《PyTorch深度学习实战》第十一讲

最新推荐文章于 2024-06-17 18:07:58 发布

原创最新推荐文章于 2024-06-17 18:07:58 发布 · 295 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#pytorch #深度学习 #神经网络

Python 同时被 2 个专栏收录

82 篇文章

订阅专栏

PyTorch

24 篇文章

订阅专栏

本文介绍了如何使用GoogLeNet的Inception模块和ResNet的残差网络结构改进基础模型，实现在MNIST数据集上超过99%的训练精度。通过代码实例展示了如何构建InceptionA模块和ResidualBlock，以及整个训练和测试流程。

Advanced CNN

传送门：https://www.bilibili.com/video/BV1Y7411d7Ys?p=11

基础的网络无法很大程度上限制了我们的发挥，高级的网络能够有效的提升训练模型的精度，本节采用了GoogLeNet中的`Inception`主干网络和`ResNet`残差主干网络，经过调试，训练精度均在99%以上。

GoogLeNet

在这里插入图片描述

Inception Module

在这里插入图片描述

代码

import torch
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision import datasets
import torch.nn.functional as F
import torch.optim as optim
import matplotlib.pyplot as plt

#1.prepare dataset
#2.design model using class
#3.construct loss and optimizer
#4.training cycle+test

#1.准备数据集

batch_size = 64
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307, ), (0.3081, ))#均值，标准化
])
train_dataset = datasets.MNIST(root='./dataset/mnist',
                               train=True,
                               transform=transform,
                               download=True)
print(train_dataset[0])
test_dataset = datasets.MNIST(root='./dataset/mnist',
                              train=False,
                              transform=transform,
                              download=True)

train_loader = DataLoader(dataset=train_dataset,
                          batch_size=32,
                          shuffle=True)
test_loader = DataLoader(dataset=test_dataset,
                         batch_size=32,
                         shuffle=False)
#---------------------Inception-----------------------
class InceptionA(torch.nn.Module):
    def __init__(self, in_channels):
        super(InceptionA, self).__init__()
        self.branch1x1 = torch.nn.Conv2d(in_channels, 16, kernel_size=1)

        self.branch5x5_1 = torch.nn.Conv2d(in_channels, 16, kernel_size=1)
        self.branch5x5_2 = torch.nn.Conv2d(16, 24, kernel_size=5, padding=2)

        self.branch3x3_1 = torch.nn.Conv2d(in_channels, 16, kernel_size=1)
        self.branch3x3_2 = torch.nn.Conv2d(16, 24, kernel_size=3, padding=1)
        self.branch3x3_3 = torch.nn.Conv2d(24, 24, kernel_size=3, padding=1)

        self.branch_pool = torch.nn.Conv2d(in_channels, 24, kernel_size=1)

    def forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch5x5 = self.branch5x5_1(x)
        branch5x5 = self.branch5x5_2(branch5x5)

        branch3x3 = self.branch3x3_1(x)
        branch3x3 = self.branch3x3_2(branch3x3)
        branch3x3 = self.branch3x3_3(branch3x3)

        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)

        outputs = [branch1x1, branch5x5, branch3x3, branch_pool]
        return torch.cat(outputs, dim=1)
        
model = Net()
# 开启显卡
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

#3.构建loss和optimzer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

#4.循环
def train(epoch):
    running_loss = 0.0
    for batch_idx, (inputs, target) in enumerate(train_loader):
        inputs, target = inputs.to(device), target.to(device) #显卡加速

        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: %d %%' % (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)
        # if epoch % 10 == 9:
        #     test()
    import os
    os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE'
    plt.plot(epoch_list, acc_list)
    plt.xlabel('epoch')
    plt.ylabel('accuracy')
    plt.show()

ResNet

在这里插入图片描述

import torch
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision import datasets
import torch.nn.functional as F
import torch.optim as optim
import matplotlib.pyplot as plt

#1.prepare dataset
#2.design model using class
#3.construct loss and optimizer
#4.training cycle+test

#1.准备数据集

batch_size = 64
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307, ), (0.3081, ))#均值，标准化
])
train_dataset = datasets.MNIST(root='./dataset/mnist',
                               train=True,
                               transform=transform,
                               download=True)
print(train_dataset[0])
test_dataset = datasets.MNIST(root='./dataset/mnist',
                              train=False,
                              transform=transform,
                              download=True)

train_loader = DataLoader(dataset=train_dataset,
                          batch_size=32,
                          shuffle=True)
test_loader = DataLoader(dataset=test_dataset,
                         batch_size=32,
                         shuffle=False)

#--------------------------RestNet------------------------
class ResidualBlock(torch.nn.Module):
    def __init__(self, channels):
        super(ResidualBlock, self).__init__()
        self.channels = channels
        self.conv1 = torch.nn.Conv2d(channels, channels, kernel_size=3, padding=1)
        self.conv2 = torch.nn.Conv2d(channels, channels, kernel_size=3, padding=1)

    def forward(self, x):
        y = F.relu(self.conv1(x))
        y = self.conv2(y)
        return F.relu(x + y)

class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 16, kernel_size=5)
        self.conv2 = torch.nn.Conv2d(16, 32, kernel_size=5)
        self.mp = torch.nn.MaxPool2d(2)

        self.rblock1 = ResidualBlock(16)
        self.rblock2 = ResidualBlock(32)

        self.fc1 = torch.nn.Linear(512, 256)
        self.fc2 = torch.nn.Linear(256, 128)
        self.fc3 = torch.nn.Linear(128, 64)
        self.fc4 = torch.nn.Linear(64, 10)

    def forward(self, x):
        in_size = x.size(0)
        x = self.mp(F.relu(self.conv1(x)))
        x = self.rblock1(x)
        x = self.mp(F.relu(self.conv2(x)))
        x = self.rblock2(x)
        x = x.view(in_size, -1)
        x = self.fc1(x)
        x = self.fc2(x)
        x = self.fc3(x)
        x = self.fc4(x)
        return x
        
model = Net()
# 开启显卡
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

#3.构建loss和optimzer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

#4.循环
def train(epoch):
    running_loss = 0.0
    for batch_idx, (inputs, target) in enumerate(train_loader):
        inputs, target = inputs.to(device), target.to(device) #显卡加速

        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: %d %%' % (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)
        # if epoch % 10 == 9:
        #     test()
    import os
    os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE'
    plt.plot(epoch_list, acc_list)
    plt.xlabel('epoch')
    plt.ylabel('accuracy')
    plt.show()