zzm

CNN(卷积神经网络)
最近在学习深度学习,这里记录一下一、cnn结构先来一个简单的示意图:一个卷积神经网络由若干卷积层、池化层、全连接层...
扫描右侧二维码阅读全文
23
2018/06

CNN(卷积神经网络)

最近在学习深度学习,这里记录一下

一、cnn结构

先来一个简单的示意图:
图1

一个卷积神经网络由若干卷积层、池化层、全连接层组成。常用的结构如下:

( 卷积层n+池化层? ) m + 全连接层 * k

也就是多个卷积层后面跟1个或者0个池化层,重复这个结构m次,最后再接k个全连接层。图1的结构也就是:

卷积层->池化层->卷积层->池化层->全连接层*2

也就是n=1,m=2,k=2

二、cnn卷积层

假设有一个5 * 5的图像,使用一个3 * 3的卷积核进行卷积,想得到一个3 * 3的Feature Map,如下所示:

二、pytorch实现cnn

这里使用了一个官网的例子,识别CIFAR10数据集中的图片类别

#coding: utf-8
import torch
import torchvision
import torchvision.transforms as transforms

#GPU可用时用GPU,否则使用CPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)

transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])


# 读取CIFAR10训练数据集
trainset = torchvision.datasets.CIFAR10(root='../data', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
                                          shuffle=True, num_workers=2)

# 读取CIFAR10测试数据集
testset = torchvision.datasets.CIFAR10(root='../data', train=False,
                                       download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,
                                         shuffle=False, num_workers=2)

classes = ('plane', 'car', 'bird', 'cat',
           'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

import torch.nn as nn
import torch.nn.functional as F


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        #卷积层
        self.conv1 = nn.Conv2d(3, 6, 5)
        #池化
        self.pool = nn.MaxPool2d(2, 2)
        #卷积层
        self.conv2 = nn.Conv2d(6, 16, 5)
        #全连接层
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

net = Net().to(device)

import torch.optim as optim

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
for epoch in range(2):
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the inputs
        inputs, labels = data
        inputs, labels = inputs.to(device), labels.to(device)
        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        if i % 2000 == 1999:    # print every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

print('Finished Training')

correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data
        images, labels = images.to(device), labels.to(device)
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %d %%' % (
    100 * correct / total))
Last modification:February 7th, 2019 at 07:12 pm

Leave a Comment