PyTorch实现逻辑斯蒂回归
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
# 超参数设置
input_size = 784
num_classes = 10
num_epochs = 5
batch_size = 100
learning_rate = 0.001
#手写数字图片数据集
train_dataset = torchvision.datasets.MNIST(root='../data',
train=True,
transform=transforms.ToTensor(),
download=True)
test_dataset = torchvision.datasets.MNIST(root='../data',
train=False,
transform=transforms.ToTensor())
# 加载数据
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=False)
# LR模型
model = nn.Linear(input_size, num_classes)
# 损失函数和优化器
# nn.CrossEntropyLoss() computes softmax internally
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
# 训练模型
total_step = len(train_loader)
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
images = images.reshape(-1, 28*28)
# 前向传播
outputs = model(images)
loss = criterion(outputs, labels)
# 后向传播、优化求解
optimizer.zero_grad()
loss.backward()
optimizer.step()
if (i+1) % 100 == 0:
print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
.format(epoch+1, num_epochs, i+1, total_step, loss.item()))
# 测试
with torch.no_grad():
correct = 0
total = 0
for images, labels in test_loader:
images = images.reshape(-1, 28*28)
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum()
print('准确率: {} %'.format(100 * correct / total))
# 保存模型
torch.save(model.state_dict(), 'model.ckpt')
参考资料
https://github.com/yunjey/pytorch-tutorial