目录
选择下图结构的卷积神经网络来进行训练:
步骤:
- 选择 5 x 5 的卷积核,输入通道为 1,输出通道为 10:此时图像矩阵经过 5 x 5 的卷积核后会小两圈,也就是4个数位,变成 24 x 24,输出通道为10;
- 选择 2 x 2 的最大池化层:此时图像大小缩短一半,变成 12 x 12,通道数不变;
- 再次经过 5 x 5 的卷积核,输入通道为 10,输出通道为 20:此时图像再小两圈,变成 8 *8,输出通道为20;
- 再次经过 2 x 2 的最大池化层:此时图像大小缩短一半,变成 4 x 4,通道数不变;
- 最后将图像整型变换成向量,输入到全连接层中:输入一共有 4 x 4 x 20 = 320 个元素,输出为 10.
具体代码如下:
1 准备数据集
# 准备数据集
batch_size = 64
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])
train_dataset = datasets.MNIST(root='../dataset/mnist/',
train=True,
download=True,
transform=transform)
train_loader = DataLoader(train_dataset,
shuffle=True,
batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist',
train=False,
download=True,
transform=transform)
test_loader = DataLoader(test_dataset,
shuffle=False,
batch_size=batch_size)
2 建立模型
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):
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)
x = self.fc(x)
return x
model = Net()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)
3 构造损失函数+优化器
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
4 训练+测试
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 / 2000))
running_loss = 0.0
def test():
correct=0
total=0
with torch.no_grad():
for data in test_loader:
inputs,target=data
inputs,target=inputs.to(device),target.to(device)
outputs=model(inputs)
_,predicted=torch.max(outputs.data,dim=1)
total+=target.size(0)
correct+=(predicted==target).sum().item()
print('Accuracy on test set:%d %% [%d%d]' %(100*correct/total,correct,total))
if __name__ =='__main__':
for epoch in range(10):
train(epoch)
test()
5 完整代码+运行结果
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
# 准备数据集
batch_size = 64
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])
train_dataset = datasets.MNIST(root='../dataset/mnist/',
train=True,
download=True,
transform=transform)
train_loader = DataLoader(train_dataset,
shuffle=True,
batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist',
train=False,
download=True,
transform=transform)
test_loader = DataLoader(test_dataset,
shuffle=False,
batch_size=batch_size)
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):
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)
x = self.fc(x)
return x
model = Net()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
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 / 2000))
running_loss = 0.0
def test():
correct=0
total=0
with torch.no_grad():
for data in test_loader:
inputs,target=data
inputs,target=inputs.to(device),target.to(device)
outputs=model(inputs)
_,predicted=torch.max(outputs.data,dim=1)
total+=target.size(0)
correct+=(predicted==target).sum().item()
print('Accuracy on test set:%d %% [%d%d]' %(100*correct/total,correct,total))
if __name__ =='__main__':
for epoch in range(10):
train(epoch)
test()
运行结果如下: