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

Posted ☆下山☆

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了《PyTorch深度学习实践8》——卷积神经网络(Convolution Neural Network)相关的知识,希望对你有一定的参考价值。

目录

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:

我们也可以这样表示:

也就是说,我们有一张n55n*5*5的图像,可以用一个n33n*3*3的卷积核,得到一张1331*3*3的特征图像:

       假如我们有nwidthinheightinn*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mwidthoutheightoutm*width_out*height_out的图像。而此时这个卷积核可以是4维张量,为mnkernel_sizewidthkernel_sizeheightm*n*kernel\\_size_width*kernel\\_size_height

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)

2.卷积层参数

padding=1是对输入边界外1层填充0(55>775*5—>7*7),然后可以得到输出也是555*5

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)

二、池化层

Max Pooling Layer:

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)

三、MNIST分类

1.网络结构


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:
Python 深度学习6:PyTorch 卷积神经网络

深入浅出卷积神经网络及实现!

Pytorch与深度学习 —— 8. 什么是循环神经网络(Recurrent Neural Network)

PyTorch深度学习实战 | 典型卷积神经网络

深度学习:《PyTorch入门到项目实战》卷积神经网络:填充(padding)和步幅(stride)

3. 使用PyTorch深度学习库训练第一个卷积神经网络CNN