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

巴特西

Pytorch实战学习(六)：基础CNN

最新文章

热门文章