Pytorch框架下训练MNIST
时间: 2023-09-09 20:13:11 浏览: 46
首先,我们需要导入必要的包和库:
```
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
```
接着,我们需要定义一些超参数,包括学习率、训练轮数、批次大小等等:
```
batch_size = 64
learning_rate = 0.01
num_epochs = 10
```
然后,我们需要加载MNIST数据集:
```
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5,), (0.5,))])
trainset = torchvision.datasets.MNIST(root='./data', train=True,
download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size,
shuffle=True, num_workers=2)
testset = torchvision.datasets.MNIST(root='./data', train=False,
download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=batch_size,
shuffle=False, num_workers=2)
```
接下来,我们需要定义模型。在本例中,我们选择使用一个简单的两层神经网络:
```
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.fc1 = nn.Linear(784, 128)
self.relu = nn.ReLU()
self.fc2 = nn.Linear(128, 10)
def forward(self, x):
x = x.view(-1, 784)
x = self.relu(self.fc1(x))
x = self.fc2(x)
return x
net = Net()
```
然后,我们需要定义损失函数和优化器:
```
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=learning_rate, momentum=0.9)
```
现在,我们可以开始训练:
```
for epoch in range(num_epochs): # loop over the dataset multiple times
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = data
# 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 % 200 == 199: # print every 200 mini-batches
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / 200))
running_loss = 0.0
print('Finished Training')
```
最后,我们可以在测试集上测试我们的模型:
```
correct = 0
total = 0
with torch.no_grad():
for data in testloader:
images, labels = data
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))
```
完整代码如下:
```
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
batch_size = 64
learning_rate = 0.01
num_epochs = 10
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5,), (0.5,))])
trainset = torchvision.datasets.MNIST(root='./data', train=True,
download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size,
shuffle=True, num_workers=2)
testset = torchvision.datasets.MNIST(root='./data', train=False,
download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=batch_size,
shuffle=False, num_workers=2)
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.fc1 = nn.Linear(784, 128)
self.relu = nn.ReLU()
self.fc2 = nn.Linear(128, 10)
def forward(self, x):
x = x.view(-1, 784)
x = self.relu(self.fc1(x))
x = self.fc2(x)
return x
net = Net()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=learning_rate, momentum=0.9)
for epoch in range(num_epochs): # loop over the dataset multiple times
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = data
# 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 % 200 == 199: # print every 200 mini-batches
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / 200))
running_loss = 0.0
print('Finished Training')
correct = 0
total = 0
with torch.no_grad():
for data in testloader:
images, labels = data
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))
```
相关推荐
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![txt](https://img-home.csdnimg.cn/images/20210720083642.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![-](https://csdnimg.cn/download_wenku/file_type_column_c1.png)
![-](https://csdnimg.cn/download_wenku/file_type_column_c1.png)
![-](https://csdnimg.cn/download_wenku/file_type_column_c1.png)
![-](https://csdnimg.cn/download_wenku/file_type_column_c1.png)
![-](https://csdnimg.cn/download_wenku/file_type_column_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)