('epoch')
    plt.ylabel('accuracy')
    plt.show()

对于图像的处理，线性模型显然会丢失掉图像之间的关系和联系，卷积神经网络有较好的提升，但网络过于简单会使得图像学习的效果较少，改进的网络/课后习题：

https://blog.youkuaiyun.com/frighting_ing/article/details/120773888?spm=1001.2014.3001.5501