In [1]:
import torch
import torch.nn as nn
import torchvision.datasets as dsets
import torchvision.transforms as transforms
from torch.autograd import Variable
In [2]:
input_size = 784
num_classes = 10
num_epochs = 5
batch_size = 100
learning_rate = 0.001
In [4]:
train_dataset = dsets.MNIST(root='./data',
train=True,
transform=transforms.ToTensor(),
download=True)
In [6]:
test_dataset = dsets.MNIST(root='./data',
train=False,
transform=transforms.ToTensor())
In [19]:
print(len(train_dataset))
print(len(test_dataset))
In [8]:
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
In [9]:
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=False)
In [10]:
class LogisticRegression(nn.Module):
def __init__(self, input_size, num_classes):
super(LogisticRegression, self).__init__()
self.linear = nn.Linear(input_size, num_classes)
# softmaxは CrossEntropyLoss() で計算されるのでここではlogitのみ
def forward(self, x):
out = self.linear(x)
return out
In [12]:
model = LogisticRegression(input_size, num_classes)
In [13]:
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
In [20]:
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
images = Variable(images.view(-1, 28 * 28))
labels = Variable(labels)
optimizer.zero_grad()
outputs = model(images)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
if (i + 1) % 100 == 0:
print('Epoch: [%d/%d], Step: [%d/%d], Loss: %.4f' % (
epoch + 1, num_epochs, i + 1, len(train_dataset) // batch_size, loss.data[0]))
In [25]:
correct = 0
total = 0
for images, labels in test_loader:
images = Variable(images.view(-1, 28 * 28))
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum()
In [26]:
correct
Out[26]:
In [27]:
print('Accuracy of the model on the 10000 test images: %d %%' % (100 * correct / total))
In [28]:
torch.save(model.state_dict(), 'model.pkl')
In [ ]: