《PyTorch深度学习实践8》——卷积神经网络-基础篇（Basic-Convolution Neural Network）

一、卷积层

1.卷积层理解

假如我们有一张图像，RGB三通道，我们对每个通道都用一个卷积核，就可以得到三个通道的特征图，之后我们可以将这三个特征图进行简单叠加，就可以得到一张特征图。如下所示：
在这里插入图片描述

我们也可以这样表示：
在这里插入图片描述

也就是说，我们有一张 $n * 5 * 5$ 的图像，可以用一个 $n * 3 * 3$ 的卷积核，得到一张 $1 * 3 * 3$ 的特征图像：
在这里插入图片描述

假如我们有 $n*width_{in}*height_{in}$ 的图像，我们可以使用m个卷积核，得到m张特征图像，之后我们可以对这m张特征图像进行串联，就可以得到 $m*width_{out}*height_{out}$ 的图像。而此时这个卷积核可以是4维张量，为 $m*n*kernel\_size_{width}*kernel\_size_{height}$
在这里插入图片描述

这段程序是torch.nn.Conv2d的简单用法：

import torch

in_channels, out_channels= 5, 10
width, height = 100, 100
kernel_size = 3
batch_size = 1

input = torch.randn(batch_size, in_channels, width, height)
conv_layer = torch.nn.Conv2d(in_channels, out_channels, kernel_size=kernel_size)
output = conv_layer(input)

print(input.shape)
print(output.shape)
print(conv_layer.weight.shape)

在这里插入图片描述

2.卷积层参数

padding=1是对输入边界外1层填充0（ $5 * 5— > 7 * 7$ ），然后可以得到输出也是 $5 * 5$
在这里插入图片描述
stride=2表示卷积过程每次移动步长为2

这段程序对上述结果进行验证：

import torch

input = [3,4,6,5,7,
        2,4,6,8,2,
        1,6,7,8,4,
        9,7,4,6,2,
        3,7,5,4,1]
input = torch.Tensor(input).view(1, 1, 5, 5)

# padding
conv_layer1 = torch.nn.Conv2d(1, 1, kernel_size=3, padding=1, bias= False)
kernel = torch.Tensor([1,2,3,4,5,6,7,8,9]).view(1, 1, 3, 3)
conv_layer1.weight.data = kernel.data
output1 = conv_layer1(input)
print("output1：",output1)

# stride
conv_layer2 = torch.nn.Conv2d(1, 1, kernel_size=3, stride=2, bias= False)
kernel = torch.Tensor([1,2,3,4,5,6,7,8,9]).view(1, 1, 3, 3)
conv_layer2.weight.data = kernel.data
output2 = conv_layer2(input)
print("output2：",output2)

在这里插入图片描述

二、池化层

Max Pooling Layer：
在这里插入图片描述

import torch

input = [3,4,6,5,
        2,4,6,8,
        1,6,7,8,
        9,7,4,6,]

input = torch.Tensor(input).view(1, 1, 4, 4)
maxpooling_layer = torch.nn.MaxPool2d(kernel_size=2)
output = maxpooling_layer(input)

print(output)

在这里插入图片描述

三、MNIST分类

1.网络结构

在这里插入图片描述

2.CPU版本

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='', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='', 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 = self.pooling(F.relu(self.conv1(x)))
        x = self.pooling(F.relu(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()

# 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
        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: %.2f %% ' % (100 * correct / total))

if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()

3.GPU版本

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
import matplotlib.pyplot as plt

# prepare dataset
batch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])

train_dataset = datasets.MNIST(root='', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='', 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
        # print("x.shape",x.shape)
        x = self.fc(x)

        return x

model = Net()
device = torch.device("cuda") # torch.device("cuda" 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: %.2f %% ' % (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)

    plt.plot(epoch_list, acc_list)
    plt.ylabel('accuracy')
    plt.xlabel('epoch')
    plt.show()

部分结果：
在这里插入图片描述

可视化：
在这里插入图片描述

本文为系列文章：

上一篇	《Pytorch深度学习实践》目录	下一篇
MNIST数据集多分类（Softmax Classifier）	资料	卷积神经网络-高级篇（Advanced-Convolution Neural Network）