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
Inception Module
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
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()