《pytorch深度学习实战》第10讲作业

老师让我们写一个三层卷积和三层的池化

就可以用老师上课讲的让pytorch帮我们计算就行

代码如下：

class Net(torch.nn.Module):
    def __init__(self):
        super(Net,self).__init__()
        self.conv1 = torch.nn.Conv2d(1,10,kernel_size = 3)
        self.conv2 = torch.nn.Conv2d(10,20,kernel_size = 5)
        self.conv3 = torch.nn.Conv2d(20,30,kernel_size = 3)
        self.pooling1 = torch.nn.MaxPool2d(kernel_size = 5,stride = 2)
        self.pooling2 = torch.nn.MaxPool2d(kernel_size = 3,stride = 1)
        self.pooling3 = torch.nn.MaxPool2d(kernel_size = 3,stride = 2)
        self.fc = torch.nn.Linear(120,10)
    
    def forward(self,x):
        batch_size = x.size(0)
        x = F.relu(self.pooling2(self.conv1(x)))
        #print(x.size())
        x = F.relu(self.pooling1(self.conv2(x)))
        #print(x.size())
        x = F.relu(self.pooling3(self.conv3(x)))
        #print(x.size())
        x = x.view(batch_size,-1)
        x = self.fc(x)
        #print(x.size())
        return x
    

第一次先把注释内的代码取消注释，并把 x = self.fc(x)注释掉，在最后输出的结果内讲self.fc第一个参数填上去（如最后一个xsize为[64,120]，就填120，因为第一个数据值是batch_size）

完整代码如下：这个是有GPU的算法，没有GPU的话把含有device的几行注释掉就行

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

batch_size = 64
#数据本身是一个28*28的像素矩阵
#做一个灰度归一化，假装这些都是由一个正态分布生成的
#正态分布的均值为0.1307，均值为0.3081
#这个数据是现成的，其他数据可以用相应的矩估计量替代
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307,),(0.3081,))
])
train_dataset = datasets.MNIST(root = "D:\python_study\PyTorch深度学习实践\minst",
                              train = True,
                              download = True,
                              transform = transform)
train_loader = DataLoader(train_dataset,
                         shuffle = True,
                         batch_size = batch_size)

test_dataset = datasets.MNIST(root = "D:\python_study\PyTorch深度学习实践\minst",
                              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 = 3)
        self.conv2 = torch.nn.Conv2d(10,20,kernel_size = 5)
        self.conv3 = torch.nn.Conv2d(20,30,kernel_size = 3)
        self.pooling1 = torch.nn.MaxPool2d(kernel_size = 5,stride = 2)
        self.pooling2 = torch.nn.MaxPool2d(kernel_size = 3,stride = 1)
        self.pooling3 = torch.nn.MaxPool2d(kernel_size = 3,stride = 2)
        self.fc = torch.nn.Linear(120,10)
    
    def forward(self,x):
        batch_size = x.size(0)
        x = F.relu(self.pooling2(self.conv1(x)))
        #print(x.size())
        x = F.relu(self.pooling1(self.conv2(x)))
        #print(x.size())
        x = F.relu(self.pooling3(self.conv3(x)))
        #print(x.size())
        x = x.view(batch_size,-1)
        x = self.fc(x)
        #print(x.size())
        return x
    
model = Net()
device = torch.device("cuda:0"if torch.cuda.is_available() else "cpu")
model.to(device)

criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(),lr = 0.1,momentum = 0.5)

def train(enpoch):
    running_loss = 0.0
    for batch_idx,data in enumerate(train_loader,0):
        inputs,target = data
        inputs,target = inputs.to(device),target.to(device)
        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(epoch):
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images,labels = data
            images,labels = images.to(device),labels.to(device)
            outputs = model(images)
            _,predicted = torch.max(outputs.data,dim =1)
            total+= labels.size(0)
            correct+=(predicted == labels).sum().item()
    print("第{}轮训练后正确率为：".format(epoch+1),correct/total)
    
if __name__ == '__main__':
    for epoch in range(30):
        train(epoch)
        if epoch % 10 == 9:
            test(epoch)