homework6——cnn基础篇

要求：
Conv2d Layer * 3
ReLU Layer * 3
MaxPooling Layer * 3
Linear Layer * 3

# Conv2d Layer * 3
# ReLU Layer * 3
# MaxPooling Layer * 3
# Linear Layer * 3


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

device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

# 加载数据
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307, ), (0.3081, ))])

tra_data = datasets.MNIST(root='./datasets/mnist', train=True, download=False, transform=transform)
test_data = datasets.MNIST(root='./datasets/mnist', train=False, download=False, transform=transform)

tra_loader = DataLoader(dataset=tra_data, batch_size=64, shuffle=True)
test_loader = DataLoader(dataset=test_data, batch_size=64, shuffle=False)


class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=7, padding=3, stride=1)
        self.pooling = torch.nn.MaxPool2d(2)
        self.conv2 = torch.nn.Conv2d(10, 10, kernel_size=5, padding=2, stride=1)
        self.conv3 = torch.nn.Conv2d(10, 20, kernel_size=5, padding=2, stride=1)
        self.relu = torch.nn.ReLU()
        self.linear1 = torch.nn.Linear(180, 256)
        self.linear2 = torch.nn.Linear(256, 128)
        self.linear3 = torch.nn.Linear(128, 10)

    def forward(self, x):
        batch_size = x.size(0)   # 求batch，方便后面flatten
        x = self.pooling(self.relu(self.conv1(x)))
        x = self.pooling(self.relu(self.conv2(x)))
        x = self.pooling(self.relu(self.conv3(x)))
        x = x.view(batch_size, -1)
        # print(x.shape)
        x = self.linear1(x)
        x = self.linear2(x)
        x = self.linear3(x)
        return x
model = Net()
model = model.to(device)   # use gpu for training
# 计算linear应该设置的参数
# x = torch.randn(1, 1, 28, 28)
# model(x)


# loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
criterion = criterion.to(device)    # use gpu for training
optimizer = torch.optim.SGD(model.parameters(), lr=1e-2, momentum=0.5)


# 训练函数
def train(epoch):
    running_loss = 0.0
    for i, data in enumerate(tra_loader):
        inputs, targets = data
        inputs, targets = inputs.to(device), targets.to(device)  # use gpu for training
        optimizer.zero_grad()

        # forward
        y_pred = model(inputs)
        l = criterion(y_pred, targets)
        # backward
        l.backward()
        # update
        optimizer.step()

        running_loss += l.item()
        # 每300 iterations 打印一次平均loss
        if i % 300 == 299:
            print("[%d %5d]\tloss: %3f" % (epoch+1, i+1, running_loss / 300))
            running_loss = 0.0

# test函数
def test():
    total = 0
    correct = 0
    with torch.no_grad():
        for data in test_loader:
            x, labels = data
            x, labels = x.to(device), labels.to(device)  # use gpu for training
            outputs = model(x)   # predict

            total += labels.size(0)    # 总的样本数量
            _, predicted = torch.max(outputs.data, dim=1)   # 取每个样本的分类最大值的下标（即样本被预测为哪个类）
            correct += (predicted == labels).sum().item()   # 被预测正确的样本数量

        print("Accuracy on Test is: %3f %% [%d %d]" % (100 * correct / total, correct, total))
        return 100 * correct / total   # 返回Accuracy，方便后面画图


if __name__ == '__main__':
    acc_list = []
    for epoch in range(10):
        train(epoch)
        accuracy = test()
        acc_list.append(accuracy)

    # 画图
    acc_list = np.array(acc_list)   # 将acc_list转为array格式
    plt.plot(range(10), acc_list)
    plt.xlabel('epoch')
    plt.ylabel('Accuracy')
    plt.show()
    plt.close()