Pytorch实战学习(六)：基础CNN

《PyTorch深度学习实践》完结合集_哔哩哔哩_bilibili

Basic Convolution Neural Network

 

1、全连接网络

线性层串行—全连接网络

每一个输入和输出都有权重--全连接层

全连接网络在处理图像时，直接将每一行像素拼接成向量，丧失了图像的空间结构

 

2、CNN结构

CNN在处理图像时，保留了图像的空间结构信息

卷积神经网络：卷积运算（特征提取）à转换成向量à全连接网络（分类）

 

3、卷积过程

1×28×28是C(channle)×W(width)×H(Hight)，就是通道数×图像宽度×图像高度

 

①单通道卷积（矩阵数乘）

②三通道卷积

 

③N通道卷积

每一个卷积核的通道数量 = 输入的通道数量

卷积核的个数 = 输出的通道数量

 

 

 

 4、下采样（subsampling）---Max Pooling

下采样的目的是减少特征图像的数据量，降低运算需求。在下采样过程中，通道数（Channel）保持不变，图像的宽度和高度发生改变

 

 

5、全连接层

先将原先多维的卷积结果通过全连接层转为一维的向量，再通过多层全连接层将原向量转变为可供输出的向量。

 

卷积和下采样都是在特征提取

全连接层才是分类

 

6、CNN

①卷积操作

Pytorch输入数据必须是小批量数据，设置batch_size

需要确定的值：输入的通道（in_channels）、输出的通道（out_channels）、卷积核的大小（kernel_size:3x3）

 

②Padding，向外填充

 

 ③Stride—步长

有效降低图像的宽度和高度

 

 

 ④下采样：Max Pooling Layer

默认Stride=2

 

 ⑤整体结构

 

 

 

 ⑥用CPU或GPU进行模型的训练和测试

torch.device

 

 

 

 

 

 

完整代码

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
 
# prepare dataset
 
batch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])
 
train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)
 
# design model using class
 
 
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):
        # flatten data from (n,1,28,28) to (n, 784)
        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) # -1 此处自动算出的是320
        x = self.fc(x)
 
        return x
 
 
model = Net()
## Device—选择是用GPU还是用CPU训练
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)
 
# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
 
# training cycle forward, backward, update
 
 
def train(epoch):
    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():
    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('accuracy on test set: %d %% ' % (100*correct/total))
 
 
if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()

 

运行结果